# Research Papers — 2026-07 · bundle page 3 of 222 > Full-text markdown of papers #101–150 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/3 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/2.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/4.md) ### Sixteen models, fewer than two voices: measuring ensemble dispersion where no answer is uniquely correct Authors: Mario Vega-Barbas, Lidia Mora-Valenciano, Iván Pau, Fernando Seoane, Farhad Abtahi Published: 2026-07-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.00285v1 Sixteen language models drawn from ten families produced, on average, the semantic diversity of 1.69 distinct formulations of a psychotherapeutic case, against a single-model baseline of 1.43 from one model's own runs. Ensembles place more than one reading before a decision-maker on the premise that several models supply several perspectives. Dispersion over their outputs is measured both as diversity and as uncertainty, and both traditions validate it against a correctness criterion that this task does not admit. Measuring diversity is a solved problem: the Vendi Score, the exponential of the von Neumann entropy of a similarity matrix, is an effective number of distinct elements. What a single aggregate does not say is where the diversity comes from. We define a per-model dissent contribution, the complement of a model's mean similarity to the other members of its ensemble: a magnitude from the same matrix, not a decomposition of the spectral index, whose maximum identifies the most divergent voice. Crossing model and case, we test as a preregistered hypothesis whether model identity accounts for a non-zero share of the variance in dissent, and characterise the structure that test detects. The panel formulated fifteen stratified vignettes, yielding 7,082 formulations for analysis. Model identity was a detectable structuring factor of the dissent that remained, but the usual categories recovered it only partly: scale differences pointed in opposite directions across pairs, family grouped models on only five two-member lines, and the most divergent voice changed with panel composition, so that the surfaced outlier describes the ensemble rather than the model. Dissent did not track the interpretive openness for which the case bank was stratified; it was organised by clinical content instead, leaving the dispersion an ensemble produces a property to measure rather than assume. --- ### Hybrid Attention Estimation Pipeline for Adaptive HRI Using an Expressive Robotic Head Authors: Pablo Moraes, Monica Rodriguez, Christopher Peters, Hiago Sodre, Tobias Doernbach, Bruna Guterres, Ricardo Grando Published: 2026-07-31 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.00284v1 This paper presents an applied case study on hybrid visual attention estimation for human-robot interaction using an expressive robotic head based on the InMoov ecosystem. The proposed pipeline combines a fast geometric perception layer with an independent semantic perception layer based on a vision-language model. The geometric layer provides high-frequency face and head-pose information for temporal regulation, while the semantic layer receives only raw egocentric camera frames and produces contextual attention labels related to attention toward the robot, phone use, or attention elsewhere. These signals are integrated through a finite state machine that regulates adaptive interaction behavior, including activation, waiting, interaction resumption, and return to rest. The system was evaluated with 10 participants across 40 trials covering baseline and adaptive interaction conditions. Results show reliable interaction start across all trials, consistent pause behavior in the adaptive distraction condition, and non-redundant semantic information between the geometric and semantic outputs. --- ### Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation Authors: Xuan Cuong Ngo Published: 2026-07-31 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2608.00279v1 Recent radiology-adapted vision-language models have achieved strong performance on standard report generation benchmarks, yet their robustness and generalization remain constrained by imperfect alignment and correlation between visual and textual features. Existing methods connect image and text either implicitly through autoregressive report supervision or explicitly through contrastive learning. However, autoregressive supervision alone is insufficient to establish reliable image-text alignment, while contrastive learning can push apart unpaired reports that describe related pathologies simply because they are not paired with the same image. This is problematic in radiology, where different reports may share compatible pathology semantics rather than being true negatives. As a result, the learned representation may fail to organize images and reports around shared pathology concepts, causing the decoder to rely on pretrained language priors and generate clinically plausible reports that are not fully supported by radiographic evidence. To address this issue, we propose PALM, a pathology-aware alignment framework for radiology report generation. Instead of directly matching each image-report pair while separating all others, PALM aligns visual and textual features through shared pathology prototypes. These prototypes provide a clinically meaningful bridge between radiographic evidence and textual findings, allowing cases with similar pathology semantics to move toward common concepts without separating compatible cases. In addition, we introduce Masked Evidence Modeling to strengthen the image encoder sensitivity to local radiographic evidence by learning semantic changes caused by masked image regions. Experiments on MIMIC-CXR, IU X-Ray, and MIMIC-ABN show that PALM consistently improves both report generation and abnormality-focused robustness. --- ### A reproducible and extensible framework for benchmarking competing risks survival models Authors: Begoña B. Sierra, Colin McLean, Peter S. Hall, Sarah Friedrich-Welz, Catalina A. Vallejos Published: 2026-07-31 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.00271v1 A wide range of statistical and machine learning methods have been proposed for survival analysis with competing risks, where the occurrence of one event (i.e., cancer death) precludes the occurrence of other events (i.e., cardiovascular disease death). Despite these methodological advances, their systematic evaluation and adoption are limited by the lack of comprehensive, reproducible and extensible benchmarking frameworks. We developed an open-source benchmarking framework for competing risks models that enables their systematic comparison across multiple datasets under different aspects of performance; calibration, discrimination, overall prediction error and clinical utility. We additionally introduce an extension of SHAP for competing risks, allowing model-agnostic interpretability of covariates contributions over time. All our code is publicly available via GitHub:https://github.com/BBolosSierra/CompRisksBenchmark --- ### Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization Authors: David Aguado, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar Published: 2026-07-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00270v2 Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP). However, the generalization capabilities of these Reinforcement Learning-based models are severely hindered when scaling to high-dimensional instances. This issue has been mitigated in other domains, like computer vision and natural language processing, by adopting a self-supervised pre-training strategy. Nevertheless, its application to routing graphs, which lack complex topological attributes beyond 2D spatial coordinates, remains a challenge. In this paper, we propose a geometric self-supervised pre-training framework specifically designed to capture spatial invariance and global relative distance distributions. By applying isometric transformations, such as rotations and axial reflections, the model learns robust structural representations prior to the policy optimization phase. Empirical results demonstrate that this strategy consistently outperforms models trained from scratch (baselines), achieving a 7.23\% improvement in tour length for massive zero-shot extrapolation scenarios (TSP1,000). Furthermore, the proposed model exhibits remarkable computational efficiency, delivering speedups of up to two orders of magnitude over the exact solver Concorde at massive scales. The source code and pre-trained models are publicly available at https://github.com/davidaguadocosano/TSP-GeoPretrain.git. --- ### Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization Authors: David Aguado, Daniel Fuertes, Carlos R. del-Blanco, Fernando Jaureguizar Published: 2026-07-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00270v1 Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP). However, the generalization capabilities of these Reinforcement Learning-based models are severely hindered when scaling to high-dimensional instances. This issue has been mitigated in other domains, like computer vision and natural language processing, by adopting a self-supervised pre-training strategy. Nevertheless, its application to routing graphs, which lack complex topological attributes beyond 2D spatial coordinates, remains a challenge. In this paper, we propose a geometric self-supervised pre-training framework specifically designed to capture spatial invariance and global relative distance distributions. By applying isometric transformations, such as rotations and axial reflections, the model learns robust structural representations prior to the policy optimization phase. Empirical results demonstrate that this strategy consistently outperforms models trained from scratch (baselines), achieving a 7.23\% improvement in tour length for massive zero-shot extrapolation scenarios (TSP1,000). Furthermore, the proposed model exhibits remarkable computational efficiency, delivering speedups of up to two orders of magnitude