# Research Papers — 2026-07 · bundle page 116 of 222 > Full-text markdown of papers #5751–5800 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/116 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/115.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/117.md) ### DyneTrion: A Spatio-temporally Coherent Generative Emulator for Protein Dynamics Across Timescales Authors: Kaihui Cheng, Zhiqiang Cai, Peng Tu, Yisong Yao, Limei Han, Libo Wu, Siyu Zhu, Tzuhsiung Yang, Yuan Qi Published: 2026-07-15 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2607.15309v1 Proteins function through coordinated motion across multiple spatial and temporal scales, underpinning processes such as ligand binding, allostery, and catalysis. However, accessing long-timescale conformational change through molecular dynamics (MD) simulations remains prohibitively expensive for systematic exploration across diverse systems. Here, we present DyneTrion, a generative protein dynamics emulator that jointly enforces geometric symmetry, structural consistency and temporal coherence within a single framework. DyneTrion uses a tri-attention architecture that integrates invariant point attention (IPA) for SE(3)-robust geometric updates, spatial attention anchored to a reference conformation to preserve structural integrity, and temporal attention to model correlated evolution across time frames. Across 100-ns MD trajectory simulation benchmarks, DyneTrion reproduces MD-derived flexibility, ensemble distributions and interaction observables while maintaining stereochemical validity during extrapolation. To evaluate long time-scale generalization, we introduce dynamicPDB, a dataset of over 10,000 proteins with up to 1-$μ$s all-atom trajectories at 10-ps resolution and accompanying physical annotations. On microsecond trajectories, DyneTrion preserves free-energy landscapes and metastable-state populations, and it supports large conformational propagation in apo-to-holo transitions and fast folders. Together, DyneTrion provides a scalable path from static structure prediction toward time-resolved, ensemble-faithful protein modeling. The code is publicly available at https://github.com/fudan-generative-vision/DyneTrion --- ### Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel Authors: Sietse Schelpe Published: 2026-07-15 Categories: cs.CL, cs.AI, cs.LG, cs.PF arXiv: https://arxiv.org/abs/2607.14431v1 We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context. The restore is bit-exact: under a pinned deterministic configuration, the grafted logits are byte-for-byte identical to a fresh computation (SHA-256 equality), with zero KL divergence and 100% argmax agreement over fifty samples. We show that own-position graft is the unique numerically exact operating point on a model with floating-point rotary encoding, and we verify byte-exactness on two model scales (12B, 31B) and two GPU targets, one through a pre-registered replay. On AIME 2025, a frozen Gemma-4-12B moves from 80.0% to 93.3% once a verified solution library is grafted, above its own 77.5% and its 31B sibling's 89.2% published anchors. On the recurring case, eight problems the base model never solves within a 401,026-token budget are answered from cached verified solutions in 61 total decode tokens, a factor of 6,574 fewer tokens and about 8,700x less energy; the capability claim proper rests on held-out transfer (7 of 7 at 31B). The same byte-exact store widens usable context from 32,768 to 2,854,766 tokens at zero extra accelerator memory, and moves byte-identical between machines of the same architecture. We describe the system at the behavior level; the engine is proprietary, and every reported number is backed by committed input and output hashes so the scoring can be re-checked without it. --- ### Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers Authors: Joe Logan Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14427v1 A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths. We ask what such a model actually computes per token, and measure it directly. On a 135M-class model trained on FineWeb-Edu, the recurrent state converges to a per-token fixed point: mean successive-output KL divergence falls from 3.9e-1 at the second loop to 8.5e-6 by the sixteenth, and per-token state change decays in step. Crucially, this convergence is not uniform across tokens. The median token converges by loop six, while approximately 10 percent of tokens continue to update at the training-mean depth of eight, and mean convergence depth is ordered by token type (whitespace shallowest, content words deepest). This per-token variation is the central object of the paper. We show it is directly readable and that reading it outperforms learning to predict it: a training-free rule that halts each token once its output stabilizes attains uniform depth-8 quality at 4.94 average loops (a 38 percent reduction in average depth) and matches uniform depth across the average-depth range, whereas a linear router trained on convergence labels harvested from the same model requires nearly full depth and yields no reduction. The elasticity that makes this possible reproduces here as background (validation loss decreases monotonically from 3.80 at one loop to 3.20 at eight and remains stable to 32 loops). We report average depth as a FLOP proxy with a three-point wall-clock bracket rather than a realized speedup, make no FLOP-matched parity claim, and note that the allocation results are established at a single scale and seed. The complete study runs on a single RTX 4090 in approximately 100 GPU-hours. --- ### ConFlow: Constraints-Guided Learning with Flow Matching for Motion Generation Authors: Nutan Chen, Jianxiang Feng, Marvin Alles, Botond Cseke Published: 2026-07-15 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14424v1 In recent years Flow Matching has become a prominent method for generative modeling robot motion generation. In its generic form Flow Matching is an ODE-based neural sampler that is trained by regressing empirical flow fields associated with motion samples as data. However, in robot motion generation we often have additional constraints that might not be present in the collected data. The majority of current approaches train the flow on the available data and use inference-time guidance to enforce task-specific constraints. To address this mismatch, we propose \textbf{ConFlow}, a constraint-guided flow matching framework that incorporates constraint information directly into the training objective via differentiable barrier or cost functions. To address design specifications such as smoothness and boundary conditions, we propose replacing the standard Gaussian source distribution used in flow matching training with a conditional Gaussian Process. Our approach also uses infeasible demonstrations as negative supervision, improving constraint satisfaction without requiring additional expert data. Experiments on a two-robot navigation task demonstrate that ConFlow achieves lower collision rates and higher trajectory quality than standard flow matching baselines, with or without inference-time guidance. These results validate training-time constraint integration as an effective approach to closing the training--inference gap in generative motion models. --- ### Emergent Region-Level Facial Correspondence in Frozen Vision Foundation Models Authors: Izaldein Al-Zyoud, Abdulmotaleb El Saddik Published: 2026-07-15 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2607.14423v1 Frozen self-supervised vision models can align parts of generic objects, but it remains unclear whether this correspondence extends to human faces, where global layout is shared while identity-specific appearance varies sharply. We test whether frozen DINOv3 features define a region-level facial coordinate system: a feature space in which eyes, brows, nose, mouth, skin, and hair remain distinguishable across people and across time without face-specific training. Using DINOv3 ViT-L/16 patch embeddings and FaRL only as a face-part labeling interface, we evaluate cross-identity nearest-neighbor matching and temporal label propagation on 200 CelebDF-v2 real videos. DINOv3 achieves 83.0% region-level semantic accuracy under unconstrained cross-identity matching, compared with a 23.0% area-weighted random baseline, and 95.5% temporal tracking accuracy without a learned temporal module. A no-FaRL control collapses to 0.9%, showing that FaRL supplies semantic initialization while DINOv3 supplies dense spatial correspondence. The strongest correspondence appears at an intermediate layer: block 18 gives a 4.93x same-region versus cross-region discrimination ratio, compared with 1.48x at the final block. Against CLIP ViT-L/14, DINOv3 shows only a small aggregate advantage but a +16.8 pp gain on anatomical regions, indicating that image-level contrastive supervision captures coarse facial layout but not fine-grained anatomical identity. These results establish frozen DINOv3 as a strong zero-shot representation for region-level facial correspondence and identify intermediate self-supervised features as the most useful layer for dense face analysis. --- ### HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects Authors: Akshay Sasi Published: 2026-07-15 Categories: cs.LG, cs.CG arXiv: https://arxiv.org/abs/2607.14419v1 Machine-learning datasets labelled "4D" universally denote three spatial dimensions plus time. We introduce HyperShadow, the first public benchmark in which the fourth, fifth, and sixth dimensions are spatial: the task is to decide whether a 3D point cloud is a native three-dimensional shape or the projection, the "shadow", of a rigid object living in R^N (N = 4-6). We show this task is fundamentally distinct from intrinsic-dimension estimation: a shadow is still at-most-3-dimensional data, and standard estimators (TwoNN, Levina-Bickel MLE) reach only 71-73% accuracy. Detection instead requires projection signatures, density folds, filled volumes with characteristic radial profiles, and topology changes, which a 190k-parameter point network recovers at 96.6% accuracy across four corruption tiers, generalizing at 79-91% to object families never seen in training. On a temporal track of rigidly rotating objects we introduce a zero-parameter rigidity witness: the residual of the optimal rigid 3D alignment (Kabsch) between consecutive frames, which must vanish for any rigid 3D motion but cannot vanish for the shadow of a rigid rotation in R^N. This single interpretable statistic separates the classes at AUROC 0.982. All data are generated reproducibly from seeds; the dataset, models, and code are released publicly. HyperShadow makes no claim about physical reality; it is a controlled instrument for studying which observable statistics can certify incompatibility with a purely three-dimensional explanation. --- ### Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment Authors: Mohammad Rashid, Hema Yoganarasimhan Published: 2026-07-15 Categories: cs.LG, econ.GN arXiv: https://arxiv.org/abs/2607.14418v1 Ad-load design is a central supply-side decision in sponsored search: more sponsored slots can raise revenue, but may crowd out organic results and degrade user outcomes. We study this trade-off using a large-scale randomized field experiment on an Android app store, where over five million users are exposed to one through six sponsored slots. Increasing ad load raises revenue by up to 43%, but reduces total search conversions by up to 5% and daily engagement by up to 2.2%. These average effects mask substantial heterogeneity: additional slots generate large revenue gains for high-ad-conversion queries, but little or negative marginal revenue for low-conversion queries. The trade-off also shifts within query as advertiser composition changes, such as brand-advertiser presence. Motivated by these findings, we design and deploy a novel adaptive algorithm -- exploration-augmented Locally Adaptive Ad Load (e-LAAL). e-LAAL combines LAAL, a model-free query-level decision rule that updates ad-load recommendations using recent outcomes, with static exploration arms that maintain support and provide fixed-policy counterfactual benchmarks. We provide a finite-time dynamic-regret guarantee for the e-LAAL architecture. In a platform-level production deployment serving 22.3 million users and 77.6 million searches, e-LAAL improves the empirical revenue--conversion trade-off relative to deployed static benchmarks and outperforms uniform and historical query-dependent static benchmarks. --- ### CausalGraphX: A Counterfactual Graph Neural Network Framework for Explainable Systemic Risk Assessment Authors: Rabimba Karanjai, Hemanth Madhavarao, Lei Xu, Weidong Shi Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14416v1 The interconnected nature of global financial systems makes them vulnerable to systemic risks, where the failure of a few institutions can trigger catastrophic cascading defaults. Traditional risk models often fail to capture the complex, non-linear dynamics of these networks. While Graph Neural Networks (GNNs) have shown promise in modeling relational data, they primarily learn correlative patterns and function as black boxes, offering little insight into the causal mechanisms of shock propagation. This limitation is critical for regulators who require explainable models to perform stress tests and devise effective interventions. We introduce CausalGraphX, a novel framework that integrates GNNs with counterfactual reasoning to provide explainable assessments of systemic risk. CausalGraphX employs a Graph Attention mechanism to learn representations of institutional vulnerability and uses an adversarial regularization technique to ensure these representations capture causal drivers rather than spurious correlations. Furthermore, we propose an optimization-based approach to generate counterfactual explanations, answering questions such as, "What minimum capital injection would have prevented Bank A's default under a specific stress scenario?" We validate CausalGraphX on large-scale synthetic financial networks. Our results demonstrate that CausalGraphX significantly outperforms traditional and deep learning baselines in predicting cascading defaults while providing sparse, plausible, and actionable counterfactual explanations. --- ### $K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs Authors: Daksh K. Shah, Emmanouil Nikolakakis, Razvan Marinescu Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14415v2 Computed Tomography (CT) carries significant ionizing radiation risks, driving the need for sparse-view reconstruction. Implicit scene representations (ISRs) address this by recovering continuous volumetric attenuation fields directly from sparse projections, and recent geometry-aware extensions jointly model surface geometry alongside attenuation to improve fidelity and enable clean tissue segmentation without manual thresholding. However, these methods remain limited by manually tuned attenuation bounds and rigid two-material constraints. This paper proposes $K$-NeAS, a unified and scalable architecture for automated, multi-material surface reconstruction. We replace independent material networks with a shared latent backbone and introduce a fully differentiable $K$-material sequential soft selector to model an arbitrary number of overlapping tissues. To eliminate manual tuning, we automate attenuation bounding using a Gaussian Mixture Model (GMM) and implement a scheduled auxiliary floater loss to mitigate geometric hallucinations common under extreme sparsity. Evaluated across four clinical Cone-Beam CT (CBCT) datasets, $K$-NeAS successfully scales to arbitrary material counts, achieving superior 3D volumetric fidelity at $K=3$ materials on complex multi-tissue regions such as the Abdomen ($33.28\text{ dB}$ 3D PSNR vs. $31.40\text{ dB}$ single-material NeAS baseline, a $+1.88\text{ dB}$ improvement). Furthermore, our model exhibits enhanced robustness under sparse-sampling conditions, outperforming baseline 3D PSNR by up to $1.17\text{ dB}$ under 5- and 10-view constraints. --- ### $K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs Authors: Daksh K. Shah, Emmanouil Nikolakakis, Razvan V. Marinescu Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14415v1 Computed Tomography (CT) carries significant ionizing radiation risks, driving the need for sparse-view reconstruction. Implicit scene representations (ISRs) address this by recovering continuous volumetric attenuation fields directly from sparse projections, and recent geometry-aware extensions jointly model surface geometry alongside attenuation to improve fidelity and enable clean tissue segmentation without manual thresholding. However, these methods remain limited by manually tuned attenuation bounds and rigid two-material constraints. This paper proposes $K$-NeAS, a unified and scalable architecture for automated, multi-material surface reconstruction. We replace independent material networks with a shared latent backbone and introduce a fully differentiable $K$-material sequential soft selector to model an arbitrary number of overlapping tissues. To eliminate manual tuning, we automate attenuation bounding using a Gaussian Mixture Model (GMM) and implement a scheduled auxiliary floater loss to mitigate geometric hallucinations common under extreme sparsity. Evaluated across four clinical Cone-Beam CT (CBCT) datasets, $K$-NeAS successfully scales to arbitrary material counts, achieving superior 3D volumetric fidelity at $K=3$ materials on complex multi-tissue regions such as the Abdomen ($33.28\text{ dB}$ 3D PSNR vs. $31.40\text{ dB}$ single-material NeAS baseline, a $+1.88\text{ dB}$ improvement). Furthermore, our model exhibits enhanced robustness under sparse-sampling conditions, outperforming baseline 3D PSNR by up to $1.17\text{ dB}$ under 5- and 10-view constraints. --- ### LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration Authors: Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Hien Van Nguyen, Kunal Rai, Tania Banerjee Published: 2026-07-15 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2607.14410v2 Spatially resolved omics studies increasingly combine transcriptomic and epigenomic assays, yet downstream analysis is often still performed using single-modality pipelines. We present LATTICE (Latent Alignment of Tissue-level and Transcriptomic Information for Cross-modal Embedding), a graph-based self-supervised framework that learns spot-level representations from harmonized multimodal features. LATTICE integrates five aligned modality blocks per Visium spot: Visium RNA, scMultiome RNA, scMultiome ATAC, spatial ATAC, and spatial CUT\&Tag. These modalities capture spatial transcriptomic measurements, single-cell inferred regulatory activity, and in situ chromatin and histone states within a unified lattice representation. LATTICE constructs a spatial neighborhood graph and trains a TransformerConv encoder using masked reconstruction, cross-modal alignment, and spatial smoothness objectives. On a private 11-sample melanoma cohort from an anonymized clinical collaborator comprising 54{,}912 total spots, LATTICE demonstrated stable optimization behavior, reproducible embeddings across analysis seeds, and complete multimodal integration across all samples. Adding scMultiome RNA to Visium RNA alone substantially improved concordance with Space Ranger clusters across 11 runs (adjusted Rand index (ARI) +0.157, normalized mutual information (NMI) +0.143, and spatial contiguity +0.174). Additional modalities further improved spatial contiguity and multimodal utility score (MUS), although they sometimes reduced agreement with RNA-derived reference labels, likely