# Research Papers — 2026-07 · bundle page 10 of 222 > Full-text markdown of papers #451–500 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/10 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/9.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/11.md) ### Evaluating Multimodal LLMs across Text and Audio Modalities for Accessible Disaster Assistance Authors: Anuridhi Gupta, Samara Mansoor, Hemant Purohit Published: 2026-07-30 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.14651v1 Effective disaster risk communication is a foundational humanitarian challenge, yet current emergency infrastructure fails to meet the needs of individuals with access and functional needs, including hard-of-hearing individuals, pregnant women, mothers with toddlers, and elderly individuals with dementia. Recent advancements in Artificial Intelligence (AI), especially Multi-Modal Large Language Models (MM-LLMs), demonstrate powerful capabilities to serve diverse users across text, audio, image, and video modalities within a single unified system, such as a chatbot. However, their suitability for deployment rests on a property that receives limited scrutiny, i.e., whether these systems produce consistent, actionable outputs regardless of the modality through which a user communicates. In this paper, we conduct a comprehensive analysis to understand the status of open-weight MM-LLMs using real emergency alert scenarios across four different vulnerable personas. These state-of-the-art (SOTA) models are evaluated on consistency of responses across text and audio modalities when the same task scenario is given. Findings indicate that no model achieves reliable consistency across modalities, and that performance gaps are heightened for personas with access needs, introducing modality-dependent inequity that undermines the humanitarian value of these systems. These results inform concrete design recommendations for building equitable, trustworthy, and inclusive AI tools for disaster risk communication. --- ### Paired Exact-Reset Evaluation of a Prediction-Derived Medium-to-Full World-Model Cascade Authors: Malo de Pastor Published: 2026-07-30 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2608.14650v1 Existing adaptive-inference and world-action-model systems use cheap-stage outputs or predicted futures to allocate additional computation. We study a narrower question: under paired exact-reset physical outcomes, can a Medium-derived interface predict when switching to a separately frozen Full predictor improves task-specific decision loss enough to justify sequential overhead? Our contribution is a paired evaluation and audit protocol, not a new generic routing rule: all candidate actions are executed from the same reset state, Medium and Full act on the same candidate set and task, and their paired physical-loss difference defines the routing target. On a fresh PushT bank (V106; 1,600 states, 39 tasks, three checkpoint pairs), a frozen prediction-interface router lowers overhead-inclusive decision cost relative to standalone Medium, standalone Full, and a latency-advantaged task-only router. We then prospectively seal a second 1,600-state PushT confirmation (V107) against a stronger current-state control using the task, a dimension-matched projection of current DINO features, and all five candidate actions, with no DINO encoder latency charged. The prediction interface lowers priced physical decision cost by 0.002549 (state-clustered 95% interval (-0.002867, -0.002238); one-sided 95% upper bound -0.002286), with negative effects for all three checkpoint pairs. A controlled-PyBullet audit independently supports a composite task-prediction-regime router. The sequential router remains slower than fixed policies, and its advantage is restricted to low compute prices. The evidence supports incremental routing information in the tested prediction interface beyond one deliberately favoured current-DINO control, but not causal sufficiency, compute saving, closed-loop value, or cross-family generality. --- ### Discrete Diffusion Language Models Are Training-Free Multi-Label Classifiers Authors: Pawan Kumar Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.14649v1 We present dLLM-SetScore, a training-free method that uses discrete masked-diffusion language models for multi-label text classification. For each candidate label, it asks a short yes/no question and compares the probabilities of the two answer tokens at one masked position. The method uses no task-specific fine-tuning or training on textual-entailment datasets; a 200-example labelled validation slice selects thresholds, temperature, and prompt wording. We first show that placing all labels in one prompt creates a strong slot-position asymmetry: the first answer slot is predicted positive on $99.4\%$ of GoEmotions examples and $100\%$ of Reuters examples. Per-label scoring places every label in the same syntactic position, making predictions invariant to label order and avoiding this artifact. We evaluate LLaDA-8B and Dream-7B on six datasets against NLI models, an autoregressive LLM, SetFit, and supervised classifiers. On the five datasets shared by both diffusion families, Instruct checkpoints improve macro-F1 in 9 of 10 comparisons and micro-F1 in 8 of 10, although these comparisons do not identify the cause. Within our protocol, LLaDA-Instruct records the highest training-free values for both Reuters and ECtHR metrics. We prove permutation invariance, characterize thresholded decisions under weighted Hamming loss, and derive shortlist ceilings for recall and F1. An exploratory local Joint Set Refinement step lowers F1 from biased and unbiased initializations and is retained as a negative result. --- ### Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings Authors: Leonardo Kuffo, Peter Boncz Published: 2026-07-30 Categories: cs.DB, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.14648v1 In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dimensionality reduction, quantization, and dimension pruning. We propose an indexing pipeline in which these techniques are applied before clustering, and we focus on how they affect storage footprint, clustering time, and the quality of the resulting centroids for vector search tasks. Our results reveal that using full-precision vectors for clustering is excessive, as even 1-bit codes can achieve near-optimal clustering quality (within 1% of ideal) while reducing storage requirements by 60x and delivering attractive performance gains (Figure 1). We open-source our implementations at https://github.com/cwida/SuperKMeans. --- ### SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation Authors: Chenyang Jiang, Changhan Huang Published: 2026-07-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.14647v1 Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns are conditioned on that reply, and uniform distillation can spend loss on tokens that carry little corrective signal. We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD. For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss; final-answer and FULL-preservation losses are unchanged. This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead. We compare SMOPD with a correctness-scaling variant that multiplies a common detached reliability proxy using final-answer correctness. On LiC with Qwen3 models, SMOPD improves SHARDED-view accuracy by 1.0-2.5 percentage points in single-seed 1.7B, 4B, and 8B comparisons, and a small 4B multi-seed check shows a +1.7pp mean SHARDED gain over baseline (two-tailed p = 0.022). Adding the outcome scalar is harmful without masking at 1.7B (-4.0pp) and remains scale-dependent when combined with masking (+1.3pp at 4B, neutral at 1.7B, and -0.5pp at 8B). These archived aggregate results suggest that token-level uncertainty is a more reliable stabilization signal than scalar final-answer correctness in this evaluated dirty-history OPSD setting, while leaving causal mechanism tests and broader benchmark validation to future work. --- ### iFuzz-Meta: An Interpretable Fuzzy Learning Framework Bridging Top-Down and Bottom-Up Knowledge Integration Authors: Xiaowei Jiang, Daniel Leong, Beining Cao, Nan Zhou, Yingtao Ren, Yu-Cheng Chang, Thomas Do, Chin-Teng Lin Published: 2026-07-30 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2608.14646v1 Interpretable representation learning remains a key challenge in modern neural computation, particularly when models are expected not only to perform but also to explain their reasoning. This paper introduces iFuzz-Meta, an interpretable fuzzy rule-based learning framework that preserves human-understandable reasoning structures within modern neural architectures. Each fuzzy rule corresponds to a semantic and spatial prototype defined in the original feature space, enabling transparent inference and direct interpretability. Meta-learning is employed as an analytical paradigm to examine how these interpretable rules reorganize across tasks and domains, providing a principled means to link algorithmic adaptation with cognitive representation. A knowledge-guided regularization mechanism further enables a top-down-bottom-up integration, in which theoretical priors act as soft inductive biases while data-driven learning refines and extends them. This dual process ensures that adaptation proceeds along semantically and physiologically meaningful trajectories, rather than arbitrary parameter shifts. Evaluations demonstrate that iFuzz-Meta achieves interpretable reasoning and stable cross-domain generalization, establishing a potential general pathway toward explainable and knowledge-aware fuzzy systems. --- ### The Edge-based Contiguous p-median Problem with Connections to Logistics Districting Authors: Zeyad Kassem, Adolfo R. Escobedo Published: 2026-07-30 Categories: cs.AI, cs.DM arXiv: https://arxiv.org/abs/2608.11230v1 This paper introduces the edge-based contiguous p-median (ECpM) problem to partition the roads in a network into a given number of compact and contiguous territories. Two binary programming models are introduced, both of which incorporate a network distance. The first model requires an exponential number of cut set-based constraints to model contiguity; it is paired with a separation scheme that usually generates only a small number of these constraints, namely, a branch-and-cut (B&C) algorithm. The second model utilizes a polynomial number of shortest-path constraints to model contiguity and can be solved with off-the-shelf