over the exact solver Concorde at massive scales. The source code and pre-trained models are publicly available at https://github.com/davidaguadocosano/TSP-GeoPretrain.git. --- ### LoopsBench: From Harness Engineering to Loop Engineering in Coding Agent Evaluation Authors: Han Li, Zhemin Fang, Rili Feng, Yingqi Zhao, Jiaheng Liu, Pengfei Gao, He Ye, Dayi Lin, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang Published: 2026-07-31 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2608.00267v2 Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations. We evaluate frontier coding agents paired with widely used loop implementations. The strongest configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks. Recorded plans recover only part of the source-recovered prerequisite DAG, and regression events remain visible across the evaluated loop profiles. We open source the benchmark data and code, including all tasks, more than 5,300 development units, and executable tests, at microsoft/Loopsbench. --- ### LoopsBench: From Harness Engineering to Loop Engineering in Benchmarking Coding Agent Authors: Han Li, Zhemin Fang, Rili Feng, Yingqi Zhao, Jiaheng Liu, Pengfei Gao, He Ye, Dayi Lin, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang Published: 2026-07-31 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2608.00267v1 Coding agent infrastructure is shifting from harness engineering toward loop engineering as coding agents are deployed for sustained long-horizon software development. Existing benchmarks often center on localized tasks or end-state outcomes, offering limited insight into sustained execution. We introduce LOOPSBENCH, a long-horizon benchmark for loop engineering in coding agent evaluation. Each task is a dependency DAG over separately testable development units with source-evidenced prerequisite edges. LOOPSBENCH comprises 112 tasks from authentic sources spanning 8 programming languages and 9 domains. Its flow-aware runtime releases tests along the ready frontier and retains completed nodes as regression obligations. We evaluate frontier coding agents paired with widely used loop implementations. The strongest configuration, Opus-4.7 with Claude Code and outer continuation, resolves 25.00% of tasks. Recorded plans recover only part of the source-recovered prerequisite DAG, and regression events remain visible across the evaluated loop profiles. We open source the benchmark data and code, including all tasks, more than 5,300 development units, and executable tests, at microsoft/Loopsbench. --- ### Interpretability-Guided Soft Pruning of Attention Heads in Vision Transformers Authors: Kamil Książek, Piotr Suszyński, Michał Jan Włodarczyk, Jacek Tabor, Przemysław Biecek Published: 2026-07-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.00264v1 Vision foundation models, such as DINOv2, learn highly expressive representations but rely on massive, opaque architectures that demand substantial computational power and memory. To provide an interpretable-guided and efficient solution to this issue, we first propose a spectral analysis and new visualization technique for individual attention heads based on the Laplacian eigenvectors of their attention maps. Building upon recent observations regarding the block structure of Vision Transformers, we perform semantic clustering of attention heads and identify functional redundancies. Leveraging these insights, we introduce SAPER (Soft Attention PrunER), an end-to-end differentiable pruning framework based on the LapSum Soft Top-K approach. Extensive experiments on ImageNet-1K demonstrate that SAPER achieves a highly favorable accuracy-efficiency trade-off, outperforming the competitive RAPTOR baseline in FLOPs reduction while preserving strong classification performance. --- ### Cross-Task Dissociation in Frontier Vision-Language Model Theory of Mind Authors: Kejia Zhang, Youran Sun, Chugang Yi, Haizhao Yang Published: 2026-07-31 Categories: cs.CL, cs.AI, cs.CV, cs.MA, q-bio.NC arXiv: https://arxiv.org/abs/2608.00261v1 Do frontier vision-language models present a coherent Theory-of-Mind (ToM) profile across tasks, matching the same human reference group, or does that profile fragment from one paradigm to the next? We evaluate a shared panel of nine frontier VLMs on two psychology-derived benchmarks: the Keysar Director Task (visual perspective-taking under egocentric interference) and the Frith-Happé animated triangles scored with the Castelli rubric (intention attribution from pure motion). On the Director Task, without chain-of-thought, the panel makes the egocentric error on 78\% of trials like children rather than adults; variation is substantial across models, and reasoning rescues several models. On the triangles, the panel under-attributes intention: its ToM profile sits more than three times closer to the high-functioning-autistic-adult (HF-ASD) mean than to the typical-development-adult (TD) mean, while Goal-Directed and Random stay near TD. No model is nearest TD on both tasks; the model that looks adult-like on the Director Task falls on the HF-ASD side on the triangles, and the most TD-like model on the triangles is child-like on the Director Task. We report group-level descriptions, not diagnostic labels for any model. --- ### MDWD: A Street-Level Dataset for Municipal Solid Waste Detection in Dense Urban Environments Authors: Andrea Filiberto Lucas, Mark Bugeja, Carl James Debono, Dylan Seychell Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00257v1 Automated visual monitoring of urban environments is a growing Computer Vision research area, but municipal solid waste detection remains under-represented in dedicated benchmark resources. Existing waste-related datasets predominantly address individual litter detection, aerial imagery, or image-level classification, and none simultaneously provide street-level imagery, instance-level localization, and categorization of domestic waste streams within a structured municipal collection context. This paper introduces the Maltese Domestic Waste Dataset (MDWD), a street-level benchmark comprising 3,697 high-resolution images and 11,461 manually annotated instances across five domestic waste categories representative of Malta's municipal collection system. The dataset captures substantial variation in location, illumination, object scale, occlusion, and urban context. To establish reproducible baselines, a cross-architecture benchmark is conducted across multiple generations of the YOLO family and a transformer-based detector. On the test set, RF-DETR-M achieves the strongest overall performance with an mAP50 of 94.49% and an F1-score of 93.56%, whilst smaller-capacity variants maintain competitive accuracy at substantially reduced parameter counts. These results indicate that MDWD supports effective training across both compact real-time detectors and transformer-based models, establishing a benchmark for future research in vision-based municipal waste monitoring. --- ### Bridging extrinsic and intrinsic variable importance Authors: Yucheng Zhao, Brian D. Williamson Published: 2026-07-31 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.00247v1 Variable importance may describe either intrinsic predictive information in a population or extrinsic importance for a fitted prediction rule. Quantifying the uncertainty in variable importance estimates is critical for interpretation. Methods for estimating intrinsic variable importance (we will refer to these as VIMP) and the minipatch leave-one-covariate-out procedure (MPLOCO) target intrinsic and extrinsic importance, respectively, and provide methods for computing standard errors. These two approaches have a shared structure, comparing prediction performance with and without features, but the relationship between them has not been formally characterized. We establish conditions under which the two perspectives align. Under squared-error loss, if the fitted full and reduced learners converge to their oracle counterparts sufficiently fast, then MPLOCO is asymptotically equivalent to VIMP. We provide further conditions extending this result to general loss functions and formalize grouped MPLOCO for potentially overlapping feature groups. Through simulations, we show that VIMP and MPLOCO agree most closely when the fitted learner is well aligned with the data-generating mechanism. In a high-dimensional grouped simulation, both procedures identified the signal-containing groups. In an analysis of HIV-1 VRC01 neutralization sensitivity, both methods placed the same three biologically relevant feature groups among their highest-ranked groups. These results clarify when intrinsic and extrinsic importance can be interpreted similarly and when they provide complementary information. --- ### Similarity-Aware Machine Unlearning Authors: Madhavan Citalamangalam Kumaran, Midhun Parakkal Unni, Vicky Kouni, Haripriya Harikumar Published: 2026-07-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.00246v1 Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localization-based methods improve unlearning efficiency by identifying a subset of influential model parameters. However, existing approaches select parameters based solely on forget-set importance, neglecting their role in retained dataset and often causing collateral damage to semantically similar retained examples. We address this limitation with a retain-aware localization method that considers parameter importance to both forgotten and retained data. We also introduce a retain-similar evaluation set, constructed using cosine similarity in the model embedding space, to directly measure collateral damage. Across eleven experimental settings on CIFAR-10 dataset and ResNet18 model, our method consistently reduces collateral damage while improving standard unlearning metrics, demonstrating the effectiveness of retain-aware localization for similarity-aware machine unlearning. --- ### More Debate, Same Evidence: Structural Limits of Homogeneous Multi-Agent Groundedness Authors: Yuelyu Ji Published: 2026-07-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00243v1 