# Research Papers — 2026-07 · bundle page 21 of 222

> Full-text markdown of papers #1001–1050 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-07/page/21
[← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/20.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-07/page/22.md)

### From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake News

Authors: Zeynep Özdemir, Murat Osmanoğlu, Sevgi Yiğit-Sert, Ömer Özgür Tanrıöver, Yılmaz Ar
Published: 2026-07-29
Categories: cs.CL
arXiv: https://arxiv.org/abs/2609.20838v1

In this study, we examine how modern LLMs generate and detect fake news under controlled settings across four manipulation scenarios. These are open-ended generation, rewriting, manipulation prompts and attribute based prompts grounded in the journalistic discourse framework. Firstly, using seven widely adapted models, we created a synthetic fake news corpus with 14000 generated articles across these four scenarios. Then we analyzed its linguistic properties to assess how closely model-generated news resembles real news structurally and semantically. Finally, to evaluate detection performance, we conducted experiments where each model judges generated fake news, starting with a basic detection prompt and improved prompts developed through an iterative refinement process that extracts misleading patterns from real-fake pairs. Our results revealed substantial variation across models in both generating and detecting misinformation, demonstrated that the generation strategy strongly influences detectability, and show that the refined prompt does not improve and often harms detection performance. Therefore, the study provides a systematic assessment of LLMs detection capability of LLMs generated fake news across typical generation scenarios.

---

### PhysioBench: A Unified Benchmark for Physiological Signal Question Answering

Authors: Mengxuan Li, Junfa Chen, Jinze Xia, Yundan Chen, Lixin Fan, Ke Liu, Keyue Shi, Haishuai Wang
Published: 2026-07-29
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2609.20836v1

Physiological signals support diverse clinical and monitoring tasks, yet existing physiological signal foundation models typically require task-specific adaptation for each task. Natural language provides a common interface for specifying different prediction objectives, but the ability of current models to follow such instructions across physiological signal modalities remains insufficiently evaluated. To address this gap, we introduce PhysioBench, a unified benchmark for physiological signal question answering. PhysioBench harmonizes annotations from 22 public datasets into 61.4 million questions across 30 tasks. Each question-answer pair is grounded in a signal segment and traceable to its source annotation. We evaluate 21 representative models, including large language models, vision-language models, time-series language models, and physiological signal foundation models under three complementary settings. The results show that none of the evaluated models achieves consistently strong performance across physiological signal modalities and tasks. The incorporation of natural language supports unified prediction across tasks, although performance remains sensitive to question formulation. Beyond these findings, PhysioBench offers an extensible platform for fine-grained analysis and future research on physiological signal understanding. Our codes are available at https://github.com/Leanna97/PhysioBench.

---

### TinyCNN: A 193K-Parameter Network for On-Device Plant Disease Detection, with a Cross-Dataset Robustness Diagnosis

Authors: Ngoc-Bao Ho-Lam, Thai-Anh Nguyen
Published: 2026-07-29
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2609.20290v1

Detecting crop disease early is central to sustainable agriculture and food security under United Nations Sustainable Development Goal 2 (Zero Hunger), and is especially urgent in resource-constrained regions where expert diagnosis is scarce but low-cost mobile devices are widespread. This paper presents TinyCNN, a lightweight convolutional neural network for on-device plant disease classification. TinyCNN uses depthwise separable convolution blocks and contains only 193,190 trainable parameters with 110.05M MACs for a 224x224 input image. On the 38-class PlantVillage benchmark, TinyCNN achieves 98.88% test accuracy and 98.03% macro-F1 while being approximately 58x smaller than ResNet18 and 11.8x smaller than a MobileNetV2 teacher, directly reducing the energy, memory, and cost footprint of inference in line with Green AI principles. The paper further analyzes vanilla knowledge distillation as a sustainable model-compression strategy; an ablation over alpha in {0.3, 0.5, 0.7} and T in {2, 4} selects alpha=0.3, T=4, producing a distilled TinyCNN with 98.81% test accuracy. Finally, cross-dataset evaluation from PlantVillage to PlantDoc reveals a substantial robustness gap under real-world conditions, which a Grad-CAM analysis attributes to off-leaf, background-driven attention consistent with shortcut learning. TinyCNN is thus an energy-efficient, deployable building block for sustainable agricultural intelligence, while field robustness remains the key barrier to durable real-world impact.

---

### Labeled Incidence Structures for Native Transformer Modeling of Text, Knowledge Graphs, and Hypergraphs

Authors: Mahesh Godavarti
Published: 2026-07-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.20278v2

Current Transformer interfaces index tokens by one or more integer coordinates, which determine their addresses inside attention. In RoPE and its multi-axis or hierarchical variants, the resulting address has the form $A(i)=R_1^{i_1}R_2^{i_2}R_3^{i_3}$, where the exponents are integer coordinates assigned after choosing a serialized token layout. When Transformers process new or large collections of data, this addressing scheme can produce unseen offsets or coordinate combinations, push repositories toward retrieve-and-serialize pipelines, and force new entities, records, or repository items to be represented by long token strings or identifier embeddings not seen in training. We introduce labeled incidence structures (LIS), in which each participating token or value is an endpoint with content $x$ and a structural index $i$. The index can include local position, relation role, relation instance, text unit, field, or content-derived identity. The model maps this index to a structural address $A(i)$, so adding new tokens, facts, text units, or repository items applies the same learned address rule to structural and content coordinates rather than requiring larger integer coordinates, unseen coordinate combinations, or new identifier embeddings. Attention scores endpoints $i,j$ using $q_i^\top P_{j\to i}k_j$, where journey consistency forces $P_{j\to i}=A(i)^{-1}A(j)$. When $i$ has several coordinates, such as position, role, and instance, coordinate independence is equivalent to factoring $A(i)$ into one address factor per coordinate. This recovers RoPE, RoPE-2D, and HiRoPE as special cases. This allows knowledge-graph (KG) roles, fact instances, and text units to enter the attention score directly. In controlled shallow diagnostics, the LIS address interface is implemented inside ordinary Transformer attention and yields promising results across text, KG, and $n$-ary settings.

---

### Memoization Without Keys: Compact, Out-of-Core Tables for Functions of Sorted Arguments

Authors: Tamal Maharaj
Published: 2026-07-29
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2609.20276v2

Memoizing an expensive function of a sorted score vector is a data-structure problem before it is a numerical one: at a billion gridpoints, a hash map or a search tree spends most of its space on keys the grid already determines. We describe an implemented memo table that stores none. An entry's address is computed in closed form from the sorted argument itself, so $N$ values occupy $N$ slots, the argument is recoverable from the index, and the table can be memory-mapped and served from a file larger than RAM. Against a chained hash map it uses $5.7\times$ less memory at $37$M entries and $10.2\times$ less at $1.9$B, answers queries up to $2.9\times$ faster and builds up to $250\times$ faster; on 64 threads its construction needs no coordination; a sharded hash gains only $1.17\times$. Against an open-addressing table with inline keys it is $4$--$7\times$ smaller and $100\times$ faster to build but $1.5\times$ slower to query, a deficit we trace to the $O(d)$ index arithmetic. At $22$ GB on a $16$ GB desktop it serves each query in one disk access, where no key-storing container can be built; and its order-preserving addressing keeps a perturbation workload on the same pages that a hashed layout scatters. The closed form exists because the key set is the multiset combinations, whose index is the combinatorial number system. Memoizing Plackett--Luce normalization runs $25$--$55\times$ faster than Newton's method; memoizing $α$-entmax thresholds does not pay. The contrast says when this structure is worthwhile.

---

### A Multi-Objective Optimisation Framework for Corticomuscular EEG-EMG Pair Selection in Hybrid BCI

Authors: Dekka Muni Kumar, Yogesh Kumar Meena
Published: 2026-07-29
Categories: cs.HC, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2609.20275v1

Hybrid brain-computer interface (BCI) systems that integrate electroencephalography (EEG) and electromyography (EMG) signals have shown significant potential in improving the reliability of motor imagery (MI) classification, particularly in neuro-rehabilitation applications. However, identifying informative EEG-EMG channel pairs that effectively capture corticomuscular interactions remains a challenging problem, as existing approaches typically rely on manually predefined channel combinations that may not generalise across subjects. In this work, a data-driven EEG-EMG pair selection framework is proposed, in which channel pair selection is formulated as a constrained bi-objective optimisation problem. The proposed method jointly maximises the spatial relevance of EEG channels with respect to motor cortex regions and the corticomuscular coupling strength between EEG and EMG signals, and is solved using the NSGA-II to automatically identify an optimal subset of pairs. To extract discriminative features, the correlation between band-power time features capturing EEG-EMG interaction is combined with ERD-based EEG features, and a sliding-window-based temporal analysis is employed to account for the dynamic nature of MI signals. The proposed framework is evaluated on MI data from eight stroke patients and achieves an average classification accuracy of 89.6%, demonstrating its effectiveness in capturing physiologically meaningful corticomuscular interactions and improving classification performance.