because the learned embeddings captured chromatin and regulatory structure beyond transcriptomic similarity alone. These results position LATTICE as a practical and empirically grounded framework for multimodal spatial omics integration, while also highlighting the need for stronger supervision and broader external benchmarking. --- ### Reward-Free Evolving Agents via Pairwise Validator Authors: Minghao Liu, Yu Wang, Jiayun Wang, Wei Wei Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14408v1 A self-evolving agentic loop repeatedly proposes a tweaked version of an agent (its prompt template or program) and accepts or rejects the change based on a per-iteration quality signal. Designing that signal is often the costly part of the project: a reliable scalar reward requires domain expertise and labeled examples that are themselves as expensive to assemble as the agent's underlying task. We propose replacing the scalar at the accept/reject gate with a pairwise validator: a frozen LLM that, given the parent and child candidate, returns a binary verdict on which is better. Pairwise judgment is generally easier and more stable than absolute scoring, due to its contrastive nature, which mitigates the need for strict scale calibration. The validator also requires no training of its own. We integrate the validator into three published self-evolving engines (GEPA, ADRS, ShinkaEvolve) and report two flavors: Adaptive Focus, which retains the engine's existing val-set parent selection, and Soft Elo, which lets the validator's verdicts drive parent selection so that val-set rewards drop as well. Across multiple agents and two artifact substrates (prompt and code), our method matches or exceeds the full-reward baseline on the majority of settings we evaluate, and the pattern survives a cross-family validator swap. The pairwise gate is thus a drop-in replacement for per-step reward design at competitive task accuracy without the labeling cost. --- ### Decision Making Needs Uncertainty Quantification (Lecture Notes) Authors: Osvaldo Simeone Published: 2026-07-15 Categories: cs.IT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14407v4 Many signal processing systems ultimately exist to act. Whenever the state variable that determines the action to be taken by a decision maker, or agent, is uncertain, the way that uncertainty is represented decides how well the agent performs and how much its performance can be trusted. This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the {objective} and the knowledge of an agent and the form of uncertainty representation that is sufficient to act optimally. To start, assuming a known environment distribution, we show that a risk-neutral agent needs the posterior distribution over the state, whereas a risk-averse agent can rely without loss of optimality on a {prediction set} and a worst-case decision rule. We then turn to the case in which the environment is unknown, and identify three complementary approaches to address the resulting epistemic uncertainty: calibration of a fixed predictor, credal (ambiguity) sets with distributionally robust optimization, and Bayesian inference over model parameters. The common thread is that reliable decisions require an uncertainty representation matched to the decision objective and to the knowledge profile of the agent, together with a guarantee that certifies the utility the agent will actually obtain. --- ### Decision Making Needs Uncertainty Quantification (Lecture Notes) Authors: Osvaldo Simeone Published: 2026-07-15 Categories: cs.IT, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14407v3 Many signal processing systems ultimately exist to {act}. Whenever the state variable that determines the action to be taken by a decision maker, or agent, is uncertain, the way that uncertainty is represented decides how well the agent performs and how much its performance can be trusted. This lecture note develops, from first principles and within a single decision-theoretic setting, the link between the {objective} and the knowledge of an agent and the form of uncertainty representation that is sufficient to act optimally. To start, assuming a known environment distribution, we show that a risk-neutral agent needs the posterior distribution over the state, whereas a risk-averse agent can rely without loss of optimality on a {prediction set} and a worst-case decision rule. We then turn to the case in which the environment is unknown, and identify three complementary approaches to address the resulting epistemic uncertainty: calibration of a fixed predictor, credal (ambiguity) sets with distributionally robust optimization, and Bayesian inference over model parameters. The common thread is that reliable decisions require an uncertainty representation matched to the decision objective and to the knowledge profile of the agent, together with a guarantee that certifies the utility the agent will actually obtain. --- ### DS@GT ARC at LongEval: Citation Integrity and Factual Grounding in Scientific QA Authors: Brandon Michaels, Brendon Johnson Published: 2026-07-15 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.14400v1 This paper describes DS@GT ARC's submission to the CLEF 2026 LongEval Task 4 on Retrieval-Augmented Generation (RAG). In this submission, we examine a divergence between traditional natural language evaluation metrics and citation integrity as applied to RAG QA systems. We evaluate a corrective pipeline using Corrective RAG (CRAG) and CiteFix against baseline and frontier model benchmark RAG QA scores. While frontier models maximized answer relevance and fluency scores, our RAGAs LLM-as-judge diagnostics indicate that frontier models would correctly identify relevant documents without using their context in answer generation. Conversely, by filtering chunks pre-generation and enforcing strict entailment of generated claims to the cited material post-generation, our corrective pipeline marginally improved citation faithfulness and answer grounding. We propose that evaluation of trustworthy RAG QA requires metrics that reward strict answer grounding. --- ### Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration Authors: Justin Bronder Published: 2026-07-15 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.14399v1 Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a text-adventure world where the game engine, not any model, knows whether the quest can be completed. A language model plays under a budget and must eventually declare its quest complete, unreachable, or not yet decidable; the engine scores every verdict. Decision rules were recorded before results were read, and run artifacts bind the revisions they executed; the strength of preregistration varies by series and is disclosed. With the player held fixed, instrument choices substantially changed measured behavior. On four byte-identical anchors, expanding a two-verdict grammar to three verdicts moved strong claims from 38/40 to 7/40, while the new incomplete verdict took 28/40 outcomes; across series 2, 93/158 valid games ended incomplete. One sentence disclosing the success criterion took matched-instance false verdicts from 18/59 to 0/58, through fewer decision points and cleaner decisions. Repeated runs of one fixed configuration produced non-stable verdict distributions on 3 of 4 instances: single runs report samples as dispositions. A formally preregistered narrative-register gradient was falsified; two post-hoc, hypothesis-generating patterns remain: register presence roughly doubled strong claims, and budget rendering moved verdicts more than register content (.383 meter vs .150 lantern). The narrator compressed abundant budgets toward scarcity landmarks, yet the registered mediation test returned a null. We propose a four-check integrity protocol for eval instruments. --- ### Integration Matters: Rollout-Based Training for Constrained Diffusion Models Authors: Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood Published: 2026-07-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.14398v1 Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods. --- ### CatalogAgent: A Supervisor-mediated Self-Learning System Enabling Context Engineering for GenAI Models Authors: Zhu Cheng, Zhenming Wang, Yu, Tang, Dan Liu, Bryan Zhang, Athanasios N. Nikolakopoulos, Pranav Souri Itabada, Jing Zhang, Chih-Chi Chou, Peng Gao, Fatemeh Mansoori et al. Published: 2026-07-15 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14396v1 Product catalogs are the backbone of e-commerce sites, yet a large number of structured attributes (SAs) -- such as material, color, and shape -- often have missing values. Typically, SA values are extracted from product information, including titles and descriptions. While LLM-based generator-evaluator frameworks have demonstrated effectiveness for SA prediction -- where an LLM generates SA values and another evaluates them -- they face challenges when the Generator and Evaluator produce conflicting outputs, as either component can make mistakes. We introduce \texttt{CatalogAgent}, a novel agentic system that continuously improves Generator and Evaluator models for e-commerce catalog enrichment. When disagreements arise from (1) internal conflicts between the LLM-based Generator and Evaluator, or (2) external feedback from sellers on LLM outputs, a Supervisor Agent intervenes to mediate these conflicts and make final decisions. The system also incorporates a Memory Base and a Memory Summarizer that stores Supervisor Agent activities from individual cases and aggregates patterns into learnings. These learnings are fed back to the worker Generator and Evaluator LLMs, enabling self-improvement without human intervention. Through context engineering -- injecting learnings and insights into worker LLMs' contexts -- the system successfully transfers the Supervisor's