Large language model (LLM) judges are increasingly organized as multi-agent panels under the assumption that exchanging critiques improves judgment quality. We test this assumption for \emph{groundedness verification}, where a judge must determine whether a claim is supported by the supplied evidence. We evaluate a homogeneous three-agent panel on six public fact-verification and hallucination-detection benchmarks. Relative to a fixed single-agent reference, the panel's system-level accuracy difference ranges from $+8.5$ to $-4.4$ percentage points: two datasets show reliable gains, one shows a reliable loss, and three are statistically inconclusive. Because the reference and panel use different model variants, these differences characterize the complete systems rather than isolate a causal debate effect. --- ### Semantically Calibrated Evidence Composition for CT Vision-Language Learning Authors: Guoliang You, Haifan Gong, Xiaomeng Chu Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00239v2 Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods typically emphasize either global CT-report alignment or fine-grained anatomy-level correspondence. Global alignment preserves broad study context but leaves the contribution of localized evidence implicit, whereas anatomy-level alignment explicitly grounds local findings but does not specify how independently represented evidence should interact, acquire study-level meaning, and contribute to a global CT representation. To address this gap, we propose SCOPE (Semantic Calibration Of comPosed Evidence), a framework for semantically calibrated evidence composition in CT vision-language learning. Under organ-specific report supervision, mask-guided queries with fixed anatomical identities extract context-aware organ evidence from shared, uncropped volumetric features, while an unrestricted global query retains access to whole-volume context. The global query then drives Local-Global Coupling to compose the organ evidence into a unified evidence representation. The composed evidence is subsequently calibrated using the diagnostic summary, providing study-level semantic supervision beyond local organ descriptions, and is finally integrated as a controlled residual into a context-preserving whole-volume representation aligned with the complete report. This progressive pathway connects localized evidence with study-level semantics without reducing the CT representation to a predefined set of organs. On CT-RATE and RadChestCT, SCOPE achieves macro AUCs of 85.0 and 72.2, respectively, outperforming the previous SOTA by 7.2 and 4.2, while also yielding substantial gains in linear probing and cross-modal retrieval. These results demonstrate the effectiveness of semantically calibrated evidence composition. --- ### Semantically Calibrated Evidence Composition for CT Vision-Language Learning Authors: Guoliang You, Haifan Gong, Xiaomeng Chu Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00239v1 Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods typically emphasize either global CT-report alignment or fine-grained anatomy-level correspondence. Global alignment preserves broad study context but leaves the contribution of localized evidence implicit, whereas anatomy-level alignment explicitly grounds local findings but does not specify how independently represented evidence should interact, acquire study-level meaning, and contribute to a global CT representation. To address this gap, we propose SCOPE (Semantic Calibration Of comPosed Evidence), a framework for semantically calibrated evidence composition in CT vision-language learning. Under organ-specific report supervision, mask-guided queries with fixed anatomical identities extract context-aware organ evidence from shared, uncropped volumetric features, while an unrestricted global query retains access to whole-volume context. The global query then drives Local-Global Coupling to compose the organ evidence into a unified evidence representation. The composed evidence is subsequently calibrated using the diagnostic summary, providing study-level semantic supervision beyond local organ descriptions, and is finally integrated as a controlled residual into a context-preserving whole-volume representation aligned with the complete report. This progressive pathway connects localized evidence with study-level semantics without reducing the CT representation to a predefined set of organs. On CT-RATE and RadChestCT, SCOPE achieves macro AUCs of 85.0 and 72.2, respectively, outperforming the previous SOTA by 7.2 and 4.2, while also yielding substantial gains in linear probing and cross-modal retrieval. These results demonstrate the effectiveness of semantically calibrated evidence composition. --- ### Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving Authors: Meibo Hu, Jiamian Wang, Pichao Wang, Zhiqiang Tao Published: 2026-07-31 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.00237v3 Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation instructions directly to executable trajectories. However, in practice, these models exhibit a persistent command-following gap: predicted trajectories often show weak sensitivity to navigation commands, resulting in incorrect behavior at critical decision points. We identify this issue as a form of conditional policy collapse, where regression-based training under multimodal trajectory distributions encourages the model to rely on dominant visual priors while marginalizing the language-conditioned signal. To address this issue, we introduce a principled formulation of classifier-free guidance (CFG) for regression-based vision-language driving. We show that CFG can be interpreted as isolating the instruction-induced residual in the action space by contrasting conditional and unconditional predictions, thereby explicitly amplifying the effect of the navigation command at inference time. However, a standard two-pass CFG introduces prohibitive latency for real-time control and produces noisy instance-level guidance directions. Building on a mean-shift interpretation of CFG, we propose Latent-Centroid Steering (LCS), a single-pass guidance mechanism that replaces instance-level residuals with class-level latent shifts. By projecting conditional representations toward precomputed command-specific centroids, LCS performs class-level latent steering based on cluster geometry that is both more stable and computationally efficient. We demonstrate that LCS reduces inference latency by approximately 50% while achieving stronger command adherence and improved driving performance on both closed-loop (Bench2Drive) and open-loop (nuScenes) benchmarks. Code are available at https://github.com/codingmlinprocess/LCS. --- ### Latent-Centroid Steering: Single-Pass Classifier-Free Guidance for Command-Aligned Autonomous Driving Authors: Meibo Hu, Jiamian Wang, Pichao Wang, Zhiqiang Tao Published: 2026-07-31 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.00237v1 Vision-language models (VLMs) have recently emerged as a promising paradigm for end-to-end autonomous driving, enabling agents to map multimodal inputs and high-level navigation instructions directly to executable trajectories. However, in practice, these models exhibit a persistent command-following gap: predicted trajectories often show weak sensitivity to navigation commands, resulting in incorrect behavior at critical decision points. We identify this issue as a form of conditional policy collapse, where regression-based training under multimodal trajectory distributions encourages the model to rely on dominant visual priors while marginalizing the language-conditioned signal. To address this issue, we introduce a principled formulation of classifier-free guidance (CFG) for regression-based vision-language driving. We show that CFG can be interpreted as isolating the instruction-induced residual in the action space by contrasting conditional and unconditional predictions, thereby explicitly amplifying the effect of the navigation command at inference time. However, a standard two-pass CFG introduces prohibitive latency for real-time control and produces noisy instance-level guidance directions. Building on a mean-shift interpretation of CFG, we propose Latent-Centroid Steering (LCS), a single-pass guidance mechanism that replaces instance-level residuals with class-level latent shifts. By projecting conditional representations toward precomputed command-specific centroids, LCS performs class-level latent steering based on cluster geometry that is both more stable and computationally efficient. We demonstrate that LCS reduces inference latency by approximately 50% while achieving stronger command adherence and improved driving performance on both closed-loop (Bench2Drive) and open-loop (nuScenes) benchmarks. Code will be released. --- ### Attention-Steered Vision-Language Models for Sign Language Translation Authors: Meibo Hu, Guohao Sun, Annemarie D. Ross, Sheng Li, Zhiqiang Tao Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00235v2 Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language translation task, where we identify a key failure mode of existing VLMbased translators: poor spatial-temporal visual grounding. In particular, we find that standard next-token cross-entropy does not directly provide signal for where and when the model should attend, causing models to overlook sign-relevant regions and frames. To address this challenge, we propose AttnSign, a VLM-based spatial-temporal attention steering framework for sign language translation. AttnSign first introduces spatial attention supervision for sign-relevant regions, such as face and hands, in each frame; then develops an RL-based motion-cadence steering method that encourages the model to explore and focus on sign-level keyframes. Experimental results on How2Sign and OpenASL benchmarks show that our proposed AttnSign consistently outperforms existing methods. --- ### Attention-Steered Vision-Language Models for Sign Language Translation Authors: Meibo Hu, Guohao Sun, Annemarie D. Ross, Sheng Li, Zhiqiang