---

### AI-Driven Real-Time Relay Optimisation in Smart Urban NR-V2X Networks via Learning-to-Optimise Graph Neural Networks

Authors: Giambattista Amati, Federica Mangiatordi, Emiliano Pallotti, Simone Angelini
Published: 2026-07-29
Categories: cs.AI, cs.LG, cs.NI
arXiv: https://arxiv.org/abs/2609.20271v1

Reliable and low-latency communication is a fundamental requirement for smart city services and Industry 4.0 applications enabled by NR-V2X networks. However, limited Road-Side Unit (RSU) deployment and complex urban propagation conditions often prevent Connected and Automated Vehicles (CAVs) from maintaining stable connectivity. This paper proposes an AI-driven Learning-to-Optimise (L2O) framework based on Graph Neural Networks (GNNs) for real-time multi-hop relay selection in NR-V2X systems. The vehicular network is modelled as a graph, where nodes represent CAVs and RSUs, and edges encode radio-link characteristics. An offline Mixed-Integer Linear Programming (MILP) formulation provides optimal relay decisions used as supervision for training an edge-aware Graph Isomorphism Network with Edge Features (GINE). Extensive experiments on realistic urban datasets demonstrate that the proposed approach achieves near-optimal connectivity performance, recovering up to 11.3% connectivity gain, while reducing execution time by orders of magnitude (up to 100 x speed-up) compared to MILP. The framework enables scalable and real-time network control, making it suitable for smart city and Industry 4.0 deployments.

---

### Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks

Authors: Taebong Kim, Youngsik Hong, Minsik Kim, Sunyoung Choi, Jaewon Jang, Minseo Kim
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20269v2

Since GPT, most Transformers have repeated the same attention mechanism at every layer. Yet this design is largely a convention rather than a tested conclusion. When multiple sequence mixers are combined in one stack, improvements may arise from mechanism choice, placement, or both, making causal attribution difficult. We introduce Aether-7B-5Attn, a 6.59B-parameter mixture-of-experts model ($\approx$2.98B active) whose 49 layers contain seven sequence-mixing mechanisms arranged as a $7\times7$ Latin square. Because each mechanism appears exactly once in every row and column, the design guarantees balanced exposure across depth while eliminating placement confounds. To evaluate this principle, we build a parameter-matched proxy with four mechanisms arranged as a $4\times4$ Latin square over sixteen layers, matched to 700.9M parameters and trained with eight seeds per arm. The results reveal a clear dissociation. Rearranging a distributed heterogeneous stack into a balanced periodic cycle changes validation loss by only 0.16\%, indicating that exact placement has little effect. In contrast, clustering the same mechanisms into contiguous depth bands incurs a 0.59\% penalty, while replacing the heterogeneous stack with a homogeneous one incurs a 1.68\% penalty. These results indicate that performance depends primarily on heterogeneous composition distributed across depth rather than on any particular permutation. We confirm this finding at 2.16$\times$ larger scale (1.514B parameters), where the homogeneous-stack penalty increases to 2.63\% and removing the SSM-family mechanism produces a 3.20\% degradation. We further report per-mechanism cost profiles, English and Korean evaluations, and a causal-safety audit of all 49 layers. We release model weights, training recipes, training code, logs, and architecture source code.

---

### Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation

Authors: Gong Gao, Xiao Lai, Jiaji Shen, Ning Jia, Xianhui Liu, Weidong Zhao
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20268v1

Online reinforcement learning (RL) algorithms frequently exhibit poor sample efficiency and unstable learning dynamics, stemming from systematic critic estimation errors that are exacerbated by greedy policy updates. Existing behavior-prior reinforcement learning methods attempt to alleviate this issue by relying on offline pre-training to learn behavior models from fixed datasets and using policy priors to constrain online policy updates. However, the limited quality of offline datasets often hinders the ability to provide high-value policies that can effectively guide policy updates. The absence of expert trajectories significantly impairs online policy learning, leading to low sample efficiency and suboptimal performance. To address these challenges, we depart from conventional behavior prior approaches and propose a Bidirectional Behavior Prior Distillation (B2PD) algorithm. B2PD leverages action-value priors to guide a conditional variational autoencoder (CVAE) in generating a high-value behavior support set. The resulting expert behavior priors are further distilled into the agent, effectively reducing inefficient exploration and enabling stable policy optimization, while establishing a bidirectional knowledge flow mechanism. Empirical evaluations on both state- and pixel-based tasks verify that B2PD substantially improves sample efficiency while maintaining stable policy optimization. More broadly, this work shows that enforcing high-quality behavioral support during online learning effectively mitigates critic-induced error amplification, enabling structured behavior priors to guide policy updates in a principled and sample-efficient manner.

---

### CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models

Authors: Junchi Liao, Hongji Li, Wenrui Zhou, Lijie Hu
Published: 2026-07-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2609.20267v1

Concept erasure aims to selectively eliminate undesired visual semantics from pre-trained generative models without compromising their general utility. Extending concept erasure from images to video is nontrivial. Target concepts emerge gradually and vary across frames and denoising steps. As a result, fixed interventions may miss the target or introduce blurring, jitter, and content distortion. We propose CleanVideo, a selective erasure framework that performs low-dimensional subspace intervention controlled by a tri-modal gating mechanism. By jointly processing spatiotemporal visual features, timestep signals, and textual semantics, CleanVideo determines where, when, and whether to intervene, steering erased content toward natural surrogate concepts when such surrogates can be clearly defined while preserving non-target content. Experiments on three video diffusion models show that CleanVideo effectively erases target concepts while maintaining visual fidelity and temporal coherence, outperforming existing baselines under frame-level and video-level evaluations and under concept-recovery attacks when the protected pipeline remains intact.

---

### Risk-Set Transported Synthetic Control with Difference-in-Differences Adjustment under Staggered Treatment Adoption

Authors: Mojtaba Eslami
Published: 2026-07-29
Categories: stat.AP, cs.AI, econ.EM, q-fin.ST, stat.ME
arXiv: https://arxiv.org/abs/2609.20264v1

In staggered treatment-adoption designs, later-treated units are valid controls for an earlier-treated cohort only until their own treatment begins, so the admissible donor set contracts with event time. Fixing the donor pool at the longest horizon discards temporarily eligible donors, whereas re-estimating synthetic-control weights independently at each horizon can make the counterfactual unstable as donor composition changes. We propose Risk-Set Transported Synthetic Control with Difference-in-Differences Adjustment (RT-SC-DiD). For each cohort and event-time horizon, the estimator fits weights on the currently untreated donors while shrinking them toward a transported reference that reallocates the weight of exiting donors to similar surviving donors. A DiD baseline correction removes persistent level differences. We characterize distortion from horizon-by-horizon reoptimization, derive the loading change induced by naive deletion and renormalization, and give a conditional recursive bound for error propagation under an explicitly assumed regularity condition on the transport map. We also introduce donor-support diagnostics and a donor-only placebo procedure for selecting the transport penalty. In an 80-replication pilot comparison and a separate 40-replication-per-value sensitivity analysis, intermediate transport regularization reduces average RMSE relative to independent horizon-specific estimation and strong anchoring. This evidence supports the method's bias-variance motivation but is not a proved guarantee. RT-SC-DiD is intended for settings where later-treated units provide useful short-horizon information and donor support contracts materially over time. Existing staggered synthetic-control and synthetic difference-in-differences methods do not, to our knowledge, explicitly regularize within-cohort weight sequences toward transported references as risk sets contract.

---

### How Far Can Sub-3B Open Language Models Go in Zero-Shot Essay Scoring on an 8 GB Consumer GPU?

Authors: Nguyen Dung Son, Dang Quang Minh, Nguyen Huu Loi, Truong Viet Vu, Nguyen Thai Anh
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20250v1

Zero-shot essay scoring with large language models is usually demonstrated with proprietary API models, yet the settings where automated scoring is most needed, such as public schools grading thousands of essays under strict privacy rules, are often those where sending student writing to a third-party API is unacceptable. We ask how much capability survives when the model must be a sub-3B open model running fully locally in FP16, with a controlled study of four instruction-tuned models from two families (Qwen2.5 at 0.5B/1.5B/3B, SmolLM2 at 1.7B) on all eight ASAP-AES prompts on a single 8 GB consumer GPU, with bootstrap confidence intervals, Holm-corrected paired tests, and deployment-realistic variants of the key design choices. Three findings emerge. (i) Rubric-decomposed prompting beats holistic prompting for every model under batch min-max aggregation (though Qwen2.5-3B drops significantly on one prompt), and under mean aggregation two unrelated families land within 0.01 at the 1.5-1.7B scale. (ii) Mapping trait scores into the prompt range is fragile to grader calibration: one model compresses traits into a narrow low band (2-4 on 0-10) and naive mean aggregation collapses, while the min-max normalization of Multi-Trait Specialization repairs it (macro QWK 0.204 to 0.388) and stays within 0.03 when its statistics are frozen on 30 held-out essays. (iii) Signed error falls with essay length in eleven of twelve configurations, opposite to the verbosity bias reported for large LLM judges; normalized rubric decomposition largely flattens this slope for well-calibrated models. We anchor results honestly: the best local configuration (0.388) remains far below both the human inter-rater ceiling (0.769) and a length-only baseline (0.523), so we position sub-3B local models strictly for formative, human-supervised feedback.

---

### Evaluating Financial Sentiment in the Age of AI

Authors: Arslan Bisharat, Oudom Hean
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.20198v1

Financial sentiment measures are widely used in empirical finance, but it remains unclear whether general-purpose large language models (LLMs) improve on existing finance-specific methods. This paper evaluates twelve sentiment models, including dictionary-based methods, finance-specific transformers, and open-source LLMs, using two criteria: linguistic validity and economic validity. We find that general-purpose LLMs achieve classification performance comparable to finance-specific transformer models without task-specific fine-tuning. However, higher classification accuracy does not translate into stronger economic relationships. Several models produce sentiment measures that are significantly associated with earnings surprises, but none is significantly associated with next-day stock returns. Model performance is strongest for announcements with large earnings beats or misses and substantially weaker for announcements with more moderate earnings surprises. These findings suggest that financial sentiment captures information about firms' economic performance but has limited ability to explain short-run market reactions

---

### When Does Retrieval Help Time-Series Forecasting?

Authors: Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban
Published: 2026-07-29
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2609.20193v1

Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry. Published evaluations report consistent gains, and each credits its own mechanism. We show that the benefit belongs instead to the operating point: the relation between window length $S$ and dominant seasonal period $L$, an axis the standard protocol never varies. Stratifying the evaluation by that relation exposes the regime. At $S{=}12$, a simple control that repeats the last observed period beats the six standard backbones, in aggregate, on four of seven benchmarks by $8\%$ to $44\%$ of MSE. It beats the strongest plug-in we run on ETTm1 and matches it on ECL. It is worse by up to $25\%$ on the three datasets whose training-split spectra lack a concentrated, shared period. A controlled synthetic sweep of horizon, period, and window shows the benefit boundary tracks the period (correlation $+0.71$), not the horizon ($-0.23$). A paired control with no phase to recover nearly erases the effect, consistent with phase starvation. Zero-shot pretraining does not escape it: a foundation model trails trained backbones by $22\%$ to $50\%$ on the periodic benchmarks. Within our instrument, exact lookup matches graph diffusion: the payoff is consulting the record, not the machinery on top. Two interpretable statistics, a trend test and a staleness rate, predict the sign of the per-cell benefit at $0.76$ accuracy under leave-one-dataset-out evaluation, a suggestive margin over the $0.69$ majority rule, where a 22-feature stack manages $0.57$. We propose no new plug-in. The contribution is the regime map, the protocol that reveals it, and two statistics that screen it before deployment. Code: https://github.com/KurbanIntelligenceLab/retrieval-regime.

---

### VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering

Authors: Yixin Peng, Er Jin, Shiwei Luo, Diego Collarana, Stefan Decker
Published: 2026-07-29
Categories: cs.CL, cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2609.19158v1

Knowledge graphs are usually integrated into question answering by encoding a retrieved subgraph with a graph neural network and fusing it with the language model in the online inference path. The same subgraph is therefore re-encoded from scratch every time a pair is scored, across training epochs, seeds, and evaluation runs, even though the knowledge graph never changes. We ask whether the retrieved knowledge graphs can instead be compiled once, offline, and then accessed as read-only memory. VisKG-LM shows that it can, by decoupling graph encoding from language reasoning. It serializes each retrieved candidate-specific subgraph as Relation-Labeled Paths and renders the result as an image whose two-dimensional layout preserves the branching structure of the paths. Each image is encoded once, offline, and cached for reuse. At inference, the language model contextualizes the question and candidate from text alone, and only its final layer consults the cached visual memory, reading both its global layout and its local relational detail. The graph information thus enters only after the text has been understood. On the test sets of CommonsenseQA, OpenBookQA, and MedQA-USMLE, VisKG-LMimproves over GreaseLM by $1.2$, $0.8$, and $4.3$ points, respectively, while matching or surpassing GraphVis, a $7$B vision-language model, with only about $400$M online parameters. Against a matched text-only control that receives the identical Relation-Labeled Paths, it gains $4.2$, $6.5$, and $5.1$ points across the three benchmarks. These gains show that the complete visual-memory interface adds value beyond path textualization alone and support compiled visual memory as an alternative to online graph propagation.

---

### Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives

Authors: Manpreet Singh, Rhythm Bhatia, Rahul Joshi
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2609.17572v1

Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded within archival metadata. In this study, we audit Contrastive Language-Image Pretraining (CLIP) models using historical artwork metadata from the Metropolitan Museum of Art Open Access collection (N = 1,500 total objects; N = 743 attributed works: Male n = 534, Female n = 209; n = 618 anonymous). We establish a quantitative audit framework evaluating zero-shot CLIP logit differential scores across three semantic prompt pairs (masterpiece, quality, and influence). Unadjusted evaluations demonstrate high score convergence without a statistically significant main gender effect under OpenAI CLIP (mu_F = -0.0067 vs mu_M = -0.0035, p = 0.1829) or OpenCLIP (mu_F = 0.0171 vs mu_M = 0.0237, p = 0.1224). Two One-Sided Tests (TOST) confirm statistical equivalence across Cohen's d >= 0.25 bounds (pTOST < 0.005). Multivariate OLS regression controlling for artwork medium, creation era, and aspect ratio (R^2 < 0.02) confirms that artist gender has no statistically significant conditional effect (p > 0.20). High residual embedding variance (R^2 < 2%) indicates that global zero-shot valuation metrics operate near an embedding noise floor, showing that broad zero-shot prompt logit differentials are a coarse measurement instrument rather than proving absolute model fairness. We highlight two key caveats: (i) macro-level score equivalence reflects metric insensitivity to fine-grained visual-semantic features and does not preclude localized micro-level visual biases, and (ii) excluding 41.2% unattributed holdings reflects institutional survival bias. These results demonstrate the necessity of multivariate confound control, equivalence testing, and archival provenance auditing when assessing AI fairness in cultural heritage collections.

---

### Where Grokking Happens: Distributed Utility and Fourier Recoding Without a Module Switch

Authors: Dekun Yang
Published: 2026-07-29
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2609.17571v1

Where in a Transformer is the change from memorization to generalization functionally expressed? We introduce Transition Games--behavior-aligned exact activation games with paired non-generalizing controls--and find distributed utility gain with a prospective block-0 attention bias; selected degree-two modes account for 67--92% of its addition contrast across replacement games, and a disjoint exact path study confirms that block-1 MLP mediates more of their effect than all other tested downstream paths in 12/12 pairs. The sharper "MLP memorizes, attention generalizes" prediction instead reverses (-.331 bits/example at the memory anchor; 0/12 in the predicted direction), while routing onset, global rank collapse, and a prime-invariant architecture ridge also fail, identifying grokking here as spectral recoding of an existing distributed circuit rather than a module switch.

---

### Measuring AI harms with multidimensional Lorenz Zonoids

Authors: Paolo Giudici, Jose' Maria Sarabia, Sofia Vei
Published: 2026-07-29
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2609.16004v1

While AI systems increasingly shape high-stakes societal domains, their governance is limited by the lack of risk management methods that operate on real harms, taking their severity, and not only their likelihood, into account. As a consequence, AI risk management models remain compliance-driven and provider-centric, offering limited insight into how harms are dangerous, and on what should be the priority of intervention. The problem is amplified by the nature of harm data which are typically ordinal and multidimensional. To solve the problem, and offer an effective risk assessment methodology, in this paper we propose to model harm data by means of Lorenz Zonoids and Gini indices. To this aim we propose to extend them in a multidimensional setting, and show how to practically calculate them for a real AI incident data repository, provided by the Massachusetts Institute of Technology. The empirical findings indicate that environmental, infrastructure, property, physical, and democracy-related harms attain the highest values under the two multidimensional Gini indices and therefore exhibit the strongest concentration in their joint direct, indirect, and inferred severity-frequency distributions. These concentration patterns may help identify categories that warrant closer examination when mitigation priorities are determined.

---

### Land Art as a Big-Data Climate Sensor

Authors: Alev Cinbarci, Sean Kalaycioglu
Published: 2026-07-29
Categories: cs.LG, cs.CV, physics.ao-ph
arXiv: https://arxiv.org/abs/2609.13182v1

Robert Smithson's 1970 land artwork Spiral Jetty, located in the north arm of Utah's Great Salt Lake, has alternated between submergence and exposure during severe lake decline. We analyze 1,744 co-registered Landsat 4-9 and Sentinel-2 image chips spanning every year and calendar month from 1984 to 2025. A 14-feature complexity signature combines Shannon entropy, multiscale permutation entropy, fractal dimension, lacunarity, gray-level co-occurrence texture, intensity statistics, and ImageNet-pretrained ResNet50 features. These measurements are compared with a 42-year monthly climate and hydrology panel from NASA GISTEMP, USGS NWIS, Open-Meteo, and the Global Carbon Budget. Bootstrap analysis shows that Shannon entropy is a weak proxy and does not support an earlier small-sample claim of positive correlation with global temperature. By contrast, coarse-scale permutation entropy and mean intensity track lake elevation strongly, with Spearman correlations of 0.85 to 0.88 and 95 percent confidence intervals excluding zero. The third principal component of the ResNet50 embeddings emerges without supervision as an AI climate axis, correlating 0.86 with cumulative CO2 and -0.83 with lake elevation. Image complexity leads lake stage by about three years, with Pearson r = 0.58 at lag +3 and a 95 percent confidence interval of 0.40 to 0.73. STL decomposition reveals a non-monotonic trend that rises from 1984 to 2015 and declines sharply thereafter as the lake approaches record-low elevations. Partial correlations controlling for month and sensor confirm robustness to seasonal and sensor effects. These results refine the art-as-thermometer metaphor into an art-as-leading-indicator-of-hydrological-state interpretation. The dataset, feature pipeline, and analysis code are released as a public benchmark.

---

### PRISM: An Agentic Multi-Model Architecture for Proactive Safety in Autonomous Transportation Systems

Authors: Joyjit Roy, Samaresh Kumar Singh, Sushanta Das
Published: 2026-07-29
Categories: cs.MA, cs.CV, cs.ET, cs.LG, physics.soc-ph
arXiv: https://arxiv.org/abs/2609.01623v2

Autonomous and intelligent transportation systems operate in complex urban environments where safety depends on interactions among vehicle behavior, environmental conditions, and vulnerable road users (VRUs) such as pedestrians and cyclists. Most advanced driver assistance systems (ADAS) employ reactive mechanisms that activate only after hazards have emerged, a critical limitation underscored by rising VRU fatalities in the United States. This study introduces PRISM (Proactive Risk Intelligence and Safety Management), an agentic multi-model safety architecture that transitions from reactive crash avoidance to proactive, continuous risk management. PRISM employs inverse crash-probability modeling to convert binary crash classifiers into dynamic, interpretable safety scores. Three specialized models addressing trajectory kinematics, environmental risk, and VRU interaction operate concurrently, coordinated by a reasoning layer incorporating reinforcement learning, contextual memory, and feature-level attribution. The system provides graduated safety interventions across four tiers, from silent monitoring to emergency alerts. Unlike rule-based systems with static thresholds, PRISM dynamically adjusts safety parameters in real time. Validated across 1,296 scenarios from three naturalistic driving datasets without dataset-specific retraining, the system yielded a mean safety score of 68 out of 100, classified 77.6% of scenarios as advisory, and flagged a near-miss rate of 3.8%, with 11% of scenarios escalating to intervention or emergency response. Feature attribution consistently identified trajectory risk and VRU proximity as primary safety factors. PRISM provides a unified, interpretable framework for proactive transportation safety with emphasis on VRU risk reduction in dense urban environments.

---

### PUFFER: Incremental Fuzzy Deduplication for Continuously Evolving Corpora

Authors: Xiao Yang, Erik Edward Aldape, Beren Millidge
Published: 2026-07-29
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2608.28622v1

Large language model training corpora grow through successive, often redundant releases, so each release must be deduplicated against both itself and the accumulated history. At trillion-token scale, this requires incremental ingestion, bounded resident memory, deterministic retry, and dataset-scoped lifecycle control without repeated corpus-wide rebuilding. We introduce PUFFER (Provenance-aware Updatable Fuzzy Filtering for Evolving Repositories), a MinHash-LSH fuzzy-deduplication pipeline built around two design choices. First, PUFFER stores each LSH band as immutable, dataset-tagged, memory-mapped sorted segments, enabling exact historical band-key membership checks without RAM proportional to corpus size. Second, T-fanout tiered compaction periodically merges segments to control screening fanout, trading lower query cost against additional index-maintenance writes while preserving membership decisions. Across N ingested keys and K equal-sized releases, PUFFER's cumulative maintenance cost is O(N log N log_T K), compared with Theta(KN) for repeated snapshot rebuilding. Dataset-tagged segments also support dataset-scoped withdrawal: removal is constant-time for uncompacted or protected datasets, while post-compaction withdrawal reconstructs only the affected merged segment, even if the original dataset is unavailable. In our implementation, PUFFER completed cumulative index-stage ingestion for one billion documents in about 1.75 hours in a single process, using 128 bytes per document for a 16-band index. A classical resident MinHash-LSH table required about 6.5 KB per document and exceeded a 900 GiB RAM cap. In a ten-hour comparison capped at one billion documents, PUFFER was 11x faster than LSHBloom and 35x faster than Milvus-LSH. PUFFER is deployed on more than 30 billion documents, and we release it as open-source software at https://github.com/Zyphra/puffer.

---

### Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values

Authors: Itai Zilberstein, Ioannis Anagnostides, Zachary W Sollie, Arman Kilic, Tuomas Sandholm
Published: 2026-07-29
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.28620v1

Preference elicitation is essential for aligning AI systems with human values. Prior approaches (e.g., for organ allocation) often ask stakeholders to compare the decisions of an algorithm (e.g., patient A vs. patient B). Such a decision-level approach conflates the means with the ends. Instead, we elicit preferences directly over allocation outcomes to learn a utility function for policy optimization. We construct a novel preference elicitation algorithm for linear utilities that outperforms prior techniques in practice. Our algorithm has two phases. The first phase learns cutting planes through pairwise comparisons to rapidly shrink the space of possible attribute weights and warm-starts the second phase by eliminating dominated regions. The second phase then provably converges to the user's utility function. We apply our technique to heart transplant allocation where a policy must balance competing objectives such as post-transplant outcomes, waitlist mortality, geographic ease, and equity. Using our algorithm, we conduct a user study to learn and aggregate a community-aligned utility function, and use it to optimize heart transplant policies that are significantly better aligned with human values. Compared to the hindsight optimum, the status quo policy achieves a competitive ratio of just 0.54, while our method is near-optimal with a competitive ratio of 0.95.

---

### From GenAI Virtual Patient Dialogue Logs to Teacher-Interpretable Process Evidence: A Learning Analytics Study in Higher Education

Authors: Xinyu Li, Zijian Li, Mengyu Xia, Luzhen Tang, Naping Chen, Changmin Lin, Danijela Gasevic, Dragan Gasevic, Yizhou Fan
Published: 2026-07-29
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2608.28619v1

Medical history taking is a dialogue-based clinical reasoning task in which learners must gather, organise, and integrate patient information while the consultation unfolds. Generative AI-powered virtual patients (GenAI VPs) make repeated history taking practice scalable and preserve full turn by turn dialogue. However, these logs are educationally difficult to use directly. Complete transcripts are too detailed for routine teacher review, whereas final scores obscure whether learners followed up patient cues, checked uncertainty, or used summaries to guide later questioning. This study examined whether coded GenAI VP dialogues can provide teacher-interpretable process evidence of clinical reasoning. We analysed 1{,}030 GenAI VP dialogues from 210 second-year medical learners across five weeks chest-pain cases. Each consultation was teacher-scored using a rubric assessing the full history taking dialogue, and consultations were classified within each week as high- or low-rated using the weekly median score. To explain how rated performance was reflected in the dialogue process, we applied three analytic layers to the same coded dialogue data: behavioural prevalence, local co-occurrence using Epistemic Network Analysis, and sequential transition using Transition Network Analysis. High-rated consultations involved more history taking activity, but differences were not simply about volume. High rated consultations more often connected information gathering and symptom exploration with communication, checking, organisation, and synthesis. Summarising and organising moves more often led to verification or mechanism-oriented follow-up. These findings show how layered analysis of GenAI VP dialogue logs can reveal process patterns associated with high rated history taking and support process-focused feedback in medical education.

---

### LingShu: A Large-Scale Symptom-Centric Contextualized Knowledge Graph Bridging Traditional Chinese Medicine and Modern Biomedicine

Authors: Rui Hua, Zixin Shu, Kai Chang, Dengying Yan, Jianan Xia, Hui Zhu, Shujie Song, Shurui Yang, Tongxin Wang, Yue Yin, Yu Wei, Lijuan Pei et al.
Published: 2026-07-29
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2608.20402v1

Biomedical knowledge graphs (KGs) are pivotal for knowledge organization, yet traditional binary relations often struggle to represent the conditional nature of biomedical knowledge. Symptoms provide a shared phenotypic layer for linking Traditional Chinese Medicine (TCM), which relies on symptom patterns for syndrome differentiation and treatment selection, with modern biomedicine, which connects clinical manifestations to diseases and molecular mechanisms. We present LingShu, a large-scale symptom-centric contextualized knowledge graph designed to bridge TCM and modern biomedicine. The exported version of LingShu analyzed in this study comprises 17.33 million atom-level entity records and 39.47 million relation records, including 17.19 million semantic triples and 22.29 million contextualized quadruples. LingShu integrates multi-source data, including clinical electronic medical records, authoritative TCM texts, biomedical ontologies, and curated knowledge bases, through a pipeline combining natural language processing, terminology normalization, and human-in-the-loop verification. A key innovation of LingShu is its hybrid data model: it maintains 64 typed triple relation patterns to ensure broad connectivity, while incorporating 35 contextual quadruple relation patterns to capture conditional medical associations. This dual-structure approach explicitly encodes conditional knowledge, providing a granular representation of the contexts associated with medical relations. These contextualized relations cover syndrome-dependent herb efficacy, disease-contextualized drug effects, population-specific clinical associations, and mechanism-related therapeutic responses. Furthermore, we developed a web platform (http://www.tcmkg.com/) that integrates graph visualization, graph-based reasoning, and an evidence-grounded knowledge question-answering agent.

---

### M3: A State-Event Generative Foundation Model for Market Microstructure Dynamics

Authors: Yanzhi Zhang, Yu Ma, Yilin Cheng, Jian Li, Yitong Duan
Published: 2026-07-29
Categories: q-fin.CP, cs.LG
arXiv: https://arxiv.org/abs/2608.19227v1

Market microstructure simulation aims to model how liquidity, prices, and order flow evolve in electronic financial markets. Since market data reveal only one realized trajectory, many important questions are inherently counterfactual and require realistic trajectory-level simulation. Existing financial generative models, however, often model order events and market states, such as the LOB, in isolation, overlooking the dynamic interaction between order flow and liquidity in market microstructure. We propose the \textbf{M3} (\underline{M}arket \underline{M}icrostructure \underline{M}odel), a state-event generative foundation model for market microstructure dynamics. \textbf{M3} learns to generate future order-flow trajectories, while accounting for the evolving interaction between order events and limit-order-book liquidity. Trained on large-scale order-level real stock market data, \textbf{M3} exhibits predictable scaling behavior, reproduces key market stylized facts, and enables practical simulation-based applications including forecasting, stress testing, and market-impact analysis. These results suggest a scalable foundation-model paradigm for counterfactual market simulation at the microstructure level.

---

### Improving Rural Medication Safety with AI: A Scoping Review

Authors: Jeong-ah Kim, Muhammad Ashad Kabir, Daniel Terry, Maryam Rouhi
Published: 2026-07-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.18135v1

Introduction: Medication errors (MEs) represent a significant threat to global healthcare systems, contributing to patient harm. Introducing artificial intelligence (AI) in rural healthcare enhances patient safety. The aim is to explore the applications and effectiveness of AI technologies in enhancing patient safety and reducing medication errors in rural health settings. Methods: A scoping review was conducted through a systematic literature search spanning 2012 to 2025 across multiple databases, including EBSCohost, Emcare (Ovid), MEDLINE, and the ProQuest Consumer Health Database. Twelve primary studies from nine different nations were examined. Data were analysed thematically to obtain insights on AI interventions across the medication process. Results: AI technologies have been integrated into every stage of medication management, right from prescribing and dispensing to administration and post-administration monitoring. Four key themes came to light: (1) the various types of AI being utilised (like Clinical Decision Support Systems, Machine Learning, Natural Language Processing, and smart pumps); (2) the phases of the medication process that are affected; (3) how effective these technologies are in minimising errors and boosting workflow safety; and (4) rural-specific challenges including infrastructure, staff training, system integration, and alert fatigue. Several studies have demonstrated that machine learning-based surveillance improves incident detection and reduces prescribing and transcription errors by an impressive 34% to 80%. Barriers included lack of governance frameworks, financial limitations, and clinician resistance, which still present major obstacles. Conclusion: In rural healthcare, AI technologies hold great potential for enhancing pharmaceutical safety. They can allow data-driven monitoring, automate processes, and offer clinical decision assistance.

---

### Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO___ Retrieval, and Application to Interferometric Sensing

Authors: Jordan Lontsi Tedongmo, Yann Ferrec, Laurence Croizé, Pablo Musé, Gabriele Facciolo, Andrés Almansa
Published: 2026-07-29
Categories: cs.LG, physics.ao-ph
arXiv: https://arxiv.org/abs/2608.14645v1

Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates spaceborne measurements with improved revisit frequency and spatial coverage. In this context, the Horizon Europe SCARBOn project assesses a low-cost satellite constellation featuring the NanoCarb imaging interferometer as its core sensor for monitoring CO2 and CH4 emissions in the atmosphere. However, estimating CO2 and CH4 concentrations with high revisit and spatial coverage poses significant challenges: full-physics retrieval algorithms commonly used rely on repeated high-resolution radiative transfer (RT) simulations, which are computationally expensive when using line-by-line RT models. As an alternative, we propose in this study a feedforward multilayer perceptron (MLP) surrogate designed to accurately and efficiently predict top-of-atmosphere radiances in the CO2 weak band, using a combined mean absolute error (MAE) loss on radiances and RT Jacobians to preserve both spectral accuracy and sensitivity to geophysical parameters. Coupling the MLP-based RT surrogate with the NanoCarb instrumental response yields an efficient and precise forward model for NanoCarb measurements, which shows promising results for CO2 concentration retrieval.

---

### DUET: Dual-Teacher On-Policy Distillation via Same-Weight Disagreement for Prohibition Compliance

Authors: Zihan Li, Feifei Li, Wenhui Que
Published: 2026-07-29
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2608.14644v1

Real-world LLM deployments increasingly rely on runtime-injected prohibitions--enterprise policies, PII redlines, tool boundaries--that vary per request and per tenant. Conventional post-training is structurally ill-suited: SFT hides the violation signal in compliant labels, and DPO's sequence-level preferences mismatch token-localized violations. We propose DUET, a token-selective on-policy distillation method for prohibition compliance. DUET pairs a teacher that sees the prohibition (positive) with an identical-weight teacher that does not (negative). Because the two teachers differ only in prohibition visibility, their per-token disagreement isolates the prohibition's causal effect--yielding a clean supervision signal uncontaminated by model capacity or mismatch. This disagreement drives two complementary mechanisms: signal cleaning, which discards agreement tokens as redundant or prefix-corrupted, and preference-directed learning, which pushes the student away from the negative teacher and toward the positive one at token granularity, embedding DPO-style optimization directly into OPD without offline preference data. We construct an industrial Prohibition-Compliance benchmark spanning five task families covering explicit-refusal, paraphrase robustness, and over-refusal. Across 1.5B-8B Qwen variants, DUET achieves 72.3-85.2% violation compliance while preserving 88-93% normal utility, dramatically outperforming teacher model and other distillation baselines. External evaluation on SysBench confirms improved safety alignment with minimal degradation on GSM8K and MATH-500.

---

### Training and Evaluating Ethical Reinforcement Learning Agents on Per-Episode Distributions

Authors: Prabhjyot Singh, Majid Ghasemi, Mark Crowley
Published: 2026-07-29
Categories: cs.LG
arXiv: https://arxiv.org/abs/2608.14642v1

Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is particularly a problem when we are trying to imbue ethical behavior into RL agents. An agent can look ethical on average while concentrating its violations in a few bad episodes, and a creature in the environment harmed in one episode is not restored by good conduct in another. We compare four ways of training ethical behavior in Craftax, an open-ended survival benchmark. The four are: scalar penalties with termination, a linear multi-objective weight sweep, an adaptive Lagrangian constraint, and a non-compensatory utility optimized per episode under the Expected Scalarized Returns (ESR) criterion. All are evaluated under a single detector-based protocol that counts every violation in every episode without censoring. On the frontier of mean return against mean violation rate, the four methods are indistinguishable; per episode they separate sharply. At matched mean return, the ESR agent holds its stated budget of one violation in effectively every episode (worst-decile 1.04 +/- 0.07 violations), the Lagrangian leaks past the same budget (1.14 +/- 0.03), and the weight sweep's worst episodes double it (2.20 +/- 0.20). An observation-augmentation control attributes the separation to the training objective rather than to what the agent observes, and the per-episode guarantee costs nothing on the mean frontier. When ethical violations do not average away across episodes, we argue both training and evaluation must target the per-episode distribution rather than the mean.

---

### Synchronizing Beliefs with Second-Order Theory-of-Mind in Human-Autonomy Teams (Extended Version)

Authors: Jack Mirenzi, Henny Admoni
Published: 2026-07-29
Categories: cs.AI, cs.RO
arXiv: https://arxiv.org/abs/2608.11229v1

Comparative feedback, asking people which of two behaviors they prefer, has become a standard way to align robot and agent behavior with human intent when the reward itself cannot be specified directly. Preference-based reward learning typically casts the human teacher as a passive oracle answering learner-generated queries. We argue this forfeits the teacher's defining advantage: knowledge of the objective. A teacher who knows the target can construct training examples more efficiently than any learner-driven acquisition strategy, an advantage that widens as the reward's feature dimension grows. However, exploiting this advantage requires an accurate model of what the learner currently knows. We therefore recast preference learning as a human-autonomy team problem coupling two behavioral models: the teacher maintains a model of the learner to design an informative curriculum, and the learner maintains a second-order model of the teacher's model, emitting structured preference constraints (understanding statements) that keep the teacher's model of the learner synchronized. In simulation, an informed teacher outperforms learner-led selection; teacher-model drift under alternating teachers erodes this advantage; and understanding statements repair it, with second-order (ToM-2) statements outperforming mean-belief statements when the teacher's error about the learner is concentrated in a particular direction rather than spread evenly.

---

### Evidence-Based Scientific Question Discovery: A Framework with Historical Backtesting

Authors: Hui Mao
Published: 2026-07-29
Categories: cs.DL, cs.AI
arXiv: https://arxiv.org/abs/2608.09968v1

Current AI systems are optimized for answering questions; the scientific enterprise is bottlenecked earlier, at discovering the questions worth investigating. We present a framework that turns a traceable, reproducible, scope controlled research corpus into ranked, falsifiable research questions: evidence is represented as provenance carrying claims; cross paper tensions are detected, typed, and human adjudicated; surviving signals are refined into questions and ranked by a two stage protocol separating scientific priority from execution priority. We instantiate the framework on exoplanet atmospheres, a domain that uniquely combines literature, structured catalogs, and space telescope archives. In a historical backtest, all questions generated from evidence available before 2021 were substantively engaged by the 2021 to 2026 literature the sys?tem never saw: two were answered, including one whose premise the community later explicitly refuted and the top ranked question is independently posed and still open. These results sug?gest that systematic question discovery from evidence tensions surfaces the questions working scientists subsequently invest in.