capabilities to the Generator and Evaluator, improving their performance by 15.24\% and 13.98\%, respectively. Our experiments demonstrate a new paradigm of Supervisor Agent-mediated self-learning systems for improving generative AI model accuracy. --- ### An offline approach to fNIRS-guided reinforcement learning for robot behavior Authors: Julia Santaniello, Madelaine Brower, Benson Jiang, Donatello Sassaroli, Chenyuan Zhang, Robert Jacob, Jivko Sinapov Published: 2026-07-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.14393v2 Human-in-the-loop Reinforcement Learning has become a popular approach for training, finetuning, and aligning robot behavior with user preferences. Our paper explores the feasibility of using brain signals via functional near-infrared spectroscopy (fNIRS) to modulate robot learning in simulation. We compare agents trained on passive (observational) versus active (demonstrative) interaction tasks, and test multiple methods for enhancing the RL algorithm with the neural signal, focusing on parameter augmentation in contrast to replacement. We further examine how model granularity and noise affect agent learning. Our results show that this framework is effective. The neural signal improves learning when augmenting trajectory priorities and state-action q-targets. Additionally, the framework learns successfully from offline data, offering a practical alternative for settings where real-time BCI setups are impractical or only limited data is available. --- ### An offline approach to fNIRS-guided reinforcement learning for robot behavior Authors: Julia Santaniello, Madelaine Brower, Benson Jiang, Donatello Sassaroli, Robert Jacob, Jivko Sinapov Published: 2026-07-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.14393v1 Human-in-the-loop Reinforcement Learning has become a popular approach to training, finetuning, and aligning robot behavior with user preferences. Our paper explores the feasibility of using brain signals via functional near-infrared spectroscopy (fNIRS) to modulate robot learning in simulation. We compare agents trained on passive (observational) versus active (demonstrative) interaction tasks, and test multiple methods for enhancing the RL algorithm with the neural signal, focusing on parameter augmentation rather than replacement. We further examine how model granularity and noise affect agent learning. Our results show that this framework is effective: the neural signal improves learning when augmenting trajectory priorities and state-action q-values. Additionally, the framework learns successfully from offline data, offering a practical alternative for settings where real-time BCI setups are impractical or only limited data is available. --- ### A Comparative Analysis of Machine Learning Models for Long and Short-Term Forecasting of the Egyptian Stock Market: A Focus on EGX30 Authors: Muhammed Walid, Ahmed El-Naeimy, Hosam Moubarak, Walid Gomaa Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14391v1 This study concentrates on predicting stock prices in the Egyptian market, focusing on the EGX30, an influential financial hub in the Middle East. While most research focuses on global stocks, there's a growing need to understand stock trends in developing countries like Egypt. The study compares different machine learning models for forecasting EGX30 trends, covering short and long-term predictions. Using historical EGX30 data, including metrics like root mean squared error, Mean Absolute Percentage Error, and coefficient of determination, models like K-Nearest Neighbours, random forest, extreme gradient boosting, long short-term memory networks, and gated recurrent unit networks were evaluated. The goal is to determine the most effective models for EGX30 prediction, considering Egypt's unique market dynamics. Insights from this study aid investors in making informed decisions. Results show that the Gated Recurrent Unit (GRU) outperformed the other models in the one-week, one-month, and two-months while the eXtreme Gradient Boosting (XGBoost) model outperformed others in the one-day predictions, highlighting their usefulness in predictive analysis for financial markets. The study also showed the importance of using the ensemble techniques, especially in the long-term predictions which proved better results reaching 5 times the GRU in the two-month predictions. Additionally, the study notes the surprisingly good performance of K-Nearest Neighbours (KNN) on long-term predictions, suggesting its enduring relevance and potential for future applications in the fintech domains. --- ### Why Git Is the Memory Solution for the Agentic Development Lifecycle Authors: Frank Guo Published: 2026-07-15 Categories: cs.SE, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.14390v1 Coding agents now produce a growing share of a team's code, while the reasoning behind each change -- the alternatives weighed, the constraints discovered, the approaches rejected -- is trapped in assistant transcripts that vanish with the session. Memory for this setting, the agentic development lifecycle (ADLC), is usually posed as one retrieval problem and built as machinery: tiered stores, memory graphs, compiled wikis, model-judged admission. We argue memory should instead be git-bound -- built into the repository's version control, inheriting the guarantees the machinery struggles to construct: ground truth from commits, freshness from rebuild, verification from the merge, containment from review. On this ledger we solve two problems separately, then combine them. Seed supply is closed as an eight-corpus retrieval study under a pre-registered ship discipline: five imported ranking mechanisms rejected, two kept, and a best configuration of ~0.31 pooled MRR -- ~60x the raw-transcript grep floor, ~15x an honest parsed-turn floor. Answer assembly is where ranking stops helping: single-shot retrieval scores only 0.07-0.20 answer-sufficiency on real developer questions, and ungated episode injection measurably degrades good answers. A router dispatches breadth to a git-anchored structural map, pointed lookups to confidence-gated episodes, and rationale to decision synthesis, which reconstructs why-arcs no single session contains (0.83 sufficiency on a young ~50k-LOC production system). Routed, the system answers at 382-980 tokens per question -- three orders of magnitude below the recorded history. Because ground truth is mined from commit-session links rather than annotated, every result is replicable on any user's own history at zero labeling cost. The remaining constraint is capture. Code, benchmark, and paper source: github.com/rekal-dev/rekal-cli. --- ### Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving Authors: Yuan Gao, Wenting Miao, Mattia Piccinini, Haoyu Wang, Qunying Song, Johannes Betz Published: 2026-07-15 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2607.14387v1 Validating autonomous driving systems requires diverse, regulation-compliant test scenarios. In simulation-based testing, scenarios are defined as executable scripts. Yet automatically generating such scripts from regulatory descriptions remains an open challenge, and existing approaches face fundamental trade-offs. Retrieval-assemble methods achieve reasonable compilation rates but lack scalability, whereas retrieval-based full-script generation suffers from low compilation success rates. We present Chat2Scenic, the first iterative retrieval-augmented framework to generate scenario scripts in Domain Specific Language (DSL). Specifically, Chat2Scenic provides a chatbot interface that supports interactive scenario refinement and integrates Retrieval-augmented Generation (RAG) to ground scenario generation in regulatory knowledge and DSL syntax. Furthermore, we propose an open benchmark for scenario generation comprising 123 scenarios from various regulations, including NHTSA and United Nations Vehicle Regulations, as well as other sources. Extensive evaluation with State-of-the-Art (SOTA) Large Language Models (LLMs) demonstrates that Chat2Scenic achieves 76.42% Compilation Success Rate (CSR) and 58.17% Framework Accuracy (FA), outperforming existing methods (Retrieval Assemble with 30.08% CSR, 11.03% FA and Retrieval full script generation with 16.26% CSR, 10.86% FA). To facilitate future research, we release our code as open source at https://github.com/TUM-AVS/chat2scenic. --- ### CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents Authors: Maxime Heuillet, Sharadind Peddiraju Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14386v1 Data science tasks span from closed-ended information extraction to open-ended analysis, presenting significant challenges for automation. Recent AI agents powered by language models show promise for handling such complex tasks. However, existing agents typically rely on a single initial state that conditions the entire agent's execution, making them vulnerable to cascading errors initiated by a suboptimal initial state. To mitigate this, we present CIPHER, an automated data science agent that leverages test-time scaling through the generation and selection of multiple initial states for concurrent execution. Unlike existing works on test-time scaling of AI agents, CIPHER explicitly decouples the generation of candidate initial states from their strategic selection for parallel execution. Through extensive evaluation on two benchmarks (closed-form and open-form tasks), we demonstrate that CIPHER exceeds state-of-the-art performance in matched-model comparisons, and remains competitive against larger-model baselines despite relying on a substantially smaller base LM. Our empirical study characterizes the design space of the Decoupled Exploration-Selection (DES) framework: we quantify how generation strategy, selection strategy, and aggregator model capacity contribute to overall performance, and