Tao Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00235v1 Vision-language models (VLMs) have emerged as a powerful framework for multimodal video understanding. However, they remain limited in the sign language translation task, where we identify a key failure mode of existing VLMbased translators: poor spatial-temporal visual grounding. In particular, we find that standard next-token cross-entropy does not directly provide signal for where and when the model should attend, causing models to overlook sign-relevant regions and frames. To address this challenge, we propose AttnSign, a VLM-based spatial-temporal attention steering framework for sign language translation. AttnSign first introduces spatial attention supervision for sign-relevant regions, such as face and hands, in each frame; then develops an RL-based motion-cadence steering method that encourages the model to explore and focus on sign-level keyframes. Experimental results on How2Sign and OpenASL benchmarks show that our proposed AttnSign consistently outperforms existing methods. --- ### Real-Time Visual Obstruction Detection in Surgical Augmented Reality Authors: Shih-Chin Yang, Yanming Xiu, Hanting Ye, Qi Chen, Elias Rotondo, Maria Gorlatova Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00232v1 Surgical augmented reality (AR) can provide contextual guidance by overlaying virtual annotations, tool cues, and procedural information onto the surgical workspace. However, the virtual content may obstruct task-relevant real-world information, such as surgical instruments, and interfere with users' perception during time-sensitive surgical tasks. In this paper, we investigate visual obstruction detection for surgical AR and present a latency-aware pipeline that combines vision-language model (VLM)-based surgical-object recognition with segmentation-based obstruction reasoning. To reduce inference overhead, the system adopts a cascaded small-to-large VLM architecture with segmentation-guided early exiting and attention-based visual token pruning. The small VLM handles easy frames when its key-object prediction is supported by segmentation consistency, while difficult frames are forwarded to a large VLM with pruned visual tokens. We construct a pseudo-AR surgical obstruction detection benchmark by overlaying virtual content onto surgical-tool images and labeling whether the virtual content obstructs task-relevant instruments. Evaluation results show that the proposed system achieves 87.43% obstruction detection accuracy with an average end-to-end latency of 479 ms, reducing latency by 62.90% compared with a cloud large-model baseline. These results demonstrate the feasibility of latency-aware obstruction detection for surgical AR and motivate future work on dynamic surgical videos, multi-object scenes, and clinically grounded AR guidance content. --- ### Learning How Much, Not Just What: Cross-Patient Burden Order for CT Vision-Language Pretraining Authors: Guoliang You, Haifan Gong, Xiaomeng Chu Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00231v2 Volumetric CT vision-language pretraining learns 3D representations from scan-report pairs, but global and anatomy-aware objectives supervise only correspondence: they establish what is present and leave how much unconstrained. Nothing separates a mild from an extensive case of the same finding along a consistent direction, so the graded burden language in reports collapses into a present/absent signal. Longitudinal supervision would supply this order, but patient-matched CT pairs are scarce at scale; cross-sectional cohorts already encode weak burden cues across different patients. We introduce Spectrum, an anatomy-conditioned framework that represents each study at whole-study and organ scopes. For each organ-mapped pathology, a rule-based scorer mines confidence-filtered lower-to-higher pairs of different patients, and Burden-Direction Alignment (BDA) aligns the pathology-conditioned image delta with the report delta at each scope, separating that direction from its reverse. Because the endpoints are different people, a target-conditioned aligner first makes them comparable, so the delta reflects burden rather than between-patient variation. BDA further separates the selected direction from its reverse, anchors it to the observed higher-burden endpoint, and enforces consistency across ordered triplets. Since every pair is drawn within a single pathology, BDA is designed to constrain intra-class structure that image-report contrast alone never touches. Spectrum attains 85.6 zero-shot AUROC on CT-RATE and 72.7 on external RAD-ChestCT, with consistent gains in linear probing and retrieval. Weak cross-patient order is thus a scalable complement to anatomy-aware correspondence, yielding burden-aware CT representations without longitudinal data. --- ### Learning How Much, Not Just What: Cross-Patient Burden Order for CT Vision-Language Pretraining Authors: Guoliang You, Haifan Gong, Xiaomeng Chu Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00231v1 Volumetric CT vision-language pretraining learns 3D representations from scan-report pairs, but global and anatomy-aware objectives supervise only correspondence: they establish what is present and leave how much unconstrained. Nothing separates a mild from an extensive case of the same finding along a consistent direction, so the graded burden language in reports collapses into a present/absent signal. Longitudinal supervision would supply this order, but patient-matched CT pairs are scarce at scale; cross-sectional cohorts already encode weak burden cues across different patients. We introduce Spectrum, an anatomy-conditioned framework that represents each study at whole-study and organ scopes. For each organ-mapped pathology, a rule-based scorer mines confidence-filtered lower-to-higher pairs of different patients, and Burden-Direction Alignment (BDA) aligns the pathology-conditioned image delta with the report delta at each scope, separating that direction from its reverse. Because the endpoints are different people, a target-conditioned aligner first makes them comparable, so the delta reflects burden rather than between-patient variation. BDA further separates the selected direction from its reverse, anchors it to the observed higher-burden endpoint, and enforces consistency across ordered triplets. Since every pair is drawn within a single pathology, BDA is designed to constrain intra-class structure that image-report contrast alone never touches. Spectrum attains 85.6 zero-shot AUROC on CT-RATE and 72.7 on external RAD-ChestCT, with consistent gains in linear probing and retrieval. Weak cross-patient order is thus a scalable complement to anatomy-aware correspondence, yielding burden-aware CT representations without longitudinal data. --- ### Hierarchical BM25: Lexical Search at Billion-Document Scale Authors: Umesh Deshpande, Swaminathan Sundararaman Published: 2026-07-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.00229v1 A flat BM25 index over one billion documents occupies about 400 GB. Holding it in memory requires DRAM proportional to corpus size. Serving it from disk takes 4-12 seconds per query. Exact top-k lexical retrieval at this scale is therefore impractical within an interactive latency budget. Hierarchical BM25 gives up exact ranking in exchange for fixed bounds on memory and latency. A resident coarse index selects which of ~1K topical, size-balanced document groups a query visits, using two signals: the total frequency of each query term within a group, and, for informative terms spread too thinly across groups for frequency totals to reflect, whether several of them appear together in one document. Selected groups are then searched exhaustively and scored against ~100 KB of global statistics. Every returned score therefore equals the flat index's score, and the approximation is confined to selection alone. The resident footprint is ~4.4 GB, independent of corpus size. Sixteen-term queries over one billion documents return in ~300 ms (4.7x to 5.6x the throughput of a flat multi-threaded index), and a warmed cache sustains ~32 queries per second versus under 3 for flat indexing. At a 500K-document configuration, visiting 5-10% of clusters recovers 0.83-0.92 of the exhaustive result score. Billion-scale recall and a direct comparison against document-reordered BlockMax-WAND remain open. --- ### Verifier-Induced Support Reshaping in On-Policy Optimization Authors: Shaohang Wei, Zikun Su, Feifan Song, Wen Luo, Wei Li, Guangyue Peng, Houfeng Wang Published: 2026-07-31 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.00220v2 We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce. We call this verifier-induced support reshaping and define effective rewardable support as successful trajectories reachable within a fixed rollout budget. Across two model families, we study this effect through repeated verifier-scored sampling and bidirectional training on mathematical reasoning and constrained instruction following, including sequential training with the opposite verifier. Math-RLVR raises average instruction-following success but reduces the number of prompts with any successful response under repeated sampling. On IFEval with Qwen3-8B-Base, pass@1 rises by 6.5 percentage points while best@32 falls by 9.8 percentage points, and the same divergence appears across both models and IF benchmarks. Conversely, IF-RLVR shifts math responses from step-by-step openings toward direct answers, lowers best@k across sampling budgets, and reduces reward variation for later Math-RLVR. Token-distribution analyses and controlled opening interventions show that these changes concentrate in the first few response tokens. RLVR mainly reranks openings already available in the base policy, and the selected opening causally affects math searchability. The tested reference-policy constraints, routing priors, and on-policy distillation preserve cross-task support only partially; MathIF and ReasonIF show that marginal gains translate only partly into responses that are both correct and