# Research Papers — 2026-10 · bundle page 66 of 156 > Full-text markdown of papers #3251–3300 of 7799 published in 2026-10, newest first. AI-readable mirrors of the full 7799-paper 2026-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-10/page/66 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/65.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/67.md) ### Beyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification Authors: Yuan Liang, Sourav Bhattacharjee, Abraham Campbell Published: 2026-10-09 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.14152v1 Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contributions at the classifier output. We investigate this distinction in a fixed 3D MedVAE--radiomics model for clear cell versus non-clear cell renal cell carcinoma classification from contrast-enhanced CT. Because the model uses a linear classification head, the binary decision logit can be decomposed exactly into a gated image term, a direct radiomics term, and a bias. We define effective radiomics dominance as the direct radiomics term's share of the summed absolute non-bias branch contributions and compare it with structural radiomics weighting. Internally, mean structural radiomics weighting was 0.823, whereas mean effective radiomics dominance was 0.148, with a modest case-wise association (\r{ho} = 0.290). The gated image term retained substantially stronger discriminative ranking information than the direct radiomics term. The same structural-to-effective discrepancy was observed in exploratory external evaluation. Branch-targeted permutation, integrated-gradient, and Shapley-style analyses further identified radiomics descriptors influencing the direct radiomics term. Because radiomics also generates the gate, the gated image term remains radiomics-dependent, so additive branch contribution should not be interpreted as total input influence. These findings show that structural gate weighting and decision-level branch contribution represent distinct aspects of gated feature fusion and should be interpreted separately. --- ### Beyond Discrimination: Evaluating Probability Calibration in Radiomics-Image Fusion for Renal Cell Carcinoma Classification Authors: Yuan Liang, Morgan May, Abraham Campbell, Sourav Bhattacharjee, Simon Caton, Pierpaolo Dondio Published: 2026-10-09 Categories: eess.IV, cs.AI, cs.CV, q-bio.QM arXiv: https://arxiv.org/abs/2610.14151v1 Reliable probability estimates are important for the clinical interpretation of machine-learning classifiers, yet radiomics--image fusion models for renal cell carcinoma (RCC) are commonly evaluated primarily by discrimination. Using 396 patients from the KiTS23 dataset, we evaluated whether adding radiomics to four image-model families improved probabilistic performance in addition to discrimination. Seventeen individual models and four probability-average ensembles were assessed using discrimination, probability calibration, and proper scoring measures. Across 12 matched image-only versus fusion comparisons, AUC and AP improved in all 12, while Brier score and negative log likelihood (NLL) improved in 11 of 12 and expected calibration error (ECE) in eight of 12. The 3D MedVAE gated-fusion model achieved the strongest overall individual-model profile. Probability averaging across concatenation, cross-attention, and gated fusion produced favourable point estimates across all five primary metrics relative to image-only models in all four families, although paired-bootstrap support was stronger for Brier score and NLL than for ECE. These findings show that radiomics--image fusion can improve probabilistic prediction quality beyond discrimination, while calibration behaviour varies across image architectures and fusion strategies. We show that our proposed probability-average ensemble models improve discrimination and calibration simultaneously across all architectures in the study. --- ### VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation Authors: Katherine J. Koebel, Renata Ivanek, Parminder Basran, Jennifer Sun, Casey Cazer, Gayatri Anil, Tommaso Banzato, Liz Barton, Dottie Cimino Brown, Leszek Bukowski, Marta Castelhano, Simon Coghlan et al. Published: 2026-10-09 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2610.14149v1 VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine through standardized, high-quality datasets and multi-institutional collaboration across academic and non-academic sectors. This framework addresses the gap between AI advances in human medicine and the fragmented state of veterinary AI development. --- ### Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress Authors: Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu et al. Published: 2026-10-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.14146v1 Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary check. We present Long-Horizon-Terminal-Bench 2.0 (LHTB 2.0), an extension of Long-Horizon-Terminal-Bench that preserves its 46 original tasks while correcting task and evaluation-infrastructure defects and extending 31 tasks. LHTB 2.0 contains 77 tasks across 13 domains and eight task types. The extended tasks are produced through a systematic reconstruction-task pipeline. We start from a working scientific or engineering artifact, then use a parameterized reference implementation to generate multiple scenarios, reveal six as behavioral