derive actionable design recommendations for practitioners. --- ### MamaBench: Benchmarking LLM Robustness in Maternal and Child Health Diagnosis through Counterfactual Clinical Perturbation Authors: Thanni Adewuyi, Anuoluwa Sotome, Samuel Okoko, Angel Ezendu, Oluwafunke Akinbuwa, Oluwaseun Odunsi, Oluwasegun Oguntuase, Ifeoma Nwabueze, Abiodun Adereni Published: 2026-07-15 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.14385v2 Large language models achieve strong scores on medical benchmarks, yet these benchmarks evaluate each question in isolation, providing no measure of whether a system can distinguish clinically similar presentations requiring different interventions. We introduce MamaBench, the first counterfactual benchmark for maternal and paediatric AI: 434 expert-authored clinical narratives in 217 pairs across 371 pathologies, evaluated via the Bias Trap Rate (BTR), the conditional probability that a model fails the counterfactual given success on the base case. We propose Evidence-Anchored RAG (EA-RAG), a three-stage retrieval method that replaces aggregate similarity with an evidence coverage objective through clinical parameter extraction, coverage auditing, and contrastive sub-queries. Across eight configurations of four frontier LLMs, base accuracy overstates robust accuracy by 16-28 percentage points in every model. EA-RAG achieves 20.3% BTR and 65.0% robust accuracy on Claude Sonnet 4.6, a 5.5 percentage point BTR reduction without degrading base accuracy. The residual 20% BTR confirms that counterfactual robustness in clinical AI remains an open challenge. Keywords: counterfactual evaluation, clinical AI, maternal healthcare, retrieval-augmented generation, diagnostic robustness --- ### Random Parameter Noise Does Not Make Exact ReLU Verification Easy Authors: Mojtaba Soltanalian Published: 2026-07-15 Categories: cs.CC, cs.LG arXiv: https://arxiv.org/abs/2607.14375v1 We study exact verification of ReLU networks in an adversarial smoothed model. Every network weight and bias is independently perturbed by Gaussian noise, clipped to $(-2,2)$, and rounded to the exact dyadic grid determined by the input bit complexity. We show that, under the standard assumption $\mathrm{NP}\not\subseteq\mathrm{BPP}$, there is no sound and complete verifier whose expected running time is polynomial in network size, bit complexity, and inverse noise level for every base instance. The conclusion already holds at the fixed noise level $σ_\star=2^{-11}$ for one-hidden-layer networks over a unit box, with hidden fan-in at most three and base coefficients in $(-1,1)$. The proof combines an exact gap embedding with a quantitative robustness argument. For every E3SAT formula $Φ$ with $m$ clauses, a four-ReLU-per-clause construction satisfies $\max_{x\in(0,1)^n} g_Φ(x)=(m-\operatorname{unsat}(Φ))/3$, and coordinatewise threshold rounding never decreases the objective. A weighted parameter-sensitivity inequality and Gaussian concentration then show that a verification gap linear in $m$ survives the aggregate perturbation of all coefficients with probability at least $1-e^{-m/8}$. The proof includes clipping, exact dyadic rounding, output-layer perturbations, polynomial-bit sampling of the rounded Gaussian law, and the conversion from expected smoothed running time to a BPP algorithm. Computational checks test the exact identity and illustrate the different scaling of extensive and constant gaps; they are diagnostics rather than evidence for the complexity theorem. The result concerns worst-case base networks in the stated absolute-noise model, but it shows that parameter nondegeneracy alone does not yield a universal smoothed-polynomial guarantee for exact verification. --- ### A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning Authors: Yang Liu, Yuhao Liu, Yunran Wei Published: 2026-07-15 Categories: cs.LG, q-fin.RM arXiv: https://arxiv.org/abs/2607.14373v1 We propose a noise-robust elicit-to-optimize framework that integrates inverse reinforcement learning (IRL) and reinforcement learning (RL) for eliciting agents' risk preferences and optimizing policies under a broad class of risk objectives characterized by distortion riskmetrics. On the elicitation side, we propose an adaptive Bayesian IRL method that infers agents' latent risk objectives from their noisy observed decisions, explicitly allowing agents to take stochastic and suboptimal actions. We establish the existence of a finite set of distinguishing questions that identifies the preferred distortion riskmetric within the candidate class and prove that the convergence rate of the algorithm is of order $O(\exp(-cm+O(\sqrt{m\log m})))$ under general settings, where $c>0$ is a constant and $m$ denotes the number of algorithm iterations. On the optimization side, we develop a model-free RL algorithm for optimizing policies under conditional distortion riskmetrics. By representing the objective as an integral of the conditional cost quantile function with respect to the distortion function, the method unifies distortion-riskmetric objectives. We optimize diverse risk objectives by extending the Proximal Policy Optimization (PPO) algorithm with policy, value, and quantile neural networks, where the quantile network estimates the full conditional cost quantile function and enables numerical evaluation of general risk objectives. A comprehensive empirical study demonstrates the framework's elicitation accuracy and effectiveness in complex financial environments. --- ### Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion Authors: Fengzhuo Zhang, Zhuoran Yang, Dirk Bergemann Published: 2026-07-15 Categories: cs.LG, econ.TH, stat.ML arXiv: https://arxiv.org/abs/2607.14371v1 Large Language Models (LLMs) have revolutionized AI services, but a critical tension emerges: while personalization improves model performance, it consumes scarce computational resources that users must share. When should a user invest in expensive Supervised Fine-Tuning (SFT) versus lightweight In-Context Learning (ICL)? How does congestion from other users' personalization choices reshape these incentives? And what strategies should platforms adopt when offering multiple personalization algorithms? We develop a tractable framework for LLM serving that captures the statistical-economic trade-offs users face. Our analysis yields several surprising insights. First, we show that ICL and SFT dominate in different regimes, determined by an interplay between pretraining coverage and data signal-to-noise ratios, but congestion can flip these rankings. Second, equilibrium resource consumption exhibits pronounced non-monotonicity: improving pretraining precision reduces the congestion, while broader pretraining coverage and harder tasks sometimes increase it. Third, we prove that offering both personalization methods never hurts the platform's maximal profits, despite potentially increasing computational load. Experiments with GPT-2 on linear regression tasks validate our theoretical predictions about algorithm performance. Complementing these results, our review of documentation from 21 major AI platforms shows that the share offering both SFT and ICL increased from 9.5% in 2021 to 71.4% in 2025, consistent with our platform-design implications. --- ### Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning Authors: Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14367v1 Federated fine-tuning of large pre-trained models increasingly relies on Low-Rank Adaptation (LoRA) to reduce communication and computation, but heterogeneous clients can make adapter aggregation unstable. We identify the data-parameter interference as a geometric source of this instability. This interference is controlled by the alignment between LoRA update subspaces and client activations, suggesting that federated LoRA aggregation should be viewed not only as parameter averaging but also as subspace allocation. We propose Dynamic Subspace Boosting (Dysco), a plug-in method that allocates client-specific LoRA subspaces in a federated and dynamic manner. In each round, clients compute activation-insensitive subspaces from local representations and transmit only the resulting bases; the server then constructs client-specific merged subspaces through a closed-form solution that maximizes compatibility with other clients' insensitive directions. To handle representation drift, Dysco performs multi-round subspace boosting to preserve past update directions while adapting to future representations. We provide a convergence analysis that embeds the data-parameter interference as an aggregation-error term in a standard federated optimization bound, and prove that Dysco's server-fixed merged subspaces yield a tighter upper bound on this error. Experiments on controlled synthetic federated tasks and on MIMIC-IV clinical-note classification with Llama-3.2-1B show that Dysco substantially reduces interference, reduces the final-round synthetic training loss by up to 9 times relative to baselines under the orthogonal-subspace partition the theory identifies, improves all five tested FL algorithms by up to 4.3% on MIMIC, outperforms recent federated LoRA methods, and adds only 0.9% wall-clock overhead. Our code is available at https://github.com/illidanlab/Dysco. --- ### NeuralChaos: Optimal Adapted Approximation of Square Integrable Predictable Processes Authors: Anastasis Kratsios, Giulia Livieri, Philipp Schmocker Published: 2026-07-15 Categories: math.PR, cs.LG, q-fin.CP, stat.ML arXiv: https://arxiv.org/abs/2607.14361v1 We address fundamental challenges in representing and computing $\mathbb{R}^{d}$-valued predictable square-integrable processes over $(0,T)$, collected in the space $\mathcal{H}^2_T(\mathbb{R}^{d})$. These processes are central to continuous-time stochastic control, reinforcement learning, and mathematical finance. Although