constraint-following. Therefore, endpoint improvements do not guarantee future trainability or joint capability under on-policy optimization. Code is available at https://github.com/sylvain-wei/VISR --- ### Verifier-Induced Support Reshaping in On-Policy Optimization Authors: Shaohang Wei, Zikun Su, Feifan Song, Wen Luo, Wei Li, Guangyue Peng, Houfeng Wang Published: 2026-07-31 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.00220v1 We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce. We call this verifier-induced support reshaping and define effective rewardable support as successful trajectories reachable within a fixed rollout budget. Across two model families, we study this effect through repeated verifier-scored sampling and bidirectional training on mathematical reasoning and constrained instruction following, including sequential training with the opposite verifier. Math-RLVR raises average instruction-following success but reduces the number of prompts with any successful response under repeated sampling. On IFEval with Qwen3-8B-Base, pass@1 rises by 6.5 percentage points while best@32 falls by 9.8 percentage points, and the same divergence appears across both models and IF benchmarks. Conversely, IF-RLVR shifts math responses from step-by-step openings toward direct answers, lowers best@k across sampling budgets, and reduces reward variation for later Math-RLVR. Token-distribution analyses and controlled opening interventions show that these changes concentrate in the first few response tokens. RLVR mainly reranks openings already available in the base policy, and the selected opening causally affects math searchability. The tested reference-policy constraints, routing priors, and on-policy distillation preserve cross-task support only partially; MathIF and ReasonIF show that marginal gains translate only partly into responses that are both correct and constraint-following. Therefore, endpoint improvements do not guarantee future trainability or joint capability under on-policy optimization. Code is available at https://github.com/sylvain-wei/verifier-induced-support-reshaping --- ### A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use Authors: Yutong Ke, Ming Yin, Chongwen Zhao, Kaizhu Huang Published: 2026-07-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.00218v1 Agentic LLMs exhibit three consequential tool-use failures: invalid arguments (validity), unnecessary calls (over-calling), and omitted calls when tools are needed (missing). We find that a small, failure-specific set of MLP neurons could distinguish such failures with linearly separable decision boundaries. Building on this observation, we introduce PRISMS (Probing Representations In Support of Monitoring and Steering), a closed-loop framework that shares a failure-specific neuron basis between sparse detection and activation steering. PRISMS selects contribution-critical MLP neurons and fits an L1-regularized detector on their activations. Across six models from the Qwen3, Llama, and Gemma families, over-calling and missing are detected at the pre-generation prompt boundary with ROC-AUC 0.90-1.00, while validity is detected from the generated tool-call span with ROC-AUC 0.86-0.90. These results are achieved with highly sparse readouts: only 1-2 MLP neurons for missing, 2-16 for over-calling, and approximately 128 for validity. These sparse detectors match or outperform dense residual-stream baselines using 23-627 times fewer features. The shared neuron basis also supports bidirectional control over tool-calling behavior, suppressing unnecessary calls and eliciting omitted ones. PRISMS therefore gates intervention on predicted failure risk to mitigate the collateral effects of unconditional steering. Across all six models, PRISMS reduces pooled over-calling rate by 80% (from 0.131 to 0.026) while increasing tool-required accuracy by 14.2 percentage points (from 0.689 to 0.831). PRISMS thus provides lightweight failure detection and selective intervention across model families. --- ### Personalizing Large Language Model Agents with Small Policy Models Authors: Dian Jin, Zhi Zhang, Huichao Li, Yihe Pan, Rundong Huang, Doudou Zhou Published: 2026-07-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.00215v1 Large language model (LLM) agents can retrieve memory, call tools, ask clarifying questions, and vary response style, yet adapting these execution decisions to an individual user remains difficult. Fine-tuning a separate LLM is costly or impossible for proprietary systems, while prompts and memory primarily expose user information to the agent rather than adapt its execution decisions from feedback. We formulate personalization of a frozen agent as online learning of a per-user execution policy from scalar feedback observed only for the executed action. We propose FABLE (Factorized Adaptive Bandit Layer for Execution), a lightweight policy layer outside a potentially black-box host agent. FABLE factorizes memory, information-acquisition, and response decisions so feedback updates related choices; filters actions through an externally specified feasible set before exploration; and learns user-specific residual preferences relative to a fixed default-and-cost score via Bayesian contextual Thompson sampling. Under a linear residual-reward model, a calibrated variant inherits an expected-regret bound against the best feasible action. We also characterize preferences unidentifiable under persistent feasibility constraints and provide anytime-valid false-promotion control. Across personalized-reasoning, controlled-feedback, and executable tool-use evaluations, FABLE improves several preference-sensitive behaviors relative to rule-only control while remaining competitive on end-to-end task performance. --- ### Manifold-GS: Certified Hybrid Assets via Varifold-Conservative Gaussian Splatting Authors: Boyang Li Published: 2026-07-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.00214v1 3D Gaussian Splatting (3DGS) gives high-quality novel-view synthesis, but its adaptive radiance primitives are not directly usable as structured assets: opacity is not an additive area measure, refinement can change the induced geometry, and watertight mesh extraction can hallucinate collision surfaces in unobserved regions. We introduce Manifold-GS, a certified hybrid asset layer for Gaussian scenes. The method separates appearance opacity from geometric quadrature mass, represents surface-like Gaussians as a discrete unoriented varifold, and exports only confidence-certified open surface patches while retaining uncertified content as residual splats. It provides refinement-conservative mass transport, local realizability diagnostics, source-preserving patch bindings, and conservative collision candidates. On three DTU scenes, a frozen asset benchmark shows zero patch-defined edit leakage, texture round-trip PSNR of 30.1/35.3/33.7 dB, and lower collision floater area than official 2DGS meshes on all scenes, with large gaps on two scenes. The result is a precision-coverage tradeoff rather than a universal reconstruction claim. External-region annotations, phantom-collision probes, and 5k-face simplification further support the certified asset interpretation, while RGB-only experiments show that local realizability is not sufficient for sparse-view surface identifiability. --- ### A Physics-Chemistry-Informed Neural Network (PCINN) for Real-Time Spatial-ALD Coverage Prediction and Reliable Kinetics Inversion Authors: Ning Hu, Chang Liu, Yunlei Jiang, Yuan Dong Published: 2026-07-31 Categories: cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2608.00212v1 Spatial atomic layer deposition (SALD) is a leading atmospheric-pressure, high-throughput route to industrial ALD, but design and control are limited by the cost of predicting surface coverage: high-fidelity CFD is far too slow for operating-window scans, while analytic models miss transport modulation such as the gas curtain. We present a physics-chemistry-informed neural network (PCINN), a hybrid surrogate with CFD-level accuracy at real-time speed: a query returns coverage in about 7 ms, roughly 5x10^4 times faster than a CFD solve, reaching a test R^2_log = 0.998 (leave-one-out R^2_raw = 0.974) from only 30 training cases spanning four orders of magnitude in coverage. The architecture is not a black box: a small network learns only the operating-condition to near-wall concentration closure, while the known surface kinetics is a hard-coded, trainable chemistry layer integrated along the substrate trajectory. This single-scalar bottleneck keeps it accurate under sparse data, interpretable and invertible. We add a full identifiability analysis (Fisher information, profile likelihood). The adsorption energy E_ads and desorption rate k_des are robustly identifiable; k_ads is not separately identifiable at a single temperature (only k_ads*c_wall is). Across four temperatures the prefactor nu and E_ads bind along a weakly identifiable degeneracy valley of slope 0.065 eV/decade, derived analytically as k_B T_eff ln(10) and turned into a reliability diagnostic: a seven-chemistry mismatch matrix shows it is invariant under any single-Arrhenius mismatch and shifts only when a second thermally activated process appears, so a slope departure flags unmodelled site heterogeneity. Data come from simulation with known ground truth inverted by the same kinetic form, so the study verifies pipeline self-consistency and the identifiability boundary, not real parameters. --- ### Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection Authors: Chaimae Abouzahir, Musa Khan, Hala Ali-Hassan, Congbo Ma, Khaled Saleh, Yousra Sadqi, Jihad Mallat, Walid Al-Eisawi, Nizar Habash, Farah E. Shamout Published: 2026-07-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.00207v2 Large Language Models (LLMs) perform strongly in English medical tasks but degrade substantially in Arabic, a gap widely attributed to limited training data. We systematically investigate this assumption via tuned lens probing and causal activation patching, and find that Arabic medical knowledge is present in