evidence, hold out three for evaluation, and use dense progress ladders to reward partial progress while preventing memorization of public outputs. We also extend the evaluation horizon from 90 minutes to three hours and record verifier checkpoints every 30 minutes, enabling direct measurement of sustained progress within a run. Across 1,145 scored model-task runs from 15 frontier models, GPT-6-astra leads with dense mean reward 0.69 and 37 tasks at R at least 0.95, followed by GPT-5.6-sol with dense mean reward 0.67 and 32 tasks at the same threshold. On the 30 reconstruction tasks, binary verifier scores average 0.221, whereas dense ladder scores average 0.653, showing that outcome-only evaluation discards substantial intermediate progress. LHTB 2.0 provides a broader, hardened, and process-aware testbed for studying reliable agent execution over hours. --- ### C$^2$LUE: Clinically Aligned Patient-Level Ultrasound Diagnosis via Evidence-Aware Multi-Instance Learning Authors: Qin-Yi Zhang, Linying Cao, De-Xing Huang, Haichuan Lin, Yi Yang, Manzhi Wang, Xiao-Hu Zhou, Chen Chen, Shuangyi Wang, Zeng-Guang Hou Published: 2026-10-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.14143v1 Patient-level ultrasound diagnosis demands not only high predictive accuracy but also clinically aligned mitigation of asymmetric diagnostic risks. While Multi-Instance Learning (MIL) effectively models routine multi-view exams, standard aggregators often dilute heterogeneous diagnostic cues and optimize solely for global accuracy. This frequently yields undesirable sensitivity-specificity trade-offs. To bridge this gap, we propose C$^2$LUE, a novel MIL framework coupling evidence aware aggregation with risk-aligned regularization. To preserve evidence heterogeneity and prevent unimodal attention collapse, C$^2$LUE employs a multi-query cross-attention mechanism built upon a LoRA-adapted DINOv3 backbone. Multiple latent queries explicitly extract and disentangle diverse morphological patterns from the ultrasound sequence. Furthermore, to improve clinical risk alignment, we introduce a dynamic trade-off regularization objective that penalizes sensitivity-specificity imbalance during training. Rather than leaving the clinical trade-off entirely to post-hoc threshold adjustment, this objective encourages the learned score distribution toward a more balanced operating region. Extensive evaluations on patient-level, biopsy-proven thyroid and breast ultrasound datasets demonstrate that C$^2$LUE consistently outperforms prior alternatives. By uniting strong discrimination with a balanced error profile, C$^2$LUE provides a promising solution for real-world ultrasound screening and diagnosis. --- ### Frozen Site-Probe Accuracy Is Not a Standalone Harmonization Score: An Audit of Evaluation Practice for Multi-Site MRI Authors: Muhammad Muqsit Islam, Gloria García Cuenco, José M. Martínez, Pierrick Coupé Published: 2026-10-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.14140v1 Image-level MRI harmonization is often evaluated with a frozen site probe, a site classifier trained on raw scans and applied unchanged to harmonized ones: a drop in its accuracy is read as removal of site effects. We audit this practice on ABIDE I (1,112 T1-weighted scans, 17 sites) with ten output sets from seven harmonization methods and controls for chance, head shape, intensity, preprocessing and target alignment. We find that this verdict depends on how the probe is trained, even among probes that classify raw scans well: across random seeds, its balanced accuracy on the same CycleGAN outputs ranges from 0.13 to 0.59 (chance: 0.06). Low frozen-probe accuracy can also arise without harmonization: a Gaussian blur, which increases the intensity distance to the target site, lowers this accuracy to chance. Moreover, where the frozen probe fails, probes trained on the harmonized scans still recover the site, even from intensity histograms alone: on HACA3 outputs, the frozen probe scores 0.25, a probe trained on those outputs 0.75, and one using only their intensity histograms 0.71. Low frozen-probe accuracy therefore does not show that site information has been removed. We recommend reporting several probes trained to convergence, probes trained on harmonized scans, and target alignment. --- ### Exploring the Latent Structure of AMD Severity Using Retinal Foundation Models Authors: Niccolò Fineschi, Jovana Panic, Atsushi Watanabe, Hideaki Hayashi, Kazuya Nishimura, Yuki Maeno, Samanta Rosati, Gabriella Balestra, Kohji Nishida, Hajime Nagahara Published: 2026-10-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2610.14138v1 Retinal foundation models have demonstrated strong performance across a wide range of ophthalmic tasks, yet relatively little is known about how disease-related information is represented within their learned embeddings and whether this distribution influences downstream prediction performance. In this work, we use Age-related Macular Degeneration (AMD) as a case study to investigate how disease severity is represented within the embedding space of RET-CLIP, a retinal vision-language foundation model, using bilateral fundus images from the AREDS dataset, benchmarked against non-retinal encoders. We first characterize the distribution of AMD severity within the learned representation space and then evaluate how this structure influences classification