Wiener-chaos expansions offer strong theoretical tools, traditional computational methods are hindered by the need for large chaos dictionaries and high-order iterated integrals. To overcome these obstacles, we introduce NeuralChaos -- a neural operator architecture that produces elements of $\mathcal{H}^2_T(\mathbb{R}^{d})$ using only finitely many evaluations of the driving Brownian motion, while preserving predictability and square-integrability. We prove that NeuralChaos is dense in $\mathcal{H}^2_T(\mathbb{R}^{d})$ and achieves the best $N$-term chaoslet approximation rates for compressible and Malliavin--Sobolev regular processes. Moreover, compressibility is shown to be typical for processes from $\mathcal{H}^2_T(\mathbb{R}^{d})$ under non-degenerate sub-Gaussian sampling. In contrast, we show that finite-dimensional Markovian neural SDE models constitute a meagre and Gaussian-null subset in $\mathcal{H}^2_T(\mathbb{R}^{d})$, regardless of discretization, whereas compressible processes are generic. Numerical experiments on a stochastic optimal control problem and dynamic hedging highlight the practical effectiveness of our approach. Our results enable more efficient and expressive modelling in stochastic analysis and mathematical finance. --- ### Unsafe at any AUC: Unlearned Lessons from Sociotechnical Disasters for Responsible AI Authors: Joshua A. Kroll, Andrew Smart, R. Stuart Geiger, Abigail Z. Jacobs Published: 2026-07-15 Categories: cs.CY, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2607.14353v1 As automated decision-making and data-driven technologies pervade society and are used to manage consequential outcomes, understanding the technology's capabilities, limitations, and attendant risks in context requires analysis of full sociotechnical systems. Sociotechnical analysis of risks in highly complex systems provides clear lessons for the design and evaluation of AI systems, transcending a technical focus on reliable or "responsibly designed" components to understand risks at a systems level. Human-made catastrophes have been studied for decades because of the severity of these events: consider Chernobyl, Three Mile Island, Fukushima-Daiichi, Bhopal, the Challenger disaster. A common misconception is that these kinds of events are freak accidents, resulting from the inherently unforeseeable interactions in complex systems. Closer examination reveals that the risks and hazards were well-known beforehand but not acted upon due to social structural, political and economic factors. We outline several areas where the development and use of AI can benefit from learning these unlearned lessons: improved risk perception, communication, and analysis at the organizational level; traceability of requirements and responsibilities; and holistic approaches to responsibility and safety that include social and organizational dynamics as first-order engineering concerns. For each area, we offer concrete unlearned lessons and exemplify how they led to failure in prior accidents as well as examples of how these lessons remain unlearned for modern computing systems, particularly AI. --- ### Beyond Pairwise Relations: Dynamic Manipulation Hypergraphs for Vision-Based Human Activity Recognition Authors: Fatemeh Ziaeetabar Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14350v2 Fine-grained manipulation recognition requires modeling evolving relations among hands, objects, tools, and supporting surfaces. Conventional graph-based methods use pairwise edges that can fragment a coordinated event into disconnected binary relations. We propose a dynamic manipulation hypergraph framework that represents multi-entity configurations as higher-order relational units. At each temporal step, relevant entities are encoded using appearance, spatial, motion, and semantic-role features. Hyperedge candidates are instantiated and ranked using proximity, contact, and motion-coupling predicates. A hypergraph reasoning network performs node-to-hyperedge and hyperedge-to-node message passing, followed by temporal attention over the evolving interaction structure. The framework provides class-agnostic hyperedge-importance scores that identify entity configurations and temporal intervals emphasized by the model without treating them as causal explanations. Quantitative evaluation is conducted on EPIC-KITCHENS-100/VISOR and Assembly101 under an annotation-assisted entity-localization protocol. Video-only and entity-based methods provide contextual comparisons, while a matched pairwise graph and a static hypergraph serve as the principal controlled baselines because they use identical entity inputs and comparable relational settings. The proposed method improves HO-F1 over the matched pairwise graph by 6.9 percentage points on EPIC-KITCHENS-100/VISOR and 9.5 points on Assembly101, and exceeds the static hypergraph by 4.4 and 5.8 points, respectively. Qualitative analysis on ARCTIC further shows correspondence between highly ranked hyperedges and contact-rich manipulation intervals. These results demonstrate the value of time-varying higher-order relational modeling for fine-grained manipulation activity recognition. --- ### HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization Authors: Abdullah Shaikh, Zain Naqi, Taha Zahid, Sandesh Kumar, Abdul Samad Published: 2026-07-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.14349v1 While Large Language Models (LLMs) excel in many general NLP tasks, their formal reasoning capabilities are often compromised by content effects, demonstrating a measurable bias towards real-world plausibility. In this paper, we present our system for SemEval-2026 Task 11, which evaluates the ability of models to disentangle formal logic from content across 12 languages with and without distractor premises. We address this challenge using mDeBERTa-v3 networks fine-tuned on a synthetic, rule-based dataset of syllogistic schemes to avoid the semantic noise of LLM-augmented data. To explicitly decouple plausibility from logical structure, our training pipeline employs a multi-objective loss function combining Adaptive Group Distributionally Robust Optimization (DRO), a scheduled differentiable bias penalty, and KL-Divergence consistency regularization. Our system achieved #1 ranks and perfect Ranking Scores (100.0) with 0.00% bias and 100.0% accuracy on Subtask 1 (English), Subtask 2 (Noisy English), and Subtask 3 (Multilingual). On the highly complex Subtask 4 (Noisy Multilingual), the system achieved the 6th rank with 89.06% Accuracy and F1-score, alongside a limited 2.89% Bias and a 37.78 Ranking Score. Our dataset generation engine and codebase are publicly available to facilitate future work on robust logical reasoning. --- ### Learning Who to Treat When Treatment is Missing Authors: Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy Published: 2026-07-15 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.14346v1 Policy learning methods are increasingly used to inform treatment allocation under budget constraints. Most proposed methods assume complete treatment data, yet applications frequently suffer from missingness that can bias estimates and lead to suboptimal policies. We address this gap by extending efficient estimators for average treatment effect (ATE) estimation to policy value and conditional average treatment effect (CATE) estimation under missing at random (MAR) and missing completely conditionally at random (MCCAR) treatment data. Through asymptotic efficiency analysis, we prove that the MAR estimator, which leverages partially-observed units, is both valid and more efficient than the MCCAR estimator when MCCAR assumptions hold. This result provides formal justification for preferring MAR-based estimation in policy learning under both missing data settings. Our comprehensive experiments using synthetic and semi-synthetic datasets confirm that correctly specifying the missingness mechanism is crucial: misspecified estimators remain biased regardless of sample size, while our estimators achieve near-oracle performance when assumptions are satisfied. Our work provides practitioners with theoretically grounded, empirically validated tools for robust policy learning in the presence of missing treatment data. --- ### Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values Authors: Jan Betley, Johannes Treutlein, Jan Dubiński, Harry Mayne, Karol Gałązka, Niels Warncke, Anna Sztyber-Betley, Owain Evans Published: 2026-07-15 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.14345v4 People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it. --- ### Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values Authors: Jan Betley, Johannes Treutlein, Jan Dubiński, Harry Mayne, Karol Gałązka, Niels Warncke, Anna Sztyber-Betley, Owain Evans Published: 2026-07-15 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.14345v3 People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it. --- ### Beyond Visual Grasping: Benchmarking Complex Grasping from Detection to Execution Authors: Hanyi Zhang, Khang Nguyen, Charith Munasinghe, Basu Hela, Tianyu Li, Zihong Luo, Hoan Nguyen, Hans Wernher van de Venn, Yalin Zheng, Ravi Prakash, Tung D. Ta, Anh Nguyen et al. Published: 2026-07-15 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.14341v1 Robust robotic grasping remains a fundamental challenge for complex real-world applications. Recent advances in large-scale models demonstrate promising capabilities for reasoning in robotic tasks. However, existing benchmarks for grasping primarily focus on isolated, visual-based grasp pose detection, failing to capture the complexity of grasping tasks that require multi-step reasoning and semantic understanding during execution. To address this gap, we propose GCA-Bench, a benchmark featuring challenging \textit{grasping with complex action} scenarios that involve