intermediate model representations but fails to surface at the output. This mechanistic insight motivates a targeted adaptation strategy: rather than fine-tuning the full network, we propose Targeted Low-Rank Adaptation (TLoRA), restricted to the layer window where cross-lingual representations diverge, upstream of the output layers where the failure manifests. We evaluate TLoRA on multiple-choice medical QA, where our approach outperforms full-network LoRA, zero-shot, and few-shot baselines. We further evaluate it on short-answer generation and multi-turn clinical dialogue, where it performs competitively without the need for task-specific finetuning. We additionally introduce AraClinicDialog, a clinician-constructed Arabic medical dialogue benchmark in MSA with validated variants across four Arabic dialects. Together, these contributions demonstrate that mechanistic diagnosis can serve as a practical guide for targeted adaptation in underrepresented-language medical LLMs. --- ### Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection Authors: Chaimae Abouzahir, Musa Khan, Hala Ali-Hassan, Congbo Ma, Khaled Saleh, Yousra Sadqi, Jihad Mallat, Walid Al-Eisawi, Nizar Habash, Farah E. Shamout Published: 2026-07-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.00207v1 Large Language Models (LLMs) perform strongly in English medical tasks but degrade substantially in Arabic, a gap widely attributed to limited training data. We systematically investigate this assumption via tuned lens probing and causal activation patching, and find that Arabic medical knowledge is present in intermediate model representations but fails to surface at the output. This mechanistic insight motivates a targeted adaptation strategy: rather than fine-tuning the full network, we propose Targeted Low-Rank Adaptation (TLoRA), restricted to the layer window where cross-lingual representations diverge, upstream of the output layers where the failure manifests. We evaluate TLoRA on multiple-choice medical QA, where our approach outperforms full-network LoRA, zero-shot, and few-shot baselines. We further evaluate it on short-answer generation and multi-turn clinical dialogue, where it performs competitively without the need for task-specific finetuning. We additionally introduce AraClinicDialog, a clinician-constructed Arabic medical dialogue benchmark in MSA with validated variants across four Arabic dialects. Together, these contributions demonstrate that mechanistic diagnosis can serve as a practical guide for targeted adaptation in underrepresented-language medical LLMs. --- ### Averaging Bias: Human Faithfulness Annotations are not Locally Faithful Authors: Huajian Zhang, Yiyang Feng, Jiawei Zhou Published: 2026-07-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.00205v1 Evaluation of faithfulness of text summarization treats a model generated summary as faithful only if every of its sentences is supported by the source document: a strict conjunctive rule under which a single unsupported sentence makes the whole summary unfaithful. Yet most faithfulness benchmarks collect only one global human annotation label per summary. We ask whether such global human labels actually implement the conjunctive rule. We hypothesize that annotators may accept a summary as faithful when most sentences are faithful, not only when all are faithful. To test our hypothesis, we use five large language model (LLM) judges as per-sentence raters across four widely used faithfulness benchmarks. We find that global human labels correlate better with the average of per-sentence LLM judgments than with the implementation of the strict conjunctive rule. A manual review confirms that a substantial fraction of summaries labeled faithful by humans contain genuine local factual errors. We call this tendency Averaging Bias. Our results reveal that human labels on widely used faithfulness benchmarks contain measurable Averaging Bias, calling for carefully structured designs for trustworthy human annotations --- ### TRACE-TS: Attribution-Grounded and Traceable Sensor-Language Reasoning for Human Activity Understanding Authors: Sparsh Rastogi, Tanmay Kumar, Baiyu Chen, Jatin Bedi, Zechen Li, Flora D. Salim Published: 2026-07-31 Categories: cs.AI, cs.CL, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2608.00200v1 Wearable sensors capture fine-grained motion patterns that support rich behavioral understanding, yet most existing methods reduce these signals to activity labels. Recent LM-based approaches generate natural-language explanations for sensor data, but their reasoning is weakly grounded in the underlying signal, leading to fluent yet unverifiable explanations. We introduce TRACE-TS (Traceable Reasoning with Attribution-Grounded Evidence), a framework for structured and signal-grounded reasoning over wearable time series. TRACE-TS uses attribution from an expert classifier to identify salient spatio-temporal sensor regions, uses them to construct DAG reasoning traces with explicit evidence provenance, and trains a compact language model to generate these traces through gated cross-attention over sensor memory tokens. At inference, the adapted model jointly outputs the activity prediction and its reasoning trace, without requiring attribution computation or teacher guidance. We introduce Semantic Node Match(SNM), an LLM-as-judge metric that diagnoses reasoning fidelity at the observation, inference, and synthesis levels, localizing hallucinated observations and broken evidence chains missed by standard NLG metrics. Across seven wearable benchmarks, TRACE-TS achieves the best average accuracy and F1 among all evaluated methods (84.43%/81.24%), and outperforms the best LLM-based baseline by 17.96% in F1. Our code is available at https://github.com/SparshRastogi/TRACE-TS. --- ### AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery Authors: Marco Ruiz, Miguel Arana-Catania, David R. Ardila, Rodrigo Ventura Published: 2026-07-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.00198v1 Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adequacy, multiple-testing control, and evidence interpretation. Applied inconsistently across datasets, these choices yield graphs that cannot be compared, reproduced, or audited. We present AutoCause, an open-source Python workflow that records each decision, derives defaults from an extended causal-audit module, and admits domain-informed overrides. The workflow wraps four established causal-discovery methods from three families, adds non-causal reference models, and grades links by method-count support. On 145 datasets from DGP-Atlas, TimeGraph, and a topology-derived CausalRivers reference, the methods recover complementary parts of the reference graphs. Majority-supported links are more precise than single-method links on the synthetic benchmarks but not against river topology. AutoCause converts inconsistent expert practice into an auditable, repeatable analysis; causal interpretation remains with the analyst. Available at https://github.com/marcoruizrueda/autocause. --- ### MedSAM2-Anatomy: Training-Free Inference-Time Optimization for Musculoskeletal Segmentation Authors: John Garcia Henao, Nicholas Bünger, Benedikt Herzog, Cindy Guerrero Toro, Benjamin Vella, Matthias Biner, Rico Brütsch, Carmen Castroviejo Fernandez, Felix Öttl, Norman Juchler, Armando Hoch, Bettina Hochreiter et al. Published: 2026-07-31 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.00195v1 High-resolution 3D segmentation of hip and shoulder anatomy from CT and MRI is essential for surgical planning, yet frozen segmentation models often fail under domain shift. CNN-based expert models are fully automatic but lack adaptability, whereas promptable foundation models generalize better but require manual prompting. We present MedSAM2-Anatomy, a training-free inference-time optimization framework that improves frozen segmentation models without retraining or human interaction. A frozen expert model generates anatomical priors that are automatically converted into multiple prompt hypotheses for a frozen 3D foundation model. Candidate masks are fused while anatomically implausible priors are rejected. No model weights are updated and no manual prompts are required. TotalSegmentator and MedSAM2 are used as representative expert and foundation models, allowing the contribution of the inference policy to be isolated. Evaluation on the independent Balgrist-V0 CT and MRI cohorts shows that inference-time optimization increases median Dice from 0.71 to 0.92 on hip MRI and from 0.89 to 0.92 on shoulder CT, while reducing median HD95 on hip MRI from 22.0 mm to 5.0 mm. On public TotalSegmentator benchmarks, the expert model remains strongest, indicating that the optimal fusion strategy depends on the reliability of the expert prior. These results demonstrate that training-free inference-time optimization provides a practical strategy for improving frozen segmentation models without manual prompting. --- ### SCALP: Semi-Supervised Statistical Shape Modeling from Imperfect 3D Photogrammetry via Landmark-Anchored Spectral Warp Authors: Nawazish Khan, Sanjay Bhandari, Sarang Joshi, Alzbeta Novotna, Tiffany Jeong, Loretta Bowman, Michael Hernandez, Tobi Somorin, Viraj Govani, Jesse Glodstein, Shireen Elhabian Published: 2026-07-31 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.00187v1 Correspondence-based statistical shape modeling (SSM) is vital for population-level morphometric analysis, but conventional pipelines assume clean, fully registered surfaces. Real-world clinical photogrammetry scans are often noisy, partial, and cluttered, hindering the adoption of radiation-free surface imaging as a safe alternative to computed tomography (CT) for infant craniosynostosis. We present SCALP (Semi-supervised Correspondence via lAndmark Localization and sPectral warping), a two-stage framework that constructs consistent shape models directly from raw, imperfect surface scans. First, a semi-supervised Point Transformer leverages a small expert-annotated dataset alongside a large unlabeled cohort to accurately localize