---

### TREAT: Evaluating Access to Formal Knowledge across Equivalent Mathematical Representations

Authors: Fateme Mazdarani, Carlos Toxtli
Published: 2026-07-29
Categories: cs.AI
arXiv: https://arxiv.org/abs/2608.07540v2

AI systems increasingly operate between flexible input representations and formal objects used by downstream tools. A key challenge is recognizing when an unfamiliar formulation denotes a known formal object. We study this challenge through theorem recognition: given an equivalence-preserving transformation of a theorem condition, a model must recover the theorem identity associated with the standard statement. We introduce TREAT, a benchmark for evaluating whether large language models can recover known theorem identities from equivalence-preserving formula-level transformations. Rather than paraphrasing theorem text, TREAT changes the mathematical form of theorem conditions themselves, expressing known results through residual equations, witness statements, optimization identities, set relations, operator forms, and proof-intermediate characterizations. Starting from scraped theorem pages, we filter for entries with usable mathematical expression forms, extract canonical theorem conditions, and generate transformed variants with recorded assumptions and inverse mappings. The final corpus contains 737 theorem identities and 29,480 transformed rows. On a test panel, the best model retrieves the correct theorem identity in only 60.73% of cases. Other systems reveal different failure modes, including abstention, wrong detection, and malformed outputs. These suggest that theorem knowledge can be fragile under equivalent changes in representation. TREAT therefore provides a controlled testbed for evaluating representation-robust access to formal knowledge, with broader relevance to domains that require stable target objects, explicit equivalence relations, validation procedures, and auditable scoring.

---

### AutoPSO: A Meta-framework for Automated Particle Swarm Optimization

Authors: Xinmeng Yu, Jiaxin Gao, Jianguo Zhang, Dongmei Jiang, Ran Cheng
Published: 2026-07-29
Categories: cs.NE
arXiv: https://arxiv.org/abs/2608.07539v3

Particle swarm optimization (PSO) is a widely used metaheuristic, prized for its simplicity and small parameter set. Although decades of research have produced numerous PSO variants that improve performance by modifying key components (e.g., parameter schedules, swarm topologies, or updating rules), two fundamental challenges persist. First, most existing approaches are problem-specific and hand-crafted, leading to poor cross-task generalization and forcing practitioners to navigate an impractically large design space, which also hinders systematic reuse of prior effective mechanisms. Second, mainstream implementations remain CPU-bound, constraining scalability and substantially increasing computational cost in real-world applications. To address these challenges, we propose AutoPSO, a highly automated meta-framework for constructing customized PSO algorithms. AutoPSO formulates PSO-based optimization as a bi-level process: an outer search explores the joint space of effective PSO components, while an inner loop instantiates candidate variants to solve the target task and provide feedback. The outer search operates over a curated, open-design component pool, supporting flexible replacement of the component set and the outer optimizer. Crucially, by leveraging EvoX for population tensorization and batched evaluations, AutoPSO can efficiently assess thousands of particles within practical time budgets. Comprehensive experiments on numerical benchmarks and neuroevolution robotic control tasks demonstrate that AutoPSO consistently discovers novel PSO variants that significantly outperform strong baselines. Ablation and scalability studies further highlight the contribution of individual algorithmic components and confirm that AutoPSO achieves increasing performance gains with larger swarm sizes. Code is available at {https://github.com/EMI-Group/autopso}.

---

### When LLM Agents Negotiate: Private Information and Dynamic Bargaining in Supply Chains

Authors: Chen Liang, Fasheng Xu
Published: 2026-07-29
Categories: cs.AI, cs.GT, econ.GN
arXiv: https://arxiv.org/abs/2608.07538v1

As LLM agents move from decision support to autonomous procurement, firms need to know whether delegated negotiators create value, divide it predictably, and avoid money-losing contracts. We study this in a canonical supply chain bargaining problem: a buyer with private demand information negotiates a quantity-payment contract with an uninformed seller. We benchmark nine LLMs from OpenAI, Google, and Alibaba against a validated Perfect Bayesian Equilibrium across 9,840 LLM-to-LLM negotiations. First, capability governs value creation. Agents agree in 98.9% of negotiations and capture 95.4% of first-best surplus undiscounted, but average 2.98 rounds against the benchmark's 1.25, and this delay erodes 21-34% of surplus. Capability also governs reliability: baseline models accept individually irrational contracts in 19.2% of cases, versus 0.0-0.6% at mid-tier and flagship, making automated profit verification the binding guardrail below that threshold. Second, surplus capture is relational. Provider identity predicts who captures surplus better than capability rank: self-play buyer shares average 40% for OpenAI, 50% for Google, and 70% for Alibaba's Qwen, an ordering that survives restricted communication and no discounting. Reversing which provider sells moves the division by 7-18 percentage points, and the capable Qwen flagship is the weakest cross-family seller: vendor choice is a first-order distributional decision. Third, the prompt is a strategic lever. Delegation separates the principal's economic patience from the agent's prompted strategic patience, a free deployment choice that is the single strongest driver of surplus division (90% of explained variance). Together these establish an equilibrium-referenced audit of AI agents along three dimensions: discounted efficiency, distributional profile, and operational reliability.

---

### An evolutionary model of animats with VLM-based subjective evaluation

Authors: Shota Miyazaki, Takaya Arita, Reiji Suzuki
Published: 2026-07-29
Categories: cs.NE, cs.AI, cs.CL, cs.HC, cs.MA
arXiv: https://arxiv.org/abs/2608.07537v1

In this study, we propose a framework that incorporates subjective evaluations provided by a Vision-Language Model (VLM) into the fitness evaluation and selection processes of a genetic algorithm. As the target of evolution, we employ virtual soft robots with flexible morphologies and locomotion and present the VLM with sequence images representing the locomotion of two individuals. Selection is performed via pairwise comparisons based on subjective evaluation terms such as adorably and weirdly. The outcomes of these comparisons are used as selection pressure within the genetic algorithm, enabling the simultaneous evolution of morphology and locomotion. Experimental results demonstrate that subjective selection by the VLM accelerates population convergence compared to random selection, while also giving rise to distinctive morphologies and motions corresponding to each evaluation term. An auxiliary experiment with human participants further showed that, although individual pairwise choices only partly agreed with the VLM selections, the resulting morphological and locomotion tendencies were qualitatively similar and repeated human evaluations imposed noticeable fatigue. Moreover, the observation that similar evolutionary outcomes emerged across different evaluation terms suggests that the VLM does not apply these terms in a purely literal manner but instead decomposes them into multiple internal evaluation criteria when making judgments. This work visualizes the evolutionary process through which subjective linguistic expressions are mapped onto embodied phenotypes and provides a foundational framework for analyzing the structure of subjective judgment in VLMs. The proposed approach is expected to contribute to new developments in evolutionary computation and artificial life research based on subjective evaluation.

---

### From Pixels to PCells: A Neurosymbolic Approach to Photonic Component Creation

Authors: Aadarsh Agarwal, Kenaish Al Qubaisi, Dirk Englund
Published: 2026-07-29
Categories: cs.CV, physics.optics
arXiv: https://arxiv.org/abs/2608.00084v1

We present PixCell, a neurosymbolic system in which multimodal agents convert a visually presented photonic component into a parametric program over a small domain-specific language (DSL) of geometric primitives. A system enabling deterministic visual verification renders evaluation asymmetrically cheaper than the generation attempt. While models using multi-seed sampling and iterative revision reach a mean best-turn IoU of only 0.416, multimodal agents through PixCell's interface and verifier consistently exceed 0.9 mean IoU, with scores reaching 0.974 and 0.955 across eight component targets while also satisfying source contracts. These results demonstrate that frontier multimodal agents can reliably understand and render executable parametric representations from visual targets. Using these live parameters, cross-stack studies on an interferometer reconstruct primitive programs that satisfy an 8.0 nm free spectral range target and the original footprint constraint on modeled 220-nm SOI, 400-nm SiN, and 400-nm TFLN stacks. PixCell further carries a paper-derived splitter from visual reconstruction through SOI full-wave simulation, producing symmetric propagation and balanced outputs. Finally, the same executable verifier supplies a training reward and dataset used to train a Qwen3.6-35B-A3B model with LoRA and GRPO without supervised demonstrations. On eight training-excluded paper figures, its mean champion IoU rises from 0.422 after eight initial attempts to 0.491 after three verifier-guided revision rounds. These results therefore establish a controlled framework for measuring, retargeting, and improving visual-to-parametric photonic component design.

---

### Beyond Edge Maps: Wavelet-Domain Conditioning for Multi-Adapter Map-to-Satellite Diffusion

Authors: Arisha Prasain
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00083v1

Commercial mapping partnerships are often unavailable in low-resource regions, leaving satellite basemaps stale and motivating synthesis of satellite imagery from independently maintained cartographic data. Existing ControlNet-based diffusion methods typically condition on structural signals like edges or segmentation extracted from the target image itself, assuming the imagery already exists and limiting their use exactly where synthesis matters most. Map-conditioned alternatives add cues like edge detection but omit frequency-domain structure. We propose a ControlNet-based diffusion framework conditioned only on cartographic sources obtainable independently of the target imagery: OpenStreetMap (OSM) raster maps and their stationary wavelet transform (SWT) subbands, a conditioning signal previously unexplored for map-to-satellite diffusion. Two ControlNet adapters, trained separately on the map and wavelet representations atop a frozen Stable Diffusion backbone, are fused via MultiControlNet, jointly drawing on spatial structure and frequency detail without retraining a multi-input model. We evaluate on a new paired map-satellite dataset curated for Nepal, a data-scarce, topographically diverse region, alongside the Pix2Pix maps-satellite benchmark. Combined conditioning wins six of eight metric-dataset comparisons -- SSIM and PSNR on both datasets, plus LPIPS (both Alex and VGG backbones) on ours and ties map-only on both Pix2Pix LPIPS backbones while still edging past wavelet-only there. Wavelet-only takes the lowest FID on both datasets, matching the tradeoff between per-image fidelity and distributional realism. We treat this gap cautiously given our modest test-set sizes and FID's known small-sample bias.