solvers. The respective solution approaches are tested on road networks with over 2,700 nodes and close to 3,400 edges, yielding models with over 9.6 million binary variables. Solving the model based on shortest path contiguity (SPC) constraints via standard branch and bound attains speedups in computational time of up to 17x relative to the cut set-based B&C implementation. In addition, the SPC constraints are demonstrated to be supervalid inequalities of the edge-based p-median (EpM) model (i.e., for which contiguity is not explicitly required), meaning that they may cut off integer-feasible solutions and some, but not all, of the optimal solutions of this simpler problem. Finally, the paper explores structural insights and connections between ECpM and the edge-based districting (EBD) problem, which enforces an additional work balance criterion. An existing model that utilizes cut set-based contiguity constraints was unable to find a feasible solution within 12 hours for any of the tested instances, while an SPC-based EBD model was able to solve most of these to optimality. --- ### Rescene: band-limited stochastic forcing turns a frozen neural weather operator into a climate emulator Authors: Minjong Cheon Published: 2026-07-30 Categories: physics.ao-ph, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.09971v1 Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-range skill matches or exceeds that of the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES). However, when these models are integrated freely beyond the horizon they were trained for, they blow up, drift, or lose their seasonal cycle, and retraining them for stability is expensive. We therefore ask what can be recovered from a strictly frozen backbone. We present Rescene, a 0.4 M-parameter wrapper around a frozen 1.5 degree, 6-hourly vision-transformer operator, developed using ERA5 reanalysis data and comprising a deterministic "slow clock" (0.33 M) that blends the forecast toward a lead-aware day-of-year climatology and a generative head (0.06 M) that adds a spectrally shaped stochastic perturbation at every step. The performance evaluation demonstrates that the deterministic wrapper alone is stable for decades but collapses daily variability to 40% of ERA5. Adding the generative head restores 126% (Z500) and 130% (MSLP) of the observed daily variability with pattern correlations of 0.89 and 0.92, recovers 82% of the observed blocking frequency, keeps the ensemble calibrated (spread-skill ratio 0.78-0.97 from day 7 to day 90), and integrates for 100 years with no detectable drift (+0.008 +/- 0.014 K per century). Moreover, because the perturbation is band-limited to total wavenumber $k \le 20$, the small scales are never forced, yet realistic $k \ge 20$ power is sustained: a direct decomposition of the 6-hourly energy budget shows that the frozen operator supplies 28 times more energy than the perturbation at $k \ge 40$, with a fractional growth rate 247 times larger at the grid scale than at planetary scales. --- ### An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop Authors: Yiwen Zhang, Eloise Zeng, Jaeha Lee, Tony Yue Yu Published: 2026-07-30 Categories: cs.AI, cs.LG, cs.MA, cs.RO arXiv: https://arxiv.org/abs/2608.07542v1 Autonomous research loops driven by large language models can run machine-learning experiments at scale but tend to drift toward local refinements of whichever metric they optimise rather than testing the hypotheses that motivate the experiments. We address this structurally and present an AI Scientist for studying generalisation in quadruped robot navigation policies in simulation. Building on the autoresearch paradigm of Karpathy, our loop adds three components: an immutable experiment card that pairs each iteration's prediction with its outcome under a fixed schema, so a falsified hypothesis cannot be retconned; specialised subagents restricted to mechanical roles; and kkanbu, a preference oracle that holds the user's research taste as a typed knowledge graph and is the only component permitted to make subjective judgements. To isolate the oracle we run the identical loop twice across eleven research streams, with and without kkanbu. Neither arm drifts: both falsify roughly three quarters of their own hypotheses, and the best trained policy comes from the oracle-less arm. What the oracle changes is direction, not score: it alone explores test-time adaptation, it authored the winning designs where its arm led, and it carried lessons across streams that the other arm repeatedly re-derived. The scaffold keeps the loop honest; kkanbu decides where it looks. --- ### NeuroPilot: An Agent-Driven Smart Pipeline for Processing, Quality Control, and Managing Neuroimages Authors: Yiyao Chen, Yucheng Li, Jungong Tong, Shaoqi Wang, Kunhao Zhou, Ziquan Wei, Monica Murea, Marissa DiPiero, Tingting Dan, Guorong Wu Published: 2026-07-30 Categories: cs.CV, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.07541v1 Transforming raw neuroimage archives into analysis-ready derivatives relies on three brittle stages: data standardization, modality-specific preprocessing, and quality control (QC). While individual neuroimaging tools are well developed, their orchestration requires project-specific scripts, environment-adaptive tuning, and labor-intensive manual QC. To address this, we introduce NeuroPilot, a multi-agent system that digitalizes the expertise of neuroimage processing, QC, and data management into three LLM-invocable skills: dcm2bids-skill, neuroimage-pre-skill, and qc-agent-skill. The LLM-driven agent autonomously orchestrates workflows, generalizing various infrastructure settings into a single configuration to achieve the highest scalability. Demonstrating the system's generalizability, we deployed NeuroPilot across 17 cohorts (>123,000 subjects) spanning infant to aging populations and multiple MRI modalities (structural, diffusion, functional). In practice, after standardizing data via the dcm2bids-skill, the agent dynamically routes datasets to the optimal neuroimage-pre-skill based on available modalities and cohort traits (e.g., dispatching T1w and fMRI data to fMRIPrep, or selecting specialized pipelines for infant cohorts). The qc-agent-skill then drives an evidence-based, semi-automated QC via a 3-D browser dashboard, utilizing a multi-tiered verification system to optimize failed cases and escalate complex issues for supervisor inspection. Quantitatively, our QC agent screened 558 production subjects, validating its automated flags against FreeSurfer's topology-defect metrics. The infant processing pipeline achieved a 100% (201/201) completion rate on QC-validated inputs. Importantly, NeuroPilot compresses the traditional 2--3 month timeline for training staff and processing complete datasets into a single week. NeuroPilot is deployed in https://wanda-cyberbench.com/. --- ### Can LLM Agents Price Competitively? A Dynamic Multi-Attribute Auction Benchmark for Agentic Commerce Authors: Shimaa Ahmed, Yiwei Cai, Mohsen Minaei, Rahul Rachuri Published: 2026-07-30 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.00102v1 Agentic commerce is moving from concept to deployed infrastructure: payment networks, retailers, and AI platforms are setting the stage for agents to transact on behalf of merchants and consumers. Yet whether the LLMs behind these agents can price competently in real markets, where customer preferences are hidden, competitors adapt in real time, and demand can shift without warning, has not been systematically tested. We introduce Bazaar, a dynamic sealed-bid benchmark for multi-attribute auction under these conditions. Despite its dynamics, the benchmark is grounded in closed-form customer utilities, enabling exact evaluation. Across 11 frontier LLMs from four providers, the leading agents on customer acquisition (e.g. Gemini 3.1 Pro) are often not the leading agents on profit (e.g. Opus 4.6). The ranking shifts again under demand shocks: agents that learned fastest pre-shock are typically the slowest to revise their beliefs afterwards, while Gemini 3.1 Pro recovers fastest despite not leading on profit. However, even the strongest agent captures less than a third of hindsight-optimal profit, suggesting current LLMs are progressing in agentic commerce but leave substantial headroom. --- ### Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale Authors: Banruo Liu, Haoran Qiu, Íñigo Goiri, Rodrigo Fonseca, Ricardo Bianchini, Esha Choukse Published: 2026-07-30 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00101v1 AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different from chatbots. We present the first production-scale characterization of this workload using sampled GitHub Copilot traces from June 2026, comprising 3.2M users, 13M sessions, 761M LLM calls, and 95T tokens. Our analysis reveals distinctive workload properties with important systems implications. For example, agentic coding sessions consist of sparse user-initiated turns, each unfolding into an autonomous agent loop of LLM calls almost always coupled with tool execution. This structure yields KV cache hit rates averaging 90% within a turn, but falling to 55\% across turn boundaries and drastically invalidated after events like model switches or context compaction. Diverse workflows and user behaviors are observed with variable and long-tailed token consumption, time span, and tool calls. We highlight the difference between quick agentic turnaround times and the minutes-long user idle periods at turn boundaries, and design a lightweight idle-time predictor that captures 86-90\% of total idle time, enabling proactive decisions for efficient resource orchestration. These findings challenge assumptions underlying current LLM-serving systems and provide an empirical foundation for agent-native infrastructure. --- ### SPARC-Rad: A Multimodal Benchmark Dataset and Evaluation Pipeline for Spatial and Anatomical Reasoning in Radiology Vision-Language Models Authors: Satvik Tripathi, Mustafa Ege Seker, Kristian Quevada, Ebubechukwu D Enwerem, Pratham Khandelwal, Emine Meltem, Bera Koca, Shahriar Faghani, Jacinta Arnold, Dania Daye, Tessa S. Cook Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.00100v1 Vision-language models (VLMs) are increasingly being evaluated for medical imaging, but many available benchmarks emphasize disease classification, report generation, or broad visual question answering rather than the spatial and anatomical reasoning required for radiology. We