craniofacial landmarks with minimal annotation overhead. Second, these landmarks anchor a Laplace--Beltrami spectral deformation of an anatomical template, generating dense correspondences while naturally isolating the cranium from peripheral scanning clutter without manual preprocessing. Experiments on infant photogrammetry scans demonstrate that SCALP consistently outperforms state-of-the-art unsupervised point-cloud approaches, offering a clinically practical pathway toward objective, radiation-free head shape analysis. --- ### Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval Authors: Chenyu Wu, You Lin Published: 2026-07-31 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2608.00183v2 Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense hybrid retrieval on FinDER, a benchmark of expert-annotated questions over corporate 10-K filings. Our first finding is methodological: if the retrieval unit is larger than the dense encoder's input window, the dense model never sees a large share of the labeled evidence, confounding comparison against a full-text sparse baseline. We measure this directly and reduce the imbalance with windows chosen for the encoder budget. On this corpus, fusing BM25 and a compact dense encoder improves reference-level Hit@10 by roughly 28 percent over either component, and training-free, untuned reciprocal rank fusion exceeds the equal-weight blend in an exploratory comparison. We then ask whether choosing the fusion weight per query helps: an oracle over the interpolation-weight grid shows headroom of 21.8 percent, yet none of the three lightweight adaptive routers (a score-confidence heuristic, a random forest over query features, and a ridge regressor over query embeddings) establishes a statistically reliable improvement over the fixed blend under company-grouped cross-validation with cluster-robust inference. Simple fusion is a strong baseline here, and we discuss why per-query weighting does not capture the available headroom. --- ### Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval Authors: Chenyu Wu, You Lin Published: 2026-07-31 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2608.00183v1 Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense hybrid retrieval on FinDER, a benchmark of expert-annotated questions over corporate 10-K filings. Our first finding is methodological: if the retrieval unit is larger than the dense encoder's input window, the dense model never sees a large share of the labeled evidence, confounding comparison against a full-text sparse baseline. We measure this directly and remove it by segmenting the corpus into encoder-sized windows. On the corrected corpus, fusing BM25 and a compact dense encoder improves reference-level Hit@10 by roughly 28 percent over either component, and training-free, untuned reciprocal rank fusion exceeds the equal-weight blend in an exploratory comparison. We then ask whether choosing the fusion weight per query helps: an oracle over the interpolation-weight grid shows headroom of 21.8 percent, yet none of the three lightweight adaptive routers (a score-confidence heuristic, a random forest over query features, and a ridge regressor over query embeddings) establishes a statistically reliable improvement over the fixed blend under company-grouped cross-validation with cluster-robust inference. Simple fusion is a strong baseline here, and we discuss why per-query weighting does not capture the available headroom. --- ### Cross-Benchmark Generalization in Long-Horizon Agents Authors: Sushant Mehta, Logan Ritchie, Liudas Panavas, Edwin Chen Published: 2026-07-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.00181v1 For reinforcement learning (RL) in self-contained environments, a policy can get rewards by exploiting environment-specific regularities (tool schemas, grader parsing, task templates) rather than by acquiring transferable skill, and an in-distribution holdout shares those regularities. We argue that the discriminating question is behavioral, namely how a trained agent acts, and that cross-benchmark transfer is the right place to look for it. We post-train an open-weight mixture-of-experts model (Qwen3.5-122B-A10B) on 363 long-horizon Model Context Protocol (MCP) tasks across 27 categories, using a two-stage SFT-then-RL pipeline. Toolathlon performance informed the initial base-family and SFT-teacher choices, but no external-benchmark task or grader entered training and no external score informed the reward, training hyperparameters, trained-checkpoint selection, or stopping. At greedy pass@1, the trained model improves over the base on five reported external evaluations: Toolathlon (+9.6 pp), $τ^2$-Bench (+5.3 pp), BFCL-V4 (+3.5 pp), SWE-Bench Pro (+5.8 pp), and Terminal-Bench 2 (+2.8 pp). Both software-engineering benchmarks improve despite the training collection containing no software-engineering tasks. An exploratory paired-trajectory analysis identifies four recurring behavioral differences (more careful local-goal formation, building goal-relevant working state, keeping parent goals stable through local repairs, and verifying completion) that appear in analogous forms across office workflows and code. These results provide descriptive evidence that long-horizon multi-tool post-training can change ways of working that transfer beyond its training domain. --- ### C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument Authors: Xianling Zhang Published: 2026-07-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.00180v5 Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two objectives that conflict: catch real harm, and do not refuse benign prompts. Our finding is that over-refusal improves 22.4% to 12.8%, while under-refusal on adversarial attacks silently worsens 0.27 to 0.33. We present C-Instrument, a constitution-grid data instrument that generates the RL training data, and C-LIM, a per-cell learnability score that decides each cell's move: prune, densify, amend, expand. C-LIM flags the dead-weight data region before any training budget is spent: 187 untargeted rows had bought zero gain, and our method lifts the same region's learning impact 0.733 to 0.80. Code and the constitution are open-sourced. --- ### A Constitution-Grid Instrument for Data-Efficient RL Alignment (C-Guard) Authors: Xianling Zhang Published: 2026-07-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.00180v2 Conflicting objectives are general in RL alignment, and training on them data-efficiently is hard. Training a safety guard with RL means optimizing two objectives that conflict: catch real harm, and do not refuse benign prompts. Our finding is that over-refusal improves 22.4% to 12.8%, while under-refusal on adversarial attacks silently worsens 0.27 to 0.33. We present C-Guard, a constitution-grid instrument that generates the RL training data, and C-LIM, a per-cell learnability score that decides each cell's move: prune, densify, amend, expand. C-LIM flags the dead-weight data region before any training budget is spent: 187 untargeted rows had bought zero gain, and our method lifts the same region's learning impact 0.733 to 0.80. Code and the constitution are open-sourced. --- ### Inference-Time Policy Alignment for Fair Reinforcement Learning Authors: Umer Siddique, Peilang Li, Conor Wallace, Yongcan Cao Published: 2026-07-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.00175v1 Deep reinforcement learning (RL) agents achieve strong performance by optimizing scalar reward functions. However, once deployed, the policies of these RL agents are often rigid and costly to adapt to new performance criteria. For instance, an agent trained to maximize expected cumulative reward may not accommodate previously unknown stakeholder preferences. Existing approaches to achieve fairness, a type of preference, in RL typically assume that such preferences are known a priori and require complete retraining of the policy under a fairness-oriented metric. Inspired by inference-time alignment in large language models, we investigate the problem of steering a pretrained RL policy toward welfare-based fairness objectives at inference time without updating the base policy's parameters. We formalize inference-time fairness alignment as a policy shaping problem and propose a multiplicative policy shaping framework that adjusts action probabilities using action-dependent welfare scores, thus requiring no modification to the base policy. Our framework is general and compatible with any deep RL agent. Through extensive experiments across multiple domains, we demonstrate that inference-time policy shaping substantially improves welfare-based fairness objectives while preserving core task performance. --- ### Generative Models for Modeling and Synthesizing MIMO Channels in Adverse Weather Conditions Authors: Vignesh Nandakumar, Faraz Barati, Brian L. Evans Published: 2026-07-31 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2608.00156v2 The push for broader coverage in future cellular networks depends on reliable service, yet this is increasingly harder to do as we encounter more instances of extreme weather conditions. In extreme weather conditions, we have difficulty evaluating coverage due to limited access to channel measurements. In this paper, we generate channel state information (CSI) in low and moderate weather conditions to synthesize realistic MIMO CSI under adverse weather conditions. Our primary contributions are to (1) synthesize MIMO channel datasets incorporating three weather types, each with three intensity levels, representative of practical 5G/6G scenarios; (2) train a diffusion model conditioned on weather using channel samples obtained through conventional pilot-based estimation under low and moderate weather intensities, and subsequently use it to generate channel realizations for severe weather conditions; and (3) evaluate the downlink Bit Error Rate (BER) and Outage Probability measures using the generated channels. The results show that diffusion-based generative models provide a scalable, data-driven alternative for channel modeling in harsh