---

### LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation

Authors: Rongxiang Zhang, Songhua Liu
Published: 2026-07-29
Categories: cs.CV, cs.SD
arXiv: https://arxiv.org/abs/2608.00079v1

Long-form and real-time talking-head generation remains challenging due to a latency-quality trade-off: inefficient multi-step diffusion prohibits streaming generation, whereas real-time autoregressive approaches suffer from error accumulation and identity drift. To address this drawback, we propose LeapTalk, a novel framework that achieves stable and real-time talking-head generation with a single forward step, scaling to arbitrarily long videos. At the heart of our approach lies a single-step bridge distillation scheme. On the one hand, departing from the conventional noise-to-data paradigm, we introduce a data-to-data transport formulation based on a Brownian bridge. Anchored by a persistent reference, this strategy effectively mitigates identity drift and enhances long-term temporal stability. On the other hand, to enable smooth knowledge transfer from a pre-trained diffusion teacher to the student bridge model, we explore a heterogeneous distillation framework with an SNR-aligned time transformation $Φ(τ)$, which bridges the functional discrepancy between the two models. Moreover, we propose an audio-driven classifier-free guidance mechanism to maintain fine-grained lip synchronization under extreme step reduction. Extensive experiments demonstrate that our method achieves high-fidelity and temporally consistent video generation with only 1 step at up to 200 FPS, significantly outperforming existing approaches in both efficiency and stability. Project Page: https://zhangrongxiang.github.io/leaptalk-page/

---

### Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search

Authors: Saif U Din, Muhammad Ahsan Hussain, Radu Timofte, Dmitry Ignatov
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00078v1

Deploying convolutional neural networks generated by large language models (LLMs) on real mobile hardware requires more than GPU validation accuracy: INT8 TensorFlow Lite export, delegate selection, and on-device latency jointly determine whether a model is usable. We present an automated mobile deployment pipeline that closes the loop from QLoRA fine-tuning of an architecture-generating LLM through GPU evaluation, INT8 export, and physical-device benchmarking to gated augmentation of the training corpus. The pipeline is fully scripted and runs cycle-by-cycle without manual intervention, with resume support after interruptions. We evaluate the same frozen protocol on two benchmarks, CIFAR-10 and CIFAR-100, on a Samsung SM-P613 tablet (seed 42, 20 models per cycle, cycles 0-6). On CIFAR-10, cycle 1 is gate-accepted and improves the mobile deployment score approximately 25.6x over the baseline with a mean quantized accuracy of 46.9%; later cycles raise GPU accuracy but fail the non-decreasing mobile gate. On CIFAR-100, the pre-QLoRA baseline retains the best mobile score; iterative rounds improve GPU accuracy (up to 26.2%) yet cannot surpass cycle 0 on-device, and the training pool stalls at 19 examples after the first accepted round. Together, the two studies show that closed-loop GPU fine-tuning does not guarantee monotonic mobile gains, especially on harder classification tasks, and that multi-dataset, on-device measurement is needed to stress-test deployment objectives. We release per-cycle metrics with 95% confidence intervals, all figures, and complete reproduction commands.

---

### Beyond Accuracy: Auditing Spatial Provenance in Visual Token Pruning for OCR-Critical MLLM Inference

Authors: Feixiang Liu, Qiang Qiu, Hao Zhang, Xinyue Wang
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00077v2

Visual-token pruning is usually judged by answer quality at a fixed retention budget. For text-rich multimodal large language models (MLLMs), this protocol can miss a distinct failure: an answer remains correct even when no retained token is locally traceable to the small OCR region that supports it. We turn this blind spot into an evidence-risk audit that couples answer behavior with geometric token-origin provenance, interventions, and realized cost; transparent training-free selectors isolate controlled operating points. On locked image-disjoint confirmation, Qwen Target at 30% retention has observed accuracy 0.786 versus 0.783 for Full (paired image-cluster difference +0.003, 95% CI (-0.014, +0.020)), yet same-budget Target, Random, and Grid retain sharply different positive-support coverage: 0.620, 0.270, and 0.318. Across Qwen3-VL-8B, LLaVA-1.5-7B, and InternVL3.5-8B, matched controls, interventions, detector tests, and external methods reveal model-specific quality-risk-traceability frontiers that accuracy alone does not expose. Materialized prefixes yield up to 4.32x batch-prefill speedup and 76.4% lower incremental peak memory; full-validation TextVQA and DocVQA further show that favorable target-verification points do not imply task-general compression. Visual-token pruning should therefore report surviving spatial provenance and realized cost alongside quality and compression.

---

### Which Modality Decides? Counterfactual Modality Attribution for Multimodal LLMs

Authors: Vahidin Hasic, Chao Wang, Luis C. Garcia-Peraza-Herrera, David Watson, Senka Krivic
Published: 2026-07-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.00076v2

Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. While existing explainability methods identify influential image regions or text tokens, they cannot answer a fundamental question: which modality drives a prediction? Consequently, a model may produce the correct output while relying on the wrong source of evidence, masking shortcut learning and unsafe reasoning. We formulate modality attribution as a complementary explainability objective for multimodal foundation models and propose Counterfactual Modality Attribution (CMA), the first framework for quantifying modality-level contributions in MLLMs. CMA generates image-only, text-only, and joint multimodal counterfactuals using coupled diffusion priors and converts them into principled modality attribution scores through a cooperative game-theoretic formulation based on Shapley values. We evaluate CMA on controlled synthetic benchmarks with known ground-truth modality reliance and on a real-world multimodal clinical dataset. CMA correctly identifies the decision-driving modality in 98% of controlled cases and consistently outperforms baselines, revealing failures of cross-modal reasoning that remain invisible to predictive accuracy alone. Our results establish modality attribution as a complementary dimension of explainability beyond feature attribution, providing a principled framework for auditing multimodal foundation models in safety-critical applications.

---

### K-space Gaussian Representation for Parallel MRI

Authors: Yu Guan, Mingyu Hu, Jiale Hu, Zhuoxu Cui, Dong Liang, Qiegen Liu
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00075v2

Accelerated magnetic resonance imaging (MRI) aims to recover the k-space signal from acquired measurements, where accurate estimation of missing samples is essential for high-fidelity reconstruction. Existing k-space reconstruction methods estimate missing samples through interpolation operators or structure priors defined on discrete sampling grids. Although these formulations effectively exploit local interpolation relationships and global k-space redundancy, they reconstruct only discrete frequency coefficients and therefore do not explicitly model the underlying continuous signal. To overcome this limitation, we propose K-space Gaussian Representation (KGR), the first explicit continuous representation formulated directly in the native k-space domain. Rather than estimating unknown samples on discrete grids, KGR parameterizes the continuous signal using Gabor-Gaussian primitives with shared spatial geometry, yielding a compact representation that naturally preserves inter-coil correlations. Because unconstrained continuous fitting does not necessarily satisfy the intrinsic structural properties of multi-coil signal, the estimated representation is projected onto a low-rank manifold to enforce the algebraic constraints arising from smoothly varying phase and coil redundancy. A frequency-adaptive fitting strategy accommodates the heterogeneous characteristics of different k-space regions. Comprehensive validation across multiple datasets and sampling schemes shows consistent improvements over representative reconstruction baselines in both quantitative metrics and visual quality. These results suggest that explicit continuous parameterization of native k-space provides a principled framework for integrating continuous signal modeling with structured low-rank reconstruction.

---

### Explainable Multimodal AI for Adaptive Calibration of Archaeological Sensing Workflows

Authors: Nevio Dubbini, Daniel P. van Helden, Claudia Sciuto, Martina Naso, Arthur Leck, Clement Joubert, Heeli C. Schechter, Remy Chapoulie, Gabriele Gattiglia
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00074v1

This paper presents a multimodal machine-learning framework for calibration monitoring, quality assessment, and adaptive acquisition support in archaeological digitisation workflows. The proposed approach operates across photogrammetric 3D reconstruction, hyperspectral imaging, X-ray fluorescence spectroscopy, and Raman spectroscopy through a unified pipeline combining deterministic quality indicators, statistical feature representations, machine-learning classification, anomaly detection, and explainable artificial intelligence (XAI). Rather than replacing instrument-level calibration, the framework introduces an additional algorithmic layer that evaluates whether acquisitions are statistically consistent, physically plausible, and suitable for downstream multimodal integration. For each sensing modality, acquisitions are represented through structured feature spaces encoding geometric, spectral, spatial, and statistical properties. These representations are used to identify degradation patterns such as reconstruction artefacts, illumination inconsistencies, spectral distortions, detector instability, baseline fluctuations, and low signal-to-noise conditions. Supervised and unsupervised learning methods are combined with XAI techniques to support both automatic discrimination between acceptable and problematic acquisitions and interpretation of the underlying causes of degradation. The framework additionally supports adaptive feedback and resource-aware acquisition strategies by linking feature-space deviations to acquisition-level corrective actions. Experimental results obtained on multimodal archaeological datasets demonstrate that the proposed methodology captures meaningful acquisition variability and enables robust quality assessment across heterogeneous sensing modalities.