developed the Spatial Perception and Anatomical Reasoning in Clinical Radiology (SPARC-Rad) Benchmark, a manually curated multimodal benchmark dataset and evaluation pipeline for assessing these capabilities in radiology VLMs. SPARC-Rad includes 300 image-question pairs derived from healthy control imaging studies in The Cancer Imaging Archive (TCIA), spanning CT, MRI, and radiography across the abdomen, chest, breast, neuro, and musculoskeletal categories. Radiology trainees manually designed and annotated questions to evaluate anatomical identification, localization, laterality, regional recognition, device identification, and inter-structure spatial relationships. The evaluation pipeline supports standardized prompting, structured output collection, response normalization, LLM-as-judge grading, human quality review, binary correctness scoring, and subgroup analysis by modality, anatomy, and reasoning type. SPARC-Rad provides a reusable framework for evaluating whether VLMs can provide reasoning for radiologic anatomy as a spatial system, supporting future model development, failure-mode analysis, and pre-deployment assessment. --- ### LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology Authors: Ximing Ran, Jie Xu, Peng Jin, Zhaohui Qin, Zhexing Wen, Jiaying Lu Published: 2026-07-30 Categories: q-bio.GN, cs.AI arXiv: https://arxiv.org/abs/2608.00099v1 Gene Ontology (GO) enrichment analysis is a foundational tool for translating large-scale genomic data into biological insights, but typically yields hundreds of redundant terms that obscure overarching themes. Existing summarization tools rely on fixed similarity metrics (REVIGO, GOSemSim, clusterProfiler::simplify()), gene-overlap measures (Metascape), or static hierarchy mappings (GO-slim), and therefore cannot incorporate biological context. Manual curation provides context-aware grouping but is subjective and labor-intensive. A scalable, context-aware framework is needed to cluster GO terms into interpretable higher-order biological domains. Here we present LLMBDC (Large Language Model for Biological Domains Oriented Clustering of Gene Ontology), a training-free framework that leverages zero-shot semantic reasoning of LLMs with confidence scoring to cluster GO terms into BioDomains using only ontology information at inference time. Benchmarked across Alzheimer's disease (AD) and Fragile X syndrome (FXS) against six baseline methods including SapBERT, LLMBDC achieved substantially higher precision, recall, and clustering performance. Against ground-truth annotations, LLMBDC improved ARI from 9.7% to 73.3% (AD) and from 15.7% to 66.6% (FXS) over REVIGO, with corresponding NMI gains from 59.9% to 73.4% (AD) and 66.0% to 79.5% (FXS). A Cauchy combination test further confirmed that aggregated BioDomains retained statistically significant functional signals. LLMBDC provides a scalable, reproducible, and interpretable route to context-aware, system-level interpretation of GO enrichment results while preserving biological specificity. --- ### GRAIN: Molecules Are Not the Right Granularity -- Active-Ingredient Modeling for Safe Medication Recommendation Authors: Juao Fan, Jinhan Li, Shengxin Zhu Published: 2026-07-30 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2608.00098v1 Medication recommendation from electronic health records must balance predictive accuracy against the risk of adverse drug-drug interactions (DDIs) under polypharmacy. Existing safety-aware recommenders operate at one of two granularities: the drug code, which treats each medication as an indivisible token, or the molecular substructure, which is finer than pharmacological interaction knowledge is actually organized. We argue that the active ingredient is the missing granularity, and introduce GRAIN, a medication recommendation framework built around it. GRAIN encodes longitudinal patient trajectories (diagnoses, procedures, past medications) with a selective state space backbone that handles long, irregular visit sequences in linear time. On top of it we introduce a joint objective unifying three knowledge sources aligned to a common medication vocabulary: a drug-level DDI graph, an ingredient-level DDI graph obtained by normalizing medication codes to active ingredients via RxNorm, and an EHR-derived co-prescription graph. A proportional controller adapts the accuracy-safety trade-off to the observed validation DDI rate rather than fixing it a priori. Under strictly matched settings -- identical preprocessing, cohort, vocabulary, split, and evaluation code -- GRAIN improves over a re-implemented MambaHealth baseline on MIMIC-IV across all standard multi-label metrics (Jaccard 0.4488 to 0.4983, PRAUC 0.6911 to 0.7485, F1 0.5989 to 0.6453) while reducing the drug-level DDI rate from 0.1875 to 0.0948. We further define an ingredient-level DDI rate, a safety measure invisible to drug-code-level evaluation. The results indicate that ingredient-level normalization recovers predictive signal erased by code-level aggregation, and that it is complementary to, rather than in competition with, accurate sequence modeling. --- ### Untrainable elements determine what physical learning remembers Authors: Bijaya Dangol Published: 2026-07-30 Categories: cond-mat.soft, cond-mat.dis-nn, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00097v2 Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements. The learned function is decided by where on the solution manifold training lands. Two properties could decide it, and they have not been separated: the circuit's invariance under rescaling every conductance, and the rule's conservation of the mass K = (1/2) sum_e kappa_e^2. We separate them. When every element is trainable, all three vector fields are homogeneous in the conductances, so the initialization scale is provably inert. An element the rule does not adjust breaks that homogeneity whatever its constitutive law. Across twenty topologies the learned function moves with the initialization scale by a median of twelve percent with fixed rectifiers and eight with fixed linear resistors, against 3e-8 when every element is trainable; a single fixed rectifier produces the whole effect. The conservation law is not what protects the function: AL, which we prove dissipates the mass at exactly twice its own loss, remembers its initialization as strongly as the rules that conserve it, and the memory survives in runs where K is conserved to 1e-4. Raising the fixed-element count from one to eight multiplies the conservation drift by five thousand and leaves the memory unchanged, while the all-trainable circuit under AL drifts comparably and remembers nothing. What the rule's conservation structure does control is solution quality: at matched training loss AL is worse than EP and CL in four of six small circuits, by a median of three to seven percent, though the ordering is not stable across checkpoints and does not reproduce at fifty nodes. Physical learning therefore carries two independent inductive biases, one belonging to the circuit and one to the rule, and only the first is a memory of how the device was built. --- ### Conservation laws determine what physical learning remembers Authors: Bijaya Dangol Published: 2026-07-30 Categories: cond-mat.soft, cond-mat.dis-nn, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00097v1 Physical learning rules such as equilibrium propagation (EP), coupled learning (CL), and adjoint coupled learning (AL) train resistive networks through local measurements. In the small-nudge limit EP and CL exactly conserve the conductance mass K = (1/2) sum_e kappa_e^2, a property that stabilizes training. We show that conservation also governs the inductive bias of these rules. For a single output we prove that EP and CL are trajectory equivalent, so single-output experiments cannot distinguish what the two rules learn. We prove that AL does not conserve the mass but dissipates it at exactly twice its own loss. In linear circuits we prove that the conserved mass has no functional consequence: all three vector fields are homogeneous in the conductances, so the selected solution is independent of the initialization scale. Fixed nonlinear elements break this protection. In diode circuits the learned input-output function depends on the initialization scale by up to about forty percent, an effect absent in linear controls, and the conservative rules retain this memory permanently while the dissipative rule partially erases it. At matched training loss the dissipative rule typically generalizes worse than the conservative rules, although it reaches low training loss faster; the penalty correlates with the mass dissipated en route and fades in larger circuits, where little mass is lost. The conservation structure of a local learning rule thus sets its initialization memory, its training speed, and, where dissipation is appreciable, its generalization; it should be treated as a design parameter of physical learning machines. --- ### Logographic Character Visual Pretraining via Semantic-based Contrastive Learning Authors: Daqian Shi, Wei Cao, Xiaoyu Zheng, Lida Shi, Xiaolei Diao, Cedric M John Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.00096v1 Current deep learning-based character vision studies, e.g., text recognition, character image denoising, and historical text completion, are offering new solutions for learning, managing, and utilizing character resources. However, the performance of these studies peaks only with large and balanced datasets, which is a rarity with real-world character datasets, especially for logographic character languages, e.g., Chinese. The imbalance in data distribution of logographic characters is a common issue due to differences in character usage frequency and new characters being continuously created. In this paper, we propose a novel method for logographic character recognition, which introduces a multi-modal learning approach using visual semantics and contextual semantics of characters. A novel pre-training strategy is designed to enhance deep visual representations, especially for datasets suffering from issues of imbalanced and rare instances, by extracting the contextual semantics of each character from the corresponding language models. We conduct experiments across various datasets to evaluate our character recognition method and further validate the contrastive pre-training strategy by several downstream tasks. Experimental results demonstrate the superiority of our method compared