both scene-level reasoning and semantic constraints. GCA-Bench enables the evaluation of recent large foundation models under the same settings. To demonstrate the effectiveness of our new benchmark, we implement a diverse set of baselines, ranging from traditional grasp detection pipelines to end-to-end learning methods. Empirical studies achieve success rates below 70\% on complex grasping scenarios, underscoring critical limitations. In addition, we propose new evaluation metrics, analyze critical failure models, and provide insights to guide the development of more robust and generalizable grasping strategies. --- ### The Prover Is the Judge: Verified Security Software from AI Coding Agents in Ada/SPARK Authors: Tobias Philipp Published: 2026-07-15 Categories: cs.SE, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2607.14340v1 AI coding agents produce code faster than humans can review it. In our approach, the prover is the judge of whether the code is correct. Under a verifier-driven loop, AI agents wrote and verified bare-metal security software in Ada/SPARK spanning classical and post-quantum cryptography, TLS 1.3, IKEv2, X.509, and a Matrix client. GNATprove discharged 49,280 proof obligations, established functional correctness for selected primitives, and proved the absence of run-time errors for the rest, at roughly 20-40 times lower supervision cost than comparable hand verification. GNATprove alone was insufficient: some defects could not be detected and were resolved using known-answer tests, interoperability, or human review of specifications. Given weak checks, the agent tried to bypass them and reported success. We report where each layer caught faults and draw the central lesson: what an agent can be trusted to establish is bounded by the strength of its feedback. --- ### Beyond scalar losses: calibrating segmentation models via gradient vector field surgery Authors: Laurin Lux, Alexander H. Berger, Moritz Knolle, Daniel Rückert, Johannes C. Paetzold Published: 2026-07-15 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.14338v1 Region-based loss functions, such as the Dice loss, have established themselves as the de facto standard for highly class- and region-imbalanced segmentation tasks. However, models trained using region-based loss functions are notoriously miscalibrated and typically yield over-confident predictions. In medical imaging applications, such as defining tumor resection margins, this miscalibration is hindering clinical adoption. In this work, we outline a novel gradient perspective on this overconfidence and show how it affects region-based loss functions. We propose a "surgery" on the gradient vector field as a simple, yet effective intervention to mitigate calibration issues. This surgery adds a factor to the loss's partial derivative, scaling the gradient's magnitude linearly with the prediction error. In empirical evaluations across 2D and 3D medical segmentation tasks, we demonstrate the effectiveness of this intervention while maintaining high prediction accuracy when used in conjunction with any region-based loss function. --- ### Copy-on-Write Scoring: Application-Specific Agent Evaluations Authors: Joanna Roy, Sven Hoelzel Published: 2026-07-15 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.14336v1 Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail. Yet existing agent evaluation mechanisms are limited: benchmarks have low construct validity for application-specific workflows and environments, and replica evaluation environments are expensive and prone to drift. We propose Copy-on-Write (CoW) Scoring, a framework that evaluates agent operations directly within application environments using a PostgreSQL-level Copy-on-Write mechanism to isolate agent writes. CoW Scoring produces session- and operation-level scores that highlight where agents' database write operations succeed and fail in a given application environment, enabling inexpensive evaluation and iteration on agent harnesses and tool surfaces. We demonstrate the framework on Plane, an open-source project-management platform, where analysis surfaced specific issues in the tool surface, and corresponding fixes produced measurable improvements on affected models. Python library: https://github.com/trail-ml/agent-cow-python --- ### MixCompress: Mixture of Experts for Variable Rate Learned Image Compression Authors: Calvin-Khang Ta, Praneet Singh, Tong Shao, Peng Yin Published: 2026-07-15 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.14334v1 Learned image compression (LIC) is bottlenecked by the need to store independent models for each rate-distortion operating point. Existing variable bit-rate (VBR) methods aim to reduce this overhead via dense parameter modulation, but forcing a shared backbone to approximate divergent mappings causes severe feature entanglement. Specifically, low-rate smoothing gradients inherently conflict with the preservation of high-frequency textural details, leading to sub-optimal performance. To resolve this, we propose MixCompress, a unified VBR framework based on sparse structural specialization. While sparsely gated Mixture-of-Experts (MoE) routing successfully mitigates gradient conflict, it operates on a fixed computational budget. To address the increased representational demands of higher bit-rates we introduce a Mixture-of-Depths (MoD) extension to dynamically scale model capacity. Combined with Conditional Auxiliary Transforms (CAT) for dynamic sub-band energy modulation, our hierarchical framework effectively dynamically scales capacity. Extensive evaluations demonstrate that MixCompress not only matches individually optimized single-rate baselines but can even surpass them, establishing a new Pareto frontier for computationally efficient image coding. --- ### SD-MAR: Multi-image Analytical Reasoning via Synthetic Data and Reinforcement Learning Authors: Shiyu Yuan, Sourav Sanjukta Bhabesh, Zhe Wang, Dmitriy Bespalov, Wesley Rose, Huzefa Rangwala Published: 2026-07-15 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2607.14333v1 Vision Language Models (VLMs) demonstrate strong perceptual abilities but remain limited in tasks requiring analytical reasoning across multiple visual states, such as multi-image comparison, change detection, and multi-step visual inference. These capabilities are critical for real-world multimodal applications where reasoning must be grounded in systematic differences between visual contexts. However, existing benchmarks rarely require both explicit visual comparison and analytical reasoning, leaving this capability underexplored. To address this gap, we introduce SD-MAR (Synthetic Data for Multi-image Analytical Reasoning), a framework for training and evaluating VLMs on multi-image analytical reasoning. SD-MAR constructs paired visual scenarios through controlled perturbations and generates reasoning tasks spanning semantic change attribution and quantitative comparison. We further train VLMs using GRPO-lite with Backward Discounted Allocation (BDA), a reinforcement learning approach that removes KL regularization to encourage stronger policy optimization while allocating greater credit to the later reasoning steps where analytical conclusions are formed. Experiments on Qwen2.5-VL-7B and InternVL3-8B show that GRPO-lite fine-tuning on SD-MAR improves in-domain accuracy by up to 36.95%, with Qwen2.5-VL-7B outperforming GPT-4.1 on the SD-MAR benchmark. Importantly, out-of-domain generalization is preserved or improved: performance remains within 1% on MME, MMMU-Pro, and MathVista, while improving by up to 4% on MMBench. LLM-as-judge evaluation further demonstrates consistent improvements in logical coherence and explanation quality across both models. --- ### ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model Authors: San Lee, Nalee Kim, Jeong Il Yu, Hee Chul Park, Boah Kim Published: 2026-07-15 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.14328v1 In proton therapy planning, respiratory-gated non-contrast CT (NCCT) is commonly used for lesion segmentation; however, accurate delineation remains challenging due to low lesion-to-background contrast. Although learning-based methods have shown strong performance, they often struggle with non-contrast image segmentation. Inspired by clinical practice, where contrast-enhanced MRI is referenced to delineate lesions on NCCT, we propose ViPSAM, a visual prompting framework that leverages complementary cross-modality information. Built upon the Segment Anything Model (SAM), ViPSAM introduces a visual prompt encoder to extract guidance features from contrast-enhanced images and a visual-guided cross-attention module to integrate non-contrast and contrast-enhanced features, thereby enhancing lesion-relevant representations in low-contrast regions. The mask decoder is further adapted in a parameter-efficient manner to utilize visual prompts effectively. We evaluate the proposed method on liver lesion segmentation using NCCT acquired for proton therapy. Experimental results demonstrate that ViPSAM outperforms representative U-Net- and SAM-based methods, indicating that cross-modality visual prompting enables more robust and accurate segmentation in non-contrast images. --- ### PReM: Learning What to Preserve and When to Refresh for Context Compression Authors: Bohan Yu, Lei Shen, Chenxi Zhou, Chen Han, Junlin Liu, Wenbo Su, Yu Cheng, Bo Zheng Published: 2026-07-15 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.14327v1 Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such designs make it difficult to adapt the compressed context to the evidence needed by later reasoning steps. This paper introduces PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it. Specifically, PReM uses a dedicated memory layer to make memory-selection decisions, and a special memory token <m> to