---

### Beyond Random Partitioning: Unsupervised Spatio-Temporal Stratification for Cohort Balancing in Longitudinal Medical Imaging

Authors: Qinghui Liu, Jon André Ottesen, Atle Bjørnerud, Kyrre Eeg Emblem
Published: 2026-07-29
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2608.00073v1

Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging. Naively shuffling small clinical cohorts routinely introduces covariate shifts and temporal sampling imbalances across training, validation, and test subsets, exposing downstream models to out-of-distribution evaluation. We address this vulnerability with an auditable Tripartite Dataset Analytics Framework that systematically characterizes spatial grid integrity, multi-parametric intensity fingerprints, and longitudinal temporal trajectories, quantifying the heavy-tailed feature dispersion and irregular, episodic sampling intervals typical of real-world clinical cohorts. Building on this characterization, we formalize an unsupervised spatio-temporal cohort-balancing standard operating procedure (SOP) that combines elbow-optimized K-means clustering over a standardized, six-dimensional joint intensity-temporal feature space with intra-cluster proportionate stratified sampling. On a longitudinal, contrast-enhanced $T1$-weighted brain MRI cohort (N=149), the protocol reduces the maximum cross-subset intensity bias from 34.1% under conventional random shuffling to under 2.1%, while aligning longitudinal follow-up intervals closely around the population mean. Monte Carlo stress testing across ten random seeds and three split configurations confirms that this alignment remains tightly bounded, in clear contrast to the substantial variability of random partitioning. The resulting protocol offers a reproducible, generalizable procedure for cohort engineering in variable-length longitudinal clinical imaging workflows.

---

### Volcanic Clouds Detection through QCNN and Geostationary Satellite Multispectral Imagery

Authors: Federica Torrisi, Claudia Corradino, Alessandro Grilli, Tommaso Catuogno, Mattia Verducci, Elisabetta Paladino, Luigi Giannelli, Alessandro Sebastianelli
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00072v1

Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches offer novel ways to process information by exploiting quantum phenomena such as superposition and entanglement. These capabilities have motivated the exploration of whether quantum-enhanced models can address long-standing challenges in satellite remote sensing, where complex spectral and spatial signals often require sophisticated feature extraction. Among various fields of application, EO data allow the global monitoring of volcanic clouds and are crucial for aviation safety, hazard assessment, real-time eruption response, and evaluation of volcanic impacts on climate. Yet accurate detection of volcanic clouds remains difficult due to their similarity with meteorological clouds, the variability of eruption signatures, and the coarse spectral sampling of geostationary sensors. In this work, the potential of hybrid quantum convolutional neural networks (QCNNs) for the classification of satellite images containing volcanic clouds was investigated. These architectures integrate quantum computational layers into a classical convolutional framework. Two QCNN variants (with 2 and 4 qubits) have been considered to evaluate their ability to classify a dataset of SEVIRI images, including scenes with volcanic clouds (composed of ash, $SO_2$, or mixed components) as well as non-volcanic backgrounds. Finally, the performance of the hybrid QCNN models was compared with that of purely classical architectures.

---

### Empirical investigation of 3D CT Foundation Models and Unsupervised Adaptation for Head and Neck Cancer Recurrence Prediction

Authors: Bilel Guetarni, Feryal Windal, David Pasquier, Halim Benhabiles
Published: 2026-07-29
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2608.00071v1

The rapid emergence of 3D CT foundation models has opened new avenues for predictive modeling from CT imaging, offering a compelling alternative to traditional radiomics which is known to suffer from reproducibility issues and sensitivity to acquisition protocol variations. Yet, as these models grow in availability, a critical need arises to evaluate how well their learned representations generalize across diverse clinical settings and whether adaptation to specific downstream tasks is necessary to unlock their full potential. To address these questions, we benchmarked several 3D CT foundation models for predicting recurrence-free survival in head and neck cancer across two public datasets totaling 3,644 patients, evaluating various adaptation strategies and modality fusion mechanisms. Our findings reveal persistent difficulty in identifying features that generalize consistently across different imaging distributions, as evidenced by significant performance drops on external validation cohorts. Ultimately, the integration of imaging features with clinical data remains the most accurate approach for prognostic prediction, though achieving universal generalization across varied clinical contexts continues to represent a substantial challenge for the current generation of models.

---

### Hybrid Quantum CNN for Cross-Sensor Spaceborne Volcanic Thermal Activity Recognition Worldwide

Authors: Claudia Corradino, Federica Torrisi, Alessandro Grilli, Tommaso Catuogno, Mattia Verducci, Elisabetta Paladino, Luigi Giannelli, Alessandro Sebastianelli
Published: 2026-07-29
Categories: physics.geo-ph, cs.LG
arXiv: https://arxiv.org/abs/2608.00069v1

As Earth Observation (EO) enters the Big Data era, the exponential volume of daily satellite imagery poses significant computational and storage challenges for classical Deep Learning (DL) models. Moreover, current approaches often struggle to generalize across heterogeneous sensors and volcanic environments while requiring large labeled datasets and substantial computational resources. These limitations are particularly critical for emerging On-Board Processing (OBP) applications, where memory, computational power, and annotated data are inherently limited. This work proposes a Hybrid Quantum AlexNet architecture for cross-sensor recognition of volcanic thermal activity at the global scale. The proposed model combines a classical convolutional backbone for high-level spatial features extraction with a parameterized quantum circuit (PQC) acting as a variational layer. By embedding high-level image representations into a high-dimensional Hilbert space, the quantum layer learns task-specific representations that enhance feature discrimination. Experimental results demonstrate that the proposed hybrid quantum model learns more discriminative feature representations, leading to improved cross-sensor transferability and robustness across heterogeneous volcanic environments using fewer trainable parameters and reduced training data than its classical counterpart.

---

### SafeBuild-Bench: A Temporal-Robust Construction Safety Benchmark with Graph-Enhanced Data Mining

Authors: Yi Cui, Zilin Wang, Yijie Xu, Qianyi Cai, Huizai Yao, Shuai Jiang, Bingzhuo Zhong, Hui Xiong
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00068v1

Construction-safety models must handle concrete deployment risks, such as a worker standing near a scaffold edge without guardrails, rather than only recognize common objects in curated images. Yet real inspection archives are redundant, long-tailed, and collected across changing sites and months. We introduce SafeBuild-Bench, a metadata-driven benchmark for evaluating multimodal large language models on construction safety under realistic temporal and site variation. It is mined from 100K+ industrial image-text records and contains 3,314 task instances from over 3,000 expert-verified images, covering multiple-choice hazard identification and free-form hazard description. To make expert verification scalable, we develop GEMS, a graph-enhanced multimodal selection pipeline that combines a proxy-model confusion signal with graph-based diversity to identify informative candidates from redundant streams. On public instruction-tuning data, GEMS-selected subsets preserve robustness-oriented performance under small data budgets. On SafeBuild-Bench, current MLLMs remain far from reliable construction-safety understanding, with the best overall score near 60. We release the benchmark, evaluation scripts, and GEMS codebase at https://github.com/safebuild/gems.

---

### PhysAgent: A Multi-Agent Framework for Reliable Remote Heart Rate Estimation

Authors: Yehui Yang, Bo Zhao, Junzhe Cao, Hui Ma, Yue Sun, Wenjin Wang, Zitong Yu
Published: 2026-07-29
Categories: cs.CV
arXiv: https://arxiv.org/abs/2608.00066v1

Remote photoplethysmography (rPPG) enables non-contact heart-rate estimation from facial videos, but its weak physiological signal is easily corrupted by motion, illumination changes, occlusion, skin-appearance variation, and device noise. Existing rPPG methods typically rely on a single model to directly predict heart rate or recover pulse waveforms, while different strong estimators may produce conflicting yet individually plausible candidates for the same video. To resolve these conflicts, we propose PhysAgent, an inference-time multi-agent candidate-verification framework. Unlike direct prediction approaches, PhysAgent neither trains a new base rPPG model nor asks Multimodal Large Language Models (MLLMs) to output heart rate directly. In contrast, it treats outputs from multiple base estimators as physiological hypotheses to be verified and uses a lightweight 4B MLLM, Qwen3-VL-4B, to drive multi-agent reasoning over video conditions, signal reliability, and candidate disagreement. A deterministic physiological verifier checks the fusion proposal, and a reproducible numerical fusion process produces the final heart rate. Experimental results on multiple public rPPG benchmarks show that PhysAgent improves fusion stability and reliability across different datasets and source-domain settings, while avoiding the irreproducibility and physiological inconsistency of direct MLLM prediction or unconstrained ensemble fusion. The code will be released soon.

---

### H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases

Authors: Shusen Zhang, Junyi Hu, Ye Feng, Ziteng Wang, Zhaoyuan Pan, Xiaojun Yuan, Jiangshou Hong, Guosheng Dong, Xiangzhi Wang
Published: 2026-07-29
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2608.00065v3

Terminology-intensive retrieval, especially in medical settings, depends on preserving multi-word entities, abbreviations, numerical constraints, and compositional concepts. However, existing representations lie at two extremes: single-vector retrievers often over-compress local relevance signals, while token-level late interaction retains every tokenizer subword at substantial indexing, storage, and scoring cost. This mismatch raises a natural question: can context-dependent phrases provide a useful retrieval unit between global vectors and tokens? We introduce H+ Embedding, a unified multi-granularity retriever that predicts variable-length phrase partitions, preserves uncovered tokens as singletons, and applies importance-guided unit selection with weighted MaxSim interaction. Across 16 scientific, medical, and bilingual tasks, its phrase retrieval branch exceeds the global retrieval branch by 6.91 macro nDCG@10. It also nearly matches Token while using 13.7% fewer document vectors and outperforms content-independent grouping rules under moderate vector budgets. Context-dependent phrase interaction therefore provides an intermediate quality-cost point between global compression and token-level interaction for practical retrieval systems.

---