to state-of-the-art methods. --- ### Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Mesh Authors: Junhao Chen, Mingjin Chen, Henghaofan Zhang, Minglin Chen, Liaoyuan Fan, Boran Zhang, Saining Zhang, Mingze Sun, Hao Zhao, Ruqi Huang, Zhihao Li, Yufei Wang Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00094v2 Pretrained video diffusion models can act as renderers when the desired scene state is already specified by an animated mesh, a camera trajectory, and a reference image. This 4D generative rendering setting raises a representation question: what image-format condition lets a video backbone obey both camera motion and scene-internal animation? We propose DAR, a reference-guided renderer that extends Wan2.2 camera control from Plücker rays alone to a joint camera-plus-geometry interface. DAR projects a neural 4D G-buffer (tracking, world position, and normal) from the animated mesh and injects it through a widened control adapter while preserving the pretrained image-to-video prior. The central design choice is the pair of tracking and world position. Tracking identifies the persistent surface element that should carry appearance; world position gives its current scene-coordinate state; normal supplies local shape. Depth plus calibrated rays can recover 3D in principle, but depth is a camera-dependent chart in which camera and object motion are mixed. On the 68-case DAR-4D benchmark, LoRA DAR reaches PSNR 23.22, SSIM 0.895, and LPIPS 0.134, improving over off-the-shelf Wan2.2-Depth by 1.54 dB PSNR; a full fine-tune reaches PSNR 25.36 and SSIM 0.917. Matched ablations show that replacing world position by depth reduces PSNR by 1.26--1.55 dB at every checkpoint, supporting tracking+world-position correspondence as a practical 4D rendering condition. --- ### Rethinking Total Absorption Gamma Spectroscopy Deconvolution: Supervised Machine Learning vs Response-Matrix Methods Authors: J. Balibrea-Correa, E. N{á}cher, C. Fonseca-Vargas, J. L. Tain Published: 2026-07-30 Categories: physics.data-an, cs.LG, nucl-ex arXiv: https://arxiv.org/abs/2608.00090v1 The extraction of $β$-feeding distributions in Total Absorption $γ$-ray Spectroscopy constitutes a challenging inverse problem, particularly in nuclei with complex decay schemes involving a large number of excited states. In such cases, the measured spectrum arises from the superposition of many detector response functions, making the determination of the individual feedings intrinsically ill-posed and highly sensitive to the methodology employed. In this work, we present a systematic comparison between supervised Machine-Learning techniques and Response-Matrix methods using realistic Monte Carlo simulations of an experimental Total Absorption Spectrometer. Supervised Machine-Learning approaches construct a non-parametric estimator that infers level feedings from the measured spectrum after a training stage, whereas Response-Matrix methods determine the feeding distribution by directly minimizing the difference between measured and reconstructed spectra. Our results show that supervised Machine-Learning techniques achieve superior accuracy in the reconstruction of individual feeding intensities, whereas Response-Matrix methods provide robust and physically consistent initial solutions. These findings support a hybrid strategy in which a Response-Matrix method is first used to obtain an initial feeding estimate, which is then refined using a supervised Machine-Learning approach to achieve improved overall accuracy. --- ### DODA: A Database of Datasets for Aesthetics Research Authors: Lisa Koßmann, Ralf Bartho, Christoph Redies, Johan Wagemans Published: 2026-07-30 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.00089v1 With rapid growth in the fields of empirical and computational aesthetics we have seen a vast increase in large image datasets annotated for aesthetics. As the image databases differ widely in many respects (e.g., different standards for annotation), it can be tedious to find the dataset that fits one's research needs best. The absence of a centralized open-science search system causes additional problems. Currently, researchers typically share dataset links in papers or on diverse platforms like OSF, GitHub or Dropbox. Manually searching for details like image quality and content often requires downloading all datasets. Therefore, we present the Database Of Datasets for Aesthetics (DODA), an intuitive Web application in which researchers can browse all important datasets for aesthetics research. DODA provides general information about these datasets (size, resolution, type of annotation, number of annotators, etc.) and for many of them also precomputed quantitative image properties. We discuss relevant criteria for selecting a suitable dataset with DODA and illustrate the benefits of reusing datasets. Our approach facilitates collaboration across the fields of empirical and computational aesthetics. Keywords: empirical aesthetics, computational aesthetics, machine learning, image annotation, quantitative image properties, Open Science --- ### SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization Authors: Lyuzhou Ye, Thanh Dat Le, Yan Huang Published: 2026-07-30 Categories: eess.SP, cs.AI arXiv: https://arxiv.org/abs/2608.00087v1 Accurately predicting directional radio maps is essential for wireless applications, yet prior approaches primarily focus on omnidirectional signals and typically treat transmitter localization and signal map reconstruction as separate tasks. In omnidirectional settings, predicting the maximum signal location often coincides with the transmitter position, which limits the need for explicit joint modeling. However, in directional propagation where angular effects, reflections, and building occlusions play critical roles, this assumption no longer holds. To address this gap, we propose SymNet, a unified framework that jointly predicts directional radio maps and transmitter locations from sparse signal measurements. SymNet incorporates a prediction head for transmitter localization alongside radio map reconstruction, enabling simultaneous learning of both tasks. This joint formulation leverages their complementary information and leads to consistent improvements over treating them separately. Experiments on challenging directional scenarios demonstrate that SymNet outperforms state-of-the-art baselines, achieving superior accuracy in both radio map reconstruction and transmitter localization. --- ### DS@GT ARC at MEDIQA-CORE-Task-1 2026: Trimodal Model Fusion with Task-Specific Gates for Brain Tumor Subtype Classification Authors: Hoang Thanh Thanh Truong, Charles R. Clark Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00086v1 Brain tumor diagnosis is a time-sensitive process in which patients may wait weeks for a finalized pathology report. This problem motivates automated systems that classify tumor subtype from multimodal inputs. This paper details the DS@GT ARC team's work for ImageCLEFmed MEDIQA-CORE 2026 Task~1, Brain Tumor Subtype Classification. The task evaluates three glioma classification problems: Level-1 Molecular Type, LGG vs HGG, and WHO Grade. We combine pre-extracted MRI (NeuroVFM) and histopathology (Prov-GigaPath) embeddings with free-text radiology reports. Our team explored two trimodal fusion architectures, two report encoders (RadBERT and Llama-3.1-8B-Instruct), and a biologically motivated post-processing stage. We achieve a mean macro-F1 of 0.801 under the Fully Multimodal condition, exceeding the organizers' baseline of 0.796 and ranking second among the teams whose code passed verification. Additional evaluation across modality-dropping conditions shows that this advantage depends heavily on the availability of the histopathology modality, and that our system falls behind the baseline when modalities are missing. Our code is available on GitHub at https://github.com/dsgt-arc/imageclef-mediqacore-2026. --- ### TORUS: A Test of Rendering-Understanding Self-Coherence for Unified Audio Models Authors: Aryan Vijay Bhosale, Harshit Rajgarhia, Abhishek Mukherji, Dinesh Manocha Published: 2026-07-30 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.28896v1 Unified audio models capable of audio understanding, audio generation and, increasingly, audio editing are proliferating rapidly. Yet a basic question about them remains unanswered: do the two heads of a unified model agree about the same audio? Current practice evaluates each capability in isolation on specialized benchmarks, and never asks whether a model can make sense of its own generations. We present TORUS, the first self-coherence test for audio-native unified models. TORUS comprises 48 three-stage self-coherence tests carrying 432 six-option questions spanning speech, sound and music across five task families. We holistically evaluate five open unified models alongside a Cascaded Baseline that combines state-of-the-art specialized generation, editing and understanding models. The best unified model answers 50.5% of questions against the Cascaded Baseline's 63.2% and a 16.7% chance floor. Models struggle on audio editing. Among the evaluated audio models (specialized and unified), we observe limited self-coherence, and thus position self-coherence as an essential test for future audio systems. --- ### Identifying Informative Environments for Cognition Parameter Inference via Bayesian Experimental Design Authors: Manisha Dubey, Rimvydas Rubavicius, N. Siddharth, Subramanian Ramamoorthy Published: 2026-07-30 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2607.28894v2 Computational cognitive modeling seeks to infer latent cognitive mechanisms underlying observed behavior. Bayesian inverse planning provides a principled framework for such inference, but its success depends critically on the experimental environment. Existing approaches typically treat environments as fixed, leaving open the question of which cognitive experiments are most informative for cognition parameter inference. We formulate the design of cognitive planning experiments as a Bayesian Experimental Design (BED) problem, treating the experimental environment as the design variable. We establish an exact Monte Carlo BED benchmark and introduce an amortized Bayesian experimental design framework for efficient posterior inference and design evaluation. Experiments on the Mouselab-MDP process-tracing paradigm show that amortized BED closely matches the environment rankings of exact Monte Carlo BED while substantially reducing computational cost. We further show that no single environment is uniformly optimal across cognitive inference objectives, revealing trade-offs between expected information gain, posterior recoverability, and information efficiency. These results provide a principled framework for designing informative cognitive experiments for Bayesian parameter inference. --- ### Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth Authors: Alex Liu, Lief Esbenshade, Michael Xiao, Victor Tian, Zachary Zhang, Kevin He, Min Sun Published: 2026-07-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28890v1 Evaluations of LLM-assisted qualitative coding almost universally measure model performance as agreement with human coders, a practice that presumes human coding is the standard to approximate. This study provides empirical evidence that the presumption fails in ways agreement metrics cannot detect. Five LLM systems and three trained human coders independently applied a 72-item hierarchical codebook to 2,560 educator messages from a K-12 AI platform. Beyond conventional agreement analysis, an independent domain expert judged 855 pairwise comparisons of code sets blind to source, treating human and machine sources symmetrically. The two evaluation approaches diverge in both directions. Human-LLM agreement (mean Jaccard 0.30) falls well below human-human agreement (0.52), which standard practice would read as inferior LLM coding, yet the blind verifier preferred human and LLM coding at indistinguishable rates (51.5% vs. 48.5%, p = 0.537), and a Bradley-Terry ranking placed two LLMs above two of three human coders. For several substantive codes, human consensus encoded shared bias that the verifier rejected in favor of the LLM interpretation. Agreement-based evaluation is therefore insufficient for automation decisions, and the study demonstrates a transferable verification protocol and a code-level division-of-labor framework. --- ### Human-LLM Collaborative Inductive Coding for Conceptualizing K-12 Educator AI Use Authors: Alex Liu, Min Sun, Lief Esbenshade, Michael Xiao, Victor Tian, Zachary Zhang, Kevin He Published: 2026-07-30 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.28889v1 Qualitative researchers increasingly encounter interaction corpora whose scale exceeds what manual coding alone can address, and large language models (LLMs) are frequently proposed as analytic assistants. The open questions are not whether LLMs can participate in qualitative analysis but to what extent, in what phases, and under what safeguards. This article provides a detailed procedural account of a multi-phase human-LLM collaborative pipeline that adapted open, axial, and selective coding to develop a hierarchical codebook from 45,000 messages exchanged between K-12 educators and a generative AI platform. Across three phases, LLMs generated candidate labels and structured annotations at scale, while human researchers retained conceptual authority over category definitions, merging decisions, and interpretive frameworks. The resulting instrument was then tested through systematic human coding, in which three trained coders with educational domain expertise applied the codebook to an independent sample of 2,560 messages, established reliability through iterative calibration using set-valued agreement measures appropriate for multi-label annotation, and extended the instrument with five codes that the LLM-assisted phases had not surfaced. The final codebook comprises 72 items within 19 categories and six domains. We reflect on the methodological decisions the pipeline required, including the choice of a conversational unit of analysis, the treatment of the LLM as a labeling instrument rather than an interpretive agent, the measurement of intercoder agreement under multi-label coding, and the conditions under which human domain expertise remained decisive. The account is offered as an auditable template for qualitative researchers considering LLM assistance in codebook development while preserving human interpretive authority. --- ### To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing Authors: Amir M. Ebrahimi, Mohammed Mehedi Hasan, Aaditya Bhatia, Gopi Krishnan Rajbahadur, Ahmed E. Hassan Published: 2026-07-30 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.28887v1 Large language models increasingly write and repair production code, yet evidence is mounting that their test-passing patches leave codebases harder to maintain. We identify one concrete source: deletion avoidance, the systematic tendency to retain code that an intended edit requires removing. Across the five leading models on the official SWE-bench Verified leaderboard, deletion recall against the developer patch reaches at most 71.7% even on tasks all five solve, and models reach the right file for over 92% of required deletions but cut the exact line in under 52% of cases. Instead, 29.0% of passing patches wrap the targeted code in a guard or fallback, a pattern we call Guard-and-Go. Such patches pass because the original tests rarely check removal: when we retrofit 34 Verified tasks with tests that fail if the targeted code remains, four frontier models spanning closed and open weights fall from 63.2% to 41.9%. Because real repairs mix removal with addition, we curate CanItDelete, a benchmark of 200 tasks mined from real commits whose entire required edit is deletion. Even with the addition work gone, the best model still fails one task in five, and smaller open models fall to 18.0%. We then ablate GPT-5.6 Sol under four cumulative prompts; success moves little until we supply the exact lines, which nearly eliminate incomplete deletion yet raise success only to 80.5% because the model then deletes beyond the spans or adds code instead. Finally, through a pilot study we show one potential fix: teaching deletion during post-training reduces deletion avoidance and improves broader code-editing performance, suggesting the behavior is undertrained rather than beyond reach. --- ### Fragility of Value under Imperfect Alignment Authors: Winter Cross, Léo Cymbalista, Alfred Harwood, Jose Faustino Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28881v4 As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that these systems are aligned with humanity. A common fear in AI safety is that human value is fragile -- that is, optimizing too heavily for an imperfect proxy to human values will lead to a catastrophic outcome. In this paper, we present a model of the alignment problem where an agent undergoes idealized alignment training that guarantees its value function satisfies a proxy condition before optimizing the world. Our primary results identify conditions on the human value function and the accuracy of several proxy conditions under which an agent with an $η$-catastrophic value function, one that is guaranteed to take the expectation of human value below $η$ in the limit of optimizing power, would be deployed. Our results highlight the danger of overoptimization and motivate AI designs that limit optimization pressure, such as quantilizers, rather than relying solely on pre-deployment training. --- ### Fragility of Value under Imperfect Alignment Authors: Winter Cross Published: 2026-07-30 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28881v2 As more responsibility is placed upon AI systems, it becomes increasingly important to guarantee that these systems are aligned with humanity. A common fear in AI safety is that human value is fragile -- that is, optimizing too heavily for an imperfect proxy to human values will lead to a catastrophic outcome. In this paper, we present a model of the alignment problem where an agent undergoes idealized alignment training that guarantees its value function satisfies a proxy condition before optimizing the world. Our primary results identify conditions on the human value function and the accuracy of several proxy conditions under which an agent with an $η$-catastrophic value function, one that is guaranteed to take the expectation of human value below $η$ in the limit of optimizing power, would be deployed. Our results highlight the danger of overoptimization and motivate AI designs that limit optimization pressure, such as quantilizers, rather than relying solely on pre-deployment training. --- ### LayoutBench: Performance Benchmarking of Cloud Storage Layouts for Multimedia Data Authors: Debopam Sanyal, Hongjie Chen, Alexey Tumanov, Joshua Kimball Published: 2026-07-30 Categories: cs.DC, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2607.28880v1 Modern multimedia machine learning workloads increasingly store large-scale datasets in cloud object storage services such as AWS S3. How these samples are physically organized in storage (i.e.,storage layout) directly affects how quickly and cheaply they can be retrieved. Yet the benchmarks used to guide storage decisions today focus on database engines and query processing, and none systematically evaluates how different storage layouts perform for multimedia data retrieval. We present LayoutBench, the first benchmark designed to fill this gap. It evaluates three representative layout strategies: storing each sample as an individual object (L1), sequentially packing samples into tar archives (L2), and organizing samples as columns in Parquet files (L3). We measure retrieval time, data transferred, and monetary cost using 11 queries of varying result-set sizes on ImageNet across six AWS EC2 instance configurations that span different network bandwidth and memory tiers. Our experiments reveal that L2 achieves lower latency than L1 and L3 through connection reuse, but loses this advantage as retrieval sizes become very large. L3 is the fastest for very large retrievals but transfers substantially more data across all query sizes due to row-group granularity, and requires significantly more memory. Across all layouts, data transfer cost dominates total expenditure, with L3 costing an order of magnitude more than L1 or L2. --- ### RareSense: Rarity-Aware Similarity Search for Anomaly Retrieval in Transactional Data Authors: Sidahmed Benabderrahmane, Talal Rahwan Published: 2026-07-30 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.28879v1 Similarity search over sparse set-valued data is often dominated by frequent background attributes because classical measures such as Jaccard, cosine, and Hamming compare objects through atomic overlap. IDF (Inverse document frequency) weighting partially reduces this effect but remains atom-wise and cannot explicitly represent informative higher-order co-occurrences. We introduce RareSense, a rarity-aware similarity framework for sparse transactional anomaly data. RareSense mines minimal rare itemsets as intermediate structures, derives reliable rare association rules, maps objects into sparse rare-rule profiles, and compares them using weighted Jaccard similarity. Rule weights combine inverse support, confidence, lift, structural complexity, and stability, so that neighborhoods are determined by shared rare evidence rather than uniform feature overlap. We show that IDF-weighted Jaccard is a restricted singleton case of RareSense, and that the induced distance is a pseudometric on the original objects and a metric over equivalence classes defined by identical rule profiles. Experiments across four benchmark families spanning cybersecurity and general categorical domains show that RareSense attains the highest observed macro-average query-conditioned retrieval performance among the evaluated similarity measures. The statistical analysis indicates significant overall differences, with corrected paired comparisons favoring RareSense over the atomic baselines. The gains remain workload-dependent and are strongest when anomalies share repeatable rare higher-order structure. For global anomaly ranking, RareSense achieves the highest observed macro-average performance while remaining statistically comparable to several strong dedicated detectors. --- ### Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL Repair Authors: Ha Trung Tran Published: 2026-07-30 Categories: cs.AR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.28877v1 Verification consumes the majority of modern chip design effort, yet the formal verification tools that provide mathematical guarantees of correctness remain expensive and restrictively licensed. While large language models (LLMs) have shown promise for hardware design, existing approaches to RTL repair validate their results through simulation - which exercises only a subset of inputs - or rely on commercial tools, and few combine formal proof with an entirely open-source toolchain. In this paper, we present a multi-agent pipeline that couples an LLM with an open-source formal backend (Yosys, SymbiYosys, and Z3) to repair RTL through counterexample-guided iteration: the framework generates formal properties, verifies the design, and feeds counterexamples back to the LLM until the design is proved correct by k-induction or an iteration budget is exhausted. Through an ALU case study, we show that the pipeline can detect and repair a real functional bug with a formal proof of correctness. Across a six-benchmark suite, one design is repaired reliably, and we characterize four distinct failure modes: bounded-cover vacuity, specification ambiguity, temporal-logic bugs, and multi-property pressure. We frame this work as a feasibility study with a detailed failure analysis, and additionally report a practical limitation of the Yosys bind directive relevant to the open-source formal verification community. --- ### Learning to Predict Performance-induced Emotion Differences in Classical Piano Music Authors: Joann Ching, Gerhard Widmer Published: 2026-07-30 Categories: cs.SD, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2607.28876v1 Music is often used as a medium for communicating emotion, with performers shaping perceived affect through interpretation. This study addresses the challenge of identifying and predicting subtle changes in perceived emotion that are exclusively due to differences in performance. We focus on classical solo piano music, using a set of 6 commercial recordings of Bach's Well-Tempered Clavier Book I, annotated in terms of valence and arousal. By encoding the recordings through performance-specific features only, we isolate performance information from aspects of the composition itself, which tend to dominate the overall perceived emotional category. A preliminary analysis validates that these features vary meaningfully across performers. We then propose a relative regression framework, Delta-VA, to predict deviations in valence-arousal relative to an ``average'' performance, thereby focusing on the changes in emotion brought about by a specific way of playing a piece. In addition to the standard $R^2$ regression score, we introduce geometric evaluation metrics to assess the preservation of pairwise differences between performances. Results indicate high directional consistency with the ground truth, but also a compression in prediction magnitude, indicating that the model tends to underestimate expressive performance effects. --- ### Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug? Authors: Xiaonan Xu, Wenjing Wu Published: 2026-07-30 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.28871v1 When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect. We measure how often that treatment is warranted. BSG-VA (buggy-state/candidate-state/gold-fix validation analysis) captures each validation command at its exact working-tree state, extracts a test-only patch, and replays the command on the original buggy code (B), the candidate state (S), and the developer gold fix (G). The captured outcome and the replay results assign every event an evidence role, from gold-aligned bug-discriminating through regression-only to misleading. Across 3,730 events in 643 rollouts on 110 tasks, 46.0% of positive comparable events carry no bug-discriminating information; 23.8% of baseline rollouts, with no feedback injected, close with a patch whose entire positive evidence base is of this kind. A three-arm experiment tests whether returning the B-replay outcome to the agent changes this pattern. Bug-contrast feedback reduces evidence-inadequate closure by 7.8 percentage points relative to an attention-matched reminder (p = 0.0029) and raises bug-discriminating evidence by 7.4 points (p = 0.011), with no detectable cost to repair success. Both estimates fall below the prespecified 10-percentage-point smallest effect size of interest, so practical magnitude remains uncertain. Roughly a third of the improvement traces to the reminder alone; across two exploratory replications, varying the scaffold and the model, the B-replay content adds a detectable increment only with gpt-5.6-sol under the unconstrained tool-use loop. BSG-VA applies post hoc to any replayable repair trajectory that preserves the required code states and execution environment. Keywords: program repair agents, validation evidence, test adequacy, large language models, software quality, controlled experiment. --- ### Physics-Aligned Self-Supervised Learning for Scientific Imaging Authors: Bashir Kazimi, Stefan Sandfeld Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28868v1 Data augmentations define the invariances learned by self-supervised learning (SSL). Standard augmentation pipelines were designed for natural images, yet scientific imaging modalities are governed by physical measurement processes with distinct symmetry and acquisition constraints. Enforcing invariances that contradict these constraints can distort learned representations and limit downstream performance, but practitioners moving from machine learning into a new scientific modality currently have little guidance beyond transferring natural-image pipelines unexamined. We address this gap with a principled, reproducible procedure for augmentation design in scientific SSL: we formalise the physics-aligned augmentation set as a union of measurement-consistent symmetries and acquisition-driven perturbations, and we give a concrete, largely label-free workflow---enumerate candidates, label each by the measurement operator, validate with representation-geometry diagnostics, and confirm by single-factor ablation---for selecting them. We instantiate the procedure for real-space electron microscopy and reciprocal-space 4D-STEM diffraction, and evaluate it across five SSL paradigms (DINOv2, SimCLR, MAE, VICRegL, I-JEPA) on classification and crystal-orientation regression. Physics-aligned augmentations substantially improve downstream performance for objectives relying on cross-view consistency, reduce geodesic error and improve robustness under realistic acquisition variability (detector gain, resolution loss), and systematically reshape representation geometry. While our experiments use electron microscopy, the procedure is modality-agnostic and applies to other measurement-driven domains such as medical and remote-sensing imaging. These results position augmentation design as a primary, and controllable, source of inductive bias in scientific self-supervised learning. --- ### Conditioning Tree-Based Diffusions and Flows for Probabilistic Tabular Regression Authors: Silas Koemen Published: 2026-07-30 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.28864v1 Tree-based diffusion models fit flexible conditional predictive distributions for tabular regression without a neural density estimator, but they inherit their design defaults---noising path, parameterization, training distribution, features, sampler---from the neural setting. We show these defaults are the binding constraint: what a gradient-boosted ensemble actually solves is a supervised regression problem whose conditioning they determine. We present DiffGBM, which makes them explicit along two axes. First, a Gaussian-path flow-matching trainer for $p(y \mid x)$ that learns a velocity field directly and recovers the score algebraically, admitting few-step deterministic ODE sampling. Second, we expose the score-side recipe---residualization, EDM-style preconditioning, log-sigma time sampling, noise-level features, loss weighting, and histogram resolution---as jointly tunable axes over a shared LightGBM surface rather than one frozen bundle. This \emph{score-flex} space represents the published recipe as a special case; across eleven tabular benchmarks under fold-0 tuning, folds-1--5 evaluation, and a matched 40-trial budget and sampler, the selected configurations beat that baseline on \emph{every} dataset (paired Wilcoxon $11/0$, $p<10^{-3}$), with the best aggregate CRPS skill (0.725 vs.\ 0.699) of any row. The two rows are complementary: score-flex buys accuracy with a stochastic sampler and is the slowest row, while flow matching is the cheapest sampler ($5.2\times$ faster than the published baseline) and the best-calibrated DiffGBM row. Tuned non-diffusion baselines still win individual datasets, and stochastic ($\varepsilon>0$) flow samplers do not Pareto-dominate the deterministic corner. --- ### TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text Authors: Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu Published: 2026-07-30 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.28862v1 The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage. Unlearnable examples (UEs) offer a promising defense by introducing carefully designed perturbations into data such that models trained on them exhibit degraded utility. However, existing methods for text protection are primarily designed for classification tasks (e.g., sentiment analysis) in discriminative language models and often rely on injecting class-specific linguistic cues, which limits their effectiveness in the open-ended generation settings of LLMs. In this work, we propose TextCloak, an RL-driven framework for protecting textual data against unauthorized LLM exploitation. TextCloak employs a generative policy that transforms batches of clean text into unlearnable examples while preserving semantic fidelity and linguistic naturalness. To optimize the policy, we introduce GRPO-UE, which rewards generated unlearnable text based on the downstream degradation they induce in fine-tuned surrogate LLMs and updates the generator parameters via group-relative policy optimization. This bi-level optimization enables the generator to discover generalizable protective patterns beyond class-specific cues. Comprehensive experiments on six publicly available datasets and nine state-of-the-art LLMs demonstrate that TextCloak consistently impairs unauthorized fine-tuning while maintaining text utility for legitimate use. Further analyses establish its transferability and robustness across model architectures, training configurations, and adaptive attacks, highlighting its broad applicability as a practical defense against unauthorized LLM exploitation. --- ### The Debiased Score Test: Hunt-and-test for Semiparametric Hypotheses Authors: Aditya Dhawan, F. Richard Guo, Rajen D. Shah Published: 2026-07-30 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.28861v1 The parametric score test assesses a hypothesis through derivatives of the log-likelihood, whose expectation vanishes under the null. When the parameter of interest is a regression function identified as a risk minimiser, we extend this idea to test whether it belongs to a given linear function class. This yields goodness-of-fit tests for common semiparametric regression models, including generalised additive and partially linear models. Suitably formulated, the framework also detects effect modifiers in observational studies. We propose a hunt-and-test strategy that splits the data into two: on one part, after fitting the null model, machine learning is used to identify a promising direction in the empirical scores; on the other, we test whether the score vanishes in that direction. To account for error in estimating the null model, we apply a debiasing correction based on a weighted least squares projection. We establish Type I error control under relatively mild conditions and show the test has power whenever the hunted direction is correlated with the true score. Simulations and real-data examples demonstrate favourable performance, including identifying effect modifiers in an HIV clinical trial and assessing an additive model for insurance claims. The methodology is implemented in the R package dScoreTest. --- ### A Unified Benchmark of Deep Learning Models for Multi-task 3D Brain Tumor Segmentation from Magnetic Resonance Imaging Authors: Diego J. Torrejón, Luna Y. Hernández, Javier Sánchez Published: 2026-07-30 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.28858v1 Automatic brain tumor segmentation from magnetic resonance imaging (MRI) has become a fundamental task in computer-assisted diagnosis, treatment planning, and disease monitoring. Although numerous deep learning architectures have recently been proposed, objective comparisons remain challenging because published studies often employ different datasets, preprocessing strategies, training protocols, and evaluation procedures. This work presents a unified experimental benchmark for comparing representative convolutional neural networks (CNNs), Transformer-based models, and recent State Space Model (SSM) architectures under homogeneous experimental conditions. Five state-of-the-art three-dimensional segmentation models, including 3D U-Net, SegResNet, Swin UNETR, SegMamba, and SegMambaV2, are evaluated on two brain tumor segmentation datasets representing distinct clinical scenarios: intracranial meningioma segmentation (BraTS 2023) and post-treatment glioma segmentation (BraTS 2024). All architectures are trained using identical preprocessing, data augmentation, optimization strategies, and evaluation protocols to ensure a fair comparison. Performance is assessed using segmentation accuracy metrics together with computational cost indicators, including inference time and the size of each model. The results provide practical insights into the trade-offs between segmentation accuracy and computational efficiency, highlighting the suitability of different architectural paradigms for challenging three-dimensional brain tumor segmentation tasks. --- ### Fast Rates for Swap-Agnostic Learning of Proper Losses Authors: Princewill Okoroafor Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28856v1 Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions. This benchmark captures prediction-dependent postprocessing, but appears to require solving a separate agnostic-learning problem for every possible prediction value. We show that, for proper losses, these prediction-level comparisons can instead be controlled jointly. Our main result is an offline swap-agnostic learner for any fixed proper loss. For a finite hypothesis class $H$ and any fixed smooth proper loss, the excess risk from $m$ i.i.d. samples is $\widetilde{O}((\log |H|/m)^{2/3})$, with a corresponding online swap-regret bound of $\widetilde{O}(T^{1/3}(\log |H|)^{2/3})$. We also give algorithms whose predictions are simultaneously swap-agnostic for entire families of losses. For all proper losses bounded in $(-1,1)$, we obtain online and offline rates of $\widetilde{O}(\sqrt{T\log |H|})$ and $\widetilde{O}(\sqrt{\log |H|/m})$, respectively. For convex, $1$-Lipschitz proper losses, these rates improve to $\widetilde{O}(T^{1/3}(\log |H|)^{2/3})$ online and $\widetilde{O}((\log |H|/m)^{2/3})$ offline. These bounds are tight up to logarithmic factors and improve upon the $\widetilde{O}(T^{2/3}(\log |H|)^{1/3})$ rate implied by the swap-omniprediction guarantee of Luo et al. (2025). Our main technical contribution is a reduction from swap-agnostic learning to a second-order form of multicalibration, obtained via Blackwell approachability with a Bernstein-style variance correction. --- ### Learning Manifolds in High-D Point Embedding for Anisotropic Surface Approximation from Unstructured Point Clouds Authors: Hongbo Li, Haikuan Zhu, Xiaohu Guo, Wenping Wang, Jing Hua, Zichun Zhong Published: 2026-07-30 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2607.28855v1 Dense 3D sensors in various real-world fields produce point clouds that are geometrically redundant for real-time processing. In this paper, we propose an efficient and scalable learning-based anisotropic surface approximation framework, HD-PEA, that operates directly on unstructured point clouds, integrating anisotropic optimization into reconstruction to produce compact, geometry-aligned surface representations with higher fidelity, fewer elements, and improved numerical stability compared to isotropic and adaptive meshes. Firstly, we develop a novel learning-based high-dimensional (high-d) Euclidean point embedding method to map the input point clouds into a high-d manifold embedding space. For handling large-scale point clouds without retraining and fine-tuning, a patch-based meta-embedding scheme is designed during the inference stage. Then, we develop a new tangent subspace estimation for the high-d embedding manifold approximation and anisotropic manifold reconstruction in high-d space. The main contribution of this work is to propose a scalable deep learning framework and a variety of datasets for constructing a high-d Euclidean point embedding space aimed to 3D anisotropic surface mesh approximation and Riemannian curvature tensor estimation from point clouds. We extensively evaluate our method against state-of-the-art surface reconstruction approaches using several datasets, such as Thingi10K dataset, AIM@SHAPE and Stanford 3D Scanning Repository, ScanNet dataset, and further demonstrate its generalization and usability on diverse unseen shapes and applications from these datasets. --- ### An analysis of machine learning approaches for enhancing decision-making in complex discrete choice tasks Authors: Sheng Lun Christine Cao, Destenie Nock, Alex Davis Published: 2026-07-30 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.28854v1 Discrete choice modeling is a common tool used for preference elicitation during policy-making, but this is typically done through parametric models. Machine learning can push the boundaries of discrete choice modeling for policy-based preference elicitation by adopting a data-driven approach or learning individual preferences. However, there is limited knowledge of how well machine learning methods can estimate individual discrete choice rules under individual heterogeneity, especially in the context of challenges often experienced during preference elicitation. This study evaluates four machine learning models (multinomial logistic regression, generalized additive model, twinned neural network, and Gaussian process) with respect to their capacity to learn and predict five choice rules that are important in the behavioral and social sciences (linear strong utility, monotonic strong utility, ideal point, lexicographic semiorder, and multiattribute linear ballistic accumulator). Monte Carlo experiments were performed to assess model performance when increasing a) the number of attributes in the choice alternatives, b) the number of training choice sets, and c) the choice rule's determinism. The simulation results demonstrated that semi-parametric and non-parametric models generally outperform parametric models across all choice rules and experimental contexts. Model performance also generally improves by 6% to 96% and 0% to 55%, respectively, with