trigger refreshes during generation. To train this behavior, PReM introduces Phase-Separated Refresh Training, aligning memory selection with memory-conditioned generation while preserving continuity across refreshes. Experiments with 32K-token contexts show that PReM outperforms strong baselines under both 16x and 32x compression, while maintaining a favorable balance between answer quality and inference efficiency. --- ### Accounting for Hysteresis and Eddy Currents in Finite Element Simulations of Ferromagnetic Laminated Cores using a Recurrent Neural Network Authors: Florent Purnode, Louis Denis, François Henrotte, Gilles Louppe, Christophe Geuzaine Published: 2026-07-15 Categories: cs.CE, cs.AI, math.NA arXiv: https://arxiv.org/abs/2607.14321v1 Incorporating hysteresis and eddy currents into finite element simulations of laminated-core electrical machines is computationally challenging. Resolving the fields inside the laminations at each integration point and at every nonlinear iteration leads to computational costs several orders of magnitude higher than anhysteretic simulations, making such approaches impractical for design applications. Conversely, simplified models accounting only for magnetic saturation are becoming increasingly inadequate as electrical machine topologies and operating conditions grow in complexity. In this context, machine learning surrogate modeling has emerged as a promising alternative, offering efficient and accurate approximations of complex electromagnetic behaviors. In this paper, a recurrent neural network is trained as a surrogate of a laminated-core material model for an isotropic laminated core, and is integrated into realistic two-dimensional magnetodynamic finite element simulations based on a magnetic vector potential formulation. The proposed approach achieves excellent agreement with the reference laminated-core model while limiting the computational cost to about twice that of an anhysteretic simulation. By training the recurrent neural network on a sufficiently diverse set of artificially generated magnetic field sequences designed to mimic those encountered in electrical machine simulations, the proposed approach can be readily applied across a wide range of finite element simulations. Furthermore, the trained surrogate model is provided as a standalone component that can be easily incorporated into existing computational frameworks. It is publicly available at https://gitlab.onelab.info/getdp/lamnet. --- ### Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data Authors: Youssef Drissi, Markus Ettl, Shivaram Subramanian, Wei Sun, Zack Xue Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14318v1 We introduce COAT (Counterfactual Optimal Action Tree), a framework for learning interpretable prescriptive policies from observational data. COAT combines counterfactual outcome estimation with large-scale mixed-integer optimization, using column generation to translate causal predictions into feasible, transparent decisions under business and regulatory constraints. We apply COAT to airline ancillary pricing, a setting characterized by complex business rules and limited experimental flexibility. In a 17-week field pilot with a major global airline, COAT increased upsell revenue per booking by 6.9%, with the airline projecting \$50-\$150 million in incremental annual premium seat revenue across eligible domestic markets. The success of the pilot led to scaled adoption and informed broader AI-driven decision initiatives within the organization. --- ### Towards a Unified Multidimensional Explainability Metric: Evaluating Trustworthiness in AI Models Authors: Georgios Makridis, Georgios Fatouros, Athanasios Kiourtis, Dimitrios Kotios, Vasileios Koukos, Dimosthenis Kyriazis, Jonh Soldatos Published: 2026-07-15 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.14315v1 In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score. Our methodology focuses on three key aspects of explainability: fidelity, simplicity, and stability. We leverage benchmarking experiments to systematically evaluate these aspects and use the insights gained to construct an offline knowledge base. This knowledge base captures the explainability scores for each registered model and serves as a valuable resource for context-dependent evaluation of explainability. By analyzing the complementary characteristics and metadata of AI models, datasets, and XAI methods, the knowledge base will enable the estimation of explainability scores for previously unseen datasets and models. Properties like fidelity, simplicity, and stability may vary significantly based on the dataset, underlying model, and domain expertise of the end user. We demonstrate our framework by applying it to three open-source datasets, discussing the implications of the obtained results in relation to the characteristics of the datasets. Our work contributes to the growing field of XAI by providing a robust and versatile tool for evaluating and comparing the explainability of various XAI methods, ultimately supporting the development of more transparent and trustworthy AI systems. --- ### NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis Authors: Lincan Li, Zheng Chen, Yushun Dong Published: 2026-07-15 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.14314v1 Seizure diagnosis from EEG signals is a critical yet persistently challenging task, due to the complicated neural dynamics and the spurious connections in inter-channel modeling. While spatial-temporal graph neural networks (STGNNs) have advanced EEG brain network representation learning, the resulting graph structures suffer from low clinical plausibility and limited interpretability due to their purely data-driven nature. To this end, we introduce NeuroGRIP, a retrieval-augmented graph refinement framework that incorporates external medical knowledge to calibrate noisy EEG graphs. We first construct a large-scale, domain-specific knowledge base derived from authoritative clinical guidelines. Leveraging large language models, we extract structured biomedical entities and relations to form a textual knowledge graph (KG), which serves as external knowledge source of clinical priors. Our framework performs alignment-aware query construction by projecting STGNN-generated EEG node embeddings into the semantic space of KG. Semantic queries are then executed via FAISS-based similarity search over knowledge triplets to retrieve relation evidence. Each predicted edge is assigned a confidence score based on retrieved similarity, relation type, and source reliability, enabling us to prune medically implausible edges from the originally predicted graph. Extensive experiments on TUSZ and CHB-MIT demonstrate that NeuroGRIP not only improves seizure detection accuracy but also enhances interpretability by grounding each prediction in clinically validated knowledge. This work provides the first unified framework that tightly couples brain dynamics with external medical expertise via retrieval-augmented reasoning, paving the way for knowledge-enhanced, explainable clinical diagnosis. The code is available at: https://github.com/LincanLi-X/NeuroGRIP. --- ### Traccia: An OpenTelemetry-Based Governance Platform for AI Systems Authors: Nutan Kumar Naik, Aditya Kumar Saroj, Vijay Prasad Poudel, Saurav Samantray, Abhishek Patel Published: 2026-07-15 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2607.14309v1 The rapid development of Large Language Models (LLMs) and Artificial Intelligent (AI) powered autonomous agents has fundamentally changed the existing forms of software governance. In spite of the rigorous standards of transparency and account ability required according to the international frameworks such as the European Union's AI Act, there is a considerable gap between theory and reality. The present study discusses the inherent drawbacks of currently utilized platforms for LLM evaluation, machine learning workflow, and application performance monitoring in general. It has been shown that current disjointed solutions fail to protect unbound state space agentic architecture from serious threats such as alignment drift, SaaS security concerns, and unauthorized deployment of shadow AI systems. Moreover, a solution is proposed for overcoming the discussed challenges in form of a coherent multi-level AI governance stack Traccia built on the top of OpenTelemetry infrastructure platform. Traccia resolves the last mile for AI Alignment by adding the telemetry data, passive semantic guardrail assessment, and execution lineage into a hashed trace ledger. Traccia automatically creates compliance evidence packages by appending tamper-resistant fingerprints and SHA-256 content hash, that map to regulatory requirements (Articles 12, 14, 19, 26(6), and 50 of the EU AI Act) without invading any data privacy. By performing this evaluation in a methodical manner, a solid machine-readable base has been created for enterprise-wide management of autonomous AI systems. --- ### Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions Authors: Zachary Izzo Published: 2026-07-15 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14306v2 In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectly, and the agreement generally increases with model scale and training compute. Nevertheless, there is a long tail of input sequences where the LLM and ENTD differ significantly, and we examine several possible sources of this discrepancy across the transformer architecture, training procedure, and finite-sample noise in the ENTD estimate itself. More broadly, we hope our findings will encourage more work on ``data-centric mechanistic interpretability,'' a complement to standard mechanistic interpretability that opens the black box of how model behaviors arise from the data, rather than how they are encoded in the learned weights. ---