environments and can generalize to severe weather conditions using only low- and moderate-intensity training data. --- ### Generative Models for Modeling and Synthesizing MIMO Channels in Adverse Weather Conditions Authors: Vignesh Nandakumar, Faraz Barati, Brian L. Evans Published: 2026-07-31 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2608.00156v1 The push for broader coverage in future cellular networks depends on reliable service, yet this is increasingly harder to do as we encounter more instances of extreme weather conditions. In extreme weather conditions, we have difficulty evaluating coverage due to limited access to channel measurements. In this paper, we generate channel state information (CSI) in low and moderate weather conditions to synthesize realistic MIMO CSI under adverse weather conditions. Our primary contributions are to (1) synthesize MIMO channel datasets incorporating three weather types, each with three intensity levels, representative of practical 5G/6G scenarios; (2) train a diffusion model conditioned on weather using channel samples obtained through conventional pilot-based estimation under low and moderate weather intensities, and subsequently use it to generate channel realizations for severe weather conditions; and (3) evaluate the downlink Bit Error Rate (BER) and Outage Probability measures using the generated channels. The results show that diffusion-based generative models provide a scalable, data-driven alternative for channel modeling in harsh environments and can generalize to severe weather conditions using only low- and moderate-intensity training data. --- ### AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Authors: Dong Yan, Jian Liang, Dapeng Hu, Ran He, Nicholas Jing Yuan, Qi Zhang, Tieniu Tan Published: 2026-07-31 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00155v2 Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \texttt{Isolated}, \texttt{Sequential}, and \texttt{Interleaved} streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and is non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings. --- ### AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks? Authors: Dong Yan, Jian Liang, Dapeng Hu, Ran He, Nicholas Jing Yuan, Qi Zhang, Tieniu Tan Published: 2026-07-31 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.00155v1 Large language model (LLM) agents can self-evolve by continually improving from their own accumulated experience. However, existing studies predominantly adopt independent evaluation. Consequently, the behavior of self-evolving agents in realistic streaming settings, where agents adapt to diverse and complex task streams, remains poorly understood. To address this gap, we introduce AgentStream, a unified framework that evaluates self-evolving agents spanning diverse evolution components by organizing agentic benchmarks into a configurable task stream and instantiating the \texttt{Isolated}, \texttt{Sequential}, and \texttt{Interleaved} streaming scenarios at test time, which progressively vary the scope and domain composition of the stream. Over these scenarios, we combinatorially evaluate five representative self-evolving methods across three frontier foundation models, disentangling how model capability, method architecture, and streaming scenario jointly shape self-evolution. Our results show that self-evolution reliability varies across streaming scenarios, the benefit of self-evolution is gated by model capability and non-monotonic in model strength, and no single method dominates across models and scenarios. These findings offer concrete guidance for selecting self-evolving methods across models and streaming scenarios. Overall, we advocate that self-evolving agents should be evaluated under realistic task streams rather than isolated single-task settings. --- ### Can We Trust In-Distribution Success? Locked Evaluation Reveals Transfer Failure and Sampling-Depth Entanglement in CRISPRi Perturbation Prediction Authors: Mehrdad Shoeibi, Niloofar Yousefi Published: 2026-07-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.00152v3 AI evaluation can support the wrong inference when an in-domain benchmark success does not survive distribution shift, or when the benchmark endpoint is entangled with a design factor. We study this problem in CRISPRi perturbation-effect prediction, evaluating a frozen Geneformer representation under a locked, pre-registered protocol: heads and model selection were frozen before test evaluation; the protocol required external outcome labels to remain withheld until final unblinding; and analysis-governing decisions were fixed before the evaluations they govern. In-distribution on the Virtual Cell Challenge (VCC), the frozen representation carries measurable predictive information beyond a dimension-matched random-feature control (Delta R^2 = +0.1645, 95% CI (+0.1375, +0.1920)), satisfying the pre-registered informativeness gate required before interpreting transfer. It then fails zero-shot transfer on both external screens (Spearman rho = -0.139 and -0.267), lying below that control on each. Adding a predefined magnitude block improves the representation externally (Delta rho = +0.032 and +0.143) but, under the frozen primary head, does not rescue transfer: both remain negative. A pre-registered, count-adjusted max-response secondary is positively associated with the outcome on both screens; we report it as correlational and secondary, not as a recovered magnitude signal. Finally, the VCC endpoint is strongly sample-size associated: a count-only linear model reaches R^2 = +0.4325, versus +0.2589 for the four magnitude scalars; adding those scalars to cell count improves R^2 by only +0.0017, so much of the aggregate-magnitude signal overlaps with cell count. This case study shows how locking the evaluation, harmonizing the measured endpoint, and separating primary from secondary evidence can change the inference supported by an AI benchmark. --- ### Response Magnitude as a Dominant Signal for Held-Out CRISPRi Perturbation Effect Prediction Authors: Mehrdad Shoeibi, Niloofar Yousefi Published: 2026-07-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.00152v1 Predicting the magnitude of a CRISPRi perturbation's transcriptomic effect on held-out target genes is an important open problem in single-cell biology. Recent work has documented that simple baselines often match or exceed deep perturbation predictors on related protocols. We study this phenomenon on the Virtual Cell Challenge (VCC) benchmark under a strict held-out target-gene split, identify the specific low-dimensional signal that drives the gap, and characterize how it transfers across cell types. The target is the log Anderson-Darling distance from non-targeting controls, which is strongly predictable from four deterministic scalar functions of the 2,000-dimensional input. A deep MLP encoder with direct access to the full input collapses toward the marginal training mean, and standard remedies do not close the gap. A linear regression on the four magnitude scalars alone exceeds the strongest x-only classical model, while a Random Forest on the input plus the four scalars substantially outperforms our deep proof-of-concept encoder. Two pre-specified controls attribute the magnitude gain to per-row alignment rather than added dimensionality. Under zero-shot transfer to two external CRISPRi screens evaluated against a target-gene endpoint rebuilt from single-cell data, magnitude-only predictors transfer positively whereas expression-only predictors are negative or unresolved. Exposing magnitude to the deep encoder improves transfer over its expression-only counterpart, yet the encoder does not outperform a four-scalar linear regression on the same features. We also find that the Anderson-Darling column distributed with these screens measures transcriptome-wide response breadth rather than target-gene effect strength, so evaluating transfer against it scores a different outcome. --- ### Optimising for Flourishing: Flourishing Metrics and Return on Flourishing as Success Criteria for Artificial Intelligence and Post-AGI Economic Systems Authors: Keyun Ruan, Jonathan D. Teubner, John M. Bremen Published: 2026-07-31 Categories: cs.CY, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2608.00151v2 Current evaluation frameworks for artificial intelligence focus mainly on capability, safety, and proxies such as adoption, engagement, efficiency, productivity, and financial return. These criteria are necessary but insufficient because they do not establish whether increasingly powerful systems improve or degrade human and planetary well-being. Through an integrative conceptual synthesis, we argue that human flourishing should serve as a primary success criterion for artificial intelligence, the global race to develop increasingly capable AI systems, and prospective post-AGI economic systems. We make three contributions. First, Flourishing Metrics provides an extensible framework spanning physical, emotional, financial, relational, spiritual, and planetary well-being, combining validated subjective measures with representative behavioural, organisational, community, and environmental indicators. Second, Return on Flourishing (RoF) extends return on investment by evaluating the counterfactual contribution of interventions, policies, and AI systems to flourishing relative to their resources, risks, and opportunity costs. Third, we develop distribution-sensitive safeguards and show how RoF could guide AI-enabled work redesign, institutional appraisal, assurance, and post-deployment monitoring through business pilots. We formalise flourishing as a dynamic system variable while emphasising the need for democratic specification, empirical calibration, independent validation, and protection against unacceptable losses within particular dimensions or stakeholder groups. RoF is proposed not as a universal reward function, but as a value-accounting and decision architecture for assessing whether intelligence, automation, and economic transformation generate durable human and planetary progress. ---