an increase in training choice sets and choice rule determinism. A case study using real energy policy preference data was also conducted, where TNN performed best with a BIC of 13.351. This work demonstrated the viability and limitations of semi-parametric and non-parametric models in the context of policy-centric discrete choice modeling and showed how the choice task context should drive model selection. --- ### Hypergradient-based Bilevel Reinforcement Learning with Improved Sample Complexity Authors: Naman Saxena, Mudit Gaur, Vaneet Aggarwal Published: 2026-07-30 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.28849v1 Bilevel reinforcement learning (RL) is an important framework within the literature of RL that can be used to formalize various categories of problems, such as meta-learning, hierarchical task decomposition, and reinforcement learning from human feedback (RL-HF). Most of the bilevel RL algorithms are either not scalable because of using hypergradient with Hessian, or they suffer from high sample complexity because of using penalty-based approximation methods. In this work, we propose a hypergradient-based bilevel RL algorithm using the optimality of the Boltzmann policy for the entropy regularized discounted RL objective function. Our proposed algorithm is Hessian-free and obtains an iteration complexity of $O(ε^{-1})$ and state-of-the-art sample complexity of $\tilde{O}(ε^{-2})$ under mild regularity conditions. Further, in our convergence analysis, we are able to remove the assumption of the Polyak-Lojasiewicz (PL) condition on the outer-level objective function present in the prior state-of-the-art sample complexity work. --- ### DeltaServe: Host-Agnostic Co-Serving of Inference and Fine-Tuning for LLMs Authors: Jiaxuan Chen, Jianshu She, Ye Yuan, Rajat Ghosh, Karan Gupta, Qirong Ho, Xue Liu, Oana Balmau Published: 2026-07-30 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2607.28848v1 LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a host-agnostic co-serving design that converts this idle inference capacity into LoRA fine-tuning throughput while preserving inference service-level objectives (SLOs). DeltaServe integrates with existing inference engines through a compact hook interface that requires only multi-LoRA batching support. It exploits the shared execution structure of inference prefill and LoRA fine-tuning forward passes, and uses an SLO-aware scheduler to admit and execute fine-tuning only when sufficient inference headroom is available. The scheduler is driven by a CUDA-graph-aware latency model calibrated offline and refined online. We integrate DeltaServe with vLLM, SGLang, and S-LoRA. On a production trace from Company X, DeltaServe on vLLM delivers 2.9x higher fine-tuning throughput than LLMStation at 100% inference SLO compliance, versus 85% for LLMStation. It also achieves 39% higher fine-tuning throughput than a baseline running vLLM+torchtune, using no additional hardware and maintaining full SLO compliance. --- ### Seeing the Forest for the Trees: The Gaussian Process Limit of BART Authors: Cory McCartan, Melody Huang Published: 2026-07-30 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.28844v2 Bayesian Additive Regression Trees (BART) have shown state-of-the-art performance in both prediction and causal inference problems. Previous theoretical work has attempted to explain BART's superior performance by establishing posterior contraction rates for standard BART models, but these rates depend strongly on the number of covariates. Here, we take a different approach and study the behavior of BART as the number of trees grows towards infinity. We show that in this regime, BART converges to a Gaussian process (GP) with a particular kernel. The kernel and its corresponding reproducing kernel Hilbert space (RKHS) have favorable inferential properties that help explain BART's excellent performance. We introduce random tree features as an approximation to this limiting GP, and establish minimax-optimal learning rates for ridge regression on these random features that depend only logarithmically on dimension. In addition to providing insight into the empirical success of BART, random tree features offer a computational benefit over traditional MCMC estimation. The random-features approximation also allows practitioners to easily incorporate BART into any model which has a linear predictor, expanding the applicability and flexibility of BART. --- ### Seeing the Forest for the Trees: The Gaussian Process Limit of BART Authors: Cory McCartan, Melody Huang Published: 2026-07-30 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.28844v1 Bayesian Additive Regression Trees (BART) have shown state-of-the-art performance in both prediction and causal inference problems. Previous theoretical work has attempted to explain BART's superior performance by establishing posterior contraction rates for standard BART models, but these rates depend strongly on the number of covariates. Here, we take a different approach and study the behavior of BART as the number of trees grows towards infinity. We show that in this regime, BART converges to a Gaussian process (GP) with a particular kernel. The kernel and its corresponding reproducing kernel Hilbert space (RKHS) have favorable inferential properties that help explain BART's excellent performance. We introduce *random tree features* as an approximation to this limiting GP, and establish minimax-optimal learning rates for ridge regression on these random features that depend only logarithmically on dimension. In addition to providing insight into the empirical success of BART, random tree features offer a computational benefit over traditional MCMC estimation. The random-features approximation also allows practitioners to easily incorporate BART into any model which has a linear predictor, expanding the applicability and flexibility of BART. --- ### Benchmarks Are Not Validation: A System-Level View of Financial LLM Applications Authors: Burak Payzun, İrem Demirtaş, Simona Scala, Elena Ferretti, Seçil Arslan Published: 2026-07-30 Categories: cs.CL, cs.SE arXiv: https://arxiv.org/abs/2607.28840v1 Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monitoring, and human escalation. Yet evaluation often remains model-centric: benchmark scores, task accuracy, or one-off qualitative reviews are treated as evidence of readiness. In financial settings, this is insufficient. We take the position that financial LLM systems should not be approved for production based on benchmark performance alone. They require system-level validation evidence across the application stack: data, model design, retrieval and generation performance, agent behavior, governance, and implementation. Drawing on industry experience validating GenAI applications in financial institutions, we outline a multi-layer validation view and explain why hybrid evaluation is necessary. We discuss where LLM-as-a-judge methods are useful and why they require controls such as multiple judges, rubrics, agreement, and auditability checks. We also highlight failure modes poorly captured by static benchmarks, including retrieval failures, unfaithful generation, tool misuse, escalation errors, and operational instability. Our position is that financial LLM validation should be an ongoing system discipline rather than a one-time model scoring exercise. Validation should produce decision-ready evidence, not only scores. We conclude with a research agenda for system-aware benchmarks, agent trace validation, judge alignment protocols, and lifecycle validation standards. --- ### FocusGS: Spatial Delta Layers for Local Repair and Deterministic Editing of Trained 3D Gaussian Assets Authors: Yiqun Pan, Yukun Shi Published: 2026-07-30 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.28834v1 3D Gaussian Splatting (3DGS) is evolving from one-time reconstruction into deliverable, inspectable, and maintainable visual assets. Existing workflows focus on global reconstruction, training-time density control, or open-ended generative editing, leaving trained assets without precise local maintenance. We propose FocusGS, which unifies local repair and deterministic editing as composite spatial deltas. Repair is the purely additive special case: its base-manipulation term is empty, and it adds only local Gaussian bases; deterministic editing uses erase-insert factorization (EIF) to combine old-carrier erasure with new-content insertion. FocusGS addresses spatial gradient starvation: local repair raises target-region PSNR by 7.91 dB over 93 evaluation views. Across all 83 deterministic editing trials, the target ROI improves, with a trial-averaged mean edited ROI PSNR of 21.97 dB and a mean gain of +11.05 dB; across five public editing cases, FocusGS-EIF reaches 33.17 dB Target-mask PSNR and 0.994 Target-delta Correlation, while both text-driven baselines fail to complete the prescribed updates. FocusGS provides a lightweight, verifiable 3DGS maintenance operator. --- ### When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks Authors: Zihao Ding, Jun Huang, Liang Dong Published: 2026-07-30 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2607.28829v1 Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back into later rounds. This closed loop makes unlearning harder than a one-time model repair. When a data owner requests deletion, the target data may have already shaped later retained trajectories, so retraining or model-side unlearning can leave an influence echo that returns as the network continues to operate. We show that this echo survives retained-data retraining, grows with the amount of forget-shaped retained data, and can be traced from deployment, collection, and aggregation records. To address this problem, we propose MUTE, a Muting Unlearned Trajectories' Echoes method for reliable deletion in self-improving federated agent networks. MUTE estimates downstream influence from a lightweight server ledger, removes the current residue through a forget-retain update, contains high-influence retained trajectories through quarantine or down-weighting, and audits later behavior to schedule additional erasure under an uplink budget. Experiments on LIBERO with two vision-language-action backbones, three deletion granularities, and a physical Jetson-based edge testbed show that MUTE keeps behavioral leakage and influence regeneration low while preserving task utility and using much less communication than full retraining. ---