performance across three clinically relevant task formulations of increasing granularity. Finally, we analyze the most influential latent dimensions combining feature attribution, statistical phenotype association, and qualitative image analyses. Our results show that RET-CLIP represents AMD severity as a continuous spectrum rather than a set of discrete categories, with healthy and advanced disease stages exhibiting clearer separation than intermediate ones. This organization was reflected in downstream performance, which decreased from a balanced accuracy of 0.844 and 0.814 for binary AMD and Late-AMD detection respectively to 0.446 for six-class grading. Furthermore, the most influential latent dimensions were statistically associated to distinct retinal phenotypes, including drusen accumulation, pigmentary alterations, and advanced retinal lesions. These findings suggest that the structure of retinal foundation-model representations influences the difficulty of clinically relevant prediction tasks and demonstrate the potential of representation-level analysis for understanding disease organization and improving interpretability. --- ### Correction Training for Diffusion Models Authors: Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe Published: 2026-10-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.14136v2 Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier steps, something it has never seen at training time. This might be one reason diffusion models often struggle without additional help, such as CFG. We introduce a correction step for diffusion models which attempts to reduce this training-inference gap. The corrector takes the base model's prediction as input and is trained against the same ground-truth target. This makes correction an explicit learning task, with training inputs provided by the base model. During sampling, at each denoising step, we iteratively refine the denoiser's clean-sample prediction. This allows us to correct predictions at intermediate denoising steps, preventing early artifacts from persisting into the final sample. Although the corrector is trained only on predictions from the base denoiser, it can be applied repeatedly to its own outputs at inference for better results. This simple framework leads to substantial improvement in sample quality while largely preserving diversity. We evaluate our method across DiT, SiT, and JiT. Our method substantially improves upon previously reported FID scores for unguided generation and, notably, unconditional generation, where producing high-quality samples without guidance has been particularly challenging. Our method achieves performance competitive with classifier-free guidance (CFG), and combining correction with CFG further improves diversity and reduces oversaturation typical of CFG. Finally, we show that the additional inference cost of correction can be amortized by distilling the refined predictions back into the base diffusion model, retaining the quality gains without additional inference-time overhead. --- ### A Stochastic Analysis Perspective on Diffusion Models Authors: Stanislas Strasman Published: 2026-10-09 Categories: stat.ML, cs.LG, math.PR arXiv: https://arxiv.org/abs/2610.14133v1 Generative modelling involves two complementary tasks: learning a probabilistic approximation of an unknown data distribution from observations, and designing a tractable mechanism for sampling from this approximation. We present a stochastic-analysis perspective on score-based generative models, connecting ideas from classical sampling theory, score estimation, and diffusion time reversal. We first explain how score functions link Langevin sampling with score matching, and how Gaussian smoothing leads to denoising score matching and multiscale sampling methods. We then emphasize the distinction between dynamics preserving a fixed distribution and dynamics transporting a prescribed family of marginals. This motivates a path-space treatment of diffusion time reversal. Finally, we connect the ideal reverse diffusion with practical generative algorithms. --- ### On physical implementability of reinforcement-learning-driven reasoning Authors: Eiji Konishi Published: 2026-10-09 Categories: cond-mat.dis-nn, cs.LG arXiv: https://arxiv.org/abs/2610.14131v1 In the machine learning community, the reinforcement-learning-driven reasoning process has been intensively studied since around 2025. In this article, we present a negative result on the hardware implementation of this reinforcement-learning-driven reasoning process in a physical neural network model in the presence of a reward external potential energy for a given reward. In this hardware implementation, the existence of a chain of thought in dynamics contradicts the Lyapunov stability of the system. --- ### The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations Authors: Ilia Frantzi, Bernie Hogan, Max M. Lang, Paul C. Bauer Published: 2026-10-09 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2610.14124v1 As interactions with large language models (LLMs) become increasingly routine, concerns about their capacity to influence users' beliefs grow. Yet how such influence unfolds in sustained dialogue remains insufficiently understood. We conduct a randomized controlled experiment (N=616) where participants engage in multi-turn, spoken dialogue with an LLM under three conditions: non-directive, and two directive conditions maintaining opposing stances on a polarizing topic (the merits of feminism). We examine opinion change, rhetorical strategies, and sycophancy, distinguishing the semantic content of LLM argumentation from the pragmatic strategies used to manage the interaction. Both directive conditions shifted opinions toward their assigned stances, but asymmetrically: shifts were larger for pro-feminist positions, which also elicited distinct rhetorical strategies. The non-directive condition, likewise shifted opinions pro-feminism. Social sycophancy, though near-universal, was not associated with opinion change; instead it shaped users' subjective experience. Our findings highlight distinct roles for argumentation and sycophantic accommodation in AI influence. --- ### Hierarchical Multi-Agent Reasoning Systems for Knowledge-Grounded Material Substitution Authors: Tarjei Paule Hage, Subhadeep Pal, Wei Lu, Yu-Chuan Hsu, Gayla Lyon, Jiezhu Jin, Markus J. Buehler Published: 2026-10-09 Categories: cond-mat.mtrl-sci, cond-mat.mes-hall, cs.LG arXiv: https://arxiv.org/abs/2610.14123v1 AI-assisted scientific discovery increasingly seeks to move beyond generating plausible ideas toward reproducible, constraint-aware workflows that can support practical engineering decisions. We present MARS, a hierarchical Multi-Agent Reasoning System for knowledge-grounded material substitution under scientific and manufacturing constraints. We apply MARS to replace per- and polyfluoroalkyl substances (PFAS), a demanding materials-design problem in which substitutes must satisfy functional performance, environmental, experimental, and processing requirements. MARS decomposes substitution into a closed-loop workflow comprising requirement analysis, grounded candidate generation, and manufacturability assessment with process design. The system integrates retrieval-augmented generation, knowledge-graph reasoning, a database of lab-available materials, persistent memory of intermediate results, and rejection-aware iterative feedback. In a PFAS-substitution case study, MARS generates structured material requirements, identifies an evidence-grounded substitute candidate, and develops a lab-scale manufacturing route. In a multi-seed ablation evaluation, MARS achieves the highest overall performance across all three subsystems, with gains that persist when the backbone model is held fixed. These results suggest that hierarchical decomposition, knowledge grounding, and manufacturability-aware refinement improve material-substitution reasoning beyond model capability alone. --- ### Early Detection of Pension-Sponsor Distress from Public Filings: A Sponsor Vulnerability Index, Stress-Augmented VaR, and Dynamic Self-Investment Caps Authors: Ravil Akhtyamov Published: 2026-10-09 Categories: q-fin.RM, cs.LG arXiv: https://arxiv.org/abs/2610.14120v1 A defined-benefit pension is only as safe as its sponsor, yet sponsor distress is under-instrumented relative to plan-side modelling. We present a transparent, reproducible early-warning pipeline built entirely on public data. A Sponsor Vulnerability Index (SVI), a gradient-boosted classifier over point-in-time SEC EDGAR balance-sheet fundamentals and two macro series, predicts a filings-based distress state one to two quarters ahead. On 36 U.S. sponsors in five sector groups (1,418 firm-quarters, 2015Q1-2025Q3) it reaches an out-of-fold AUC-ROC of 0.887 and PR-AUC of 0.711 (base rate 11.9%) under leave-one-firm-out cross-validation. A Monte Carlo VaR with a stylized transition-stress overlay shows that climate-type stress is negligible for a diversified plan but adds 20-43% to one-year 95% VaR when 22.5% of assets are held in sponsor securities. A dynamic self-investment cap maps the SVI to a limit that falls from 8% to below 1% in acute distress and recovers with the sponsor, which we illustrate on PG&E's 2019 bankruptcy and Boeing's persistent fragility. We report the method's failure modes alongside its results (book-equity labels that also fire on non-credit events such as spin-offs, positives concentrated in one firm, and stylized stress parameters) and release code, data and results under a concept DOI. --- ### ClawLoop: Self-Improving Agents via Harness-Native Training Loop Authors: Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai Published: 2026-10-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.14118v1 The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both agent-free and agent-based task validation; Training, which updates the agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the agent's rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and ClawGym-Bench. The iteratively refined tasks are further transferred to smaller-scale Qwen3.5-4B and 9B models with gains across all benchmarks, validating data quality independently of the loop model. --- ### The Silent Failures in Agentic Data Science Authors: Xue Li, Hongqian Xia, Daniel Gomm, Aécio Santos, Cornelius Wolff, Madelon Hulsebos Published: 2026-10-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.14115v1 Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines. --- ### Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages Authors: Romi Fadli, Rusdah, Wahyu Ramadani Putri Utami, Zulfa Malika Amana Published: 2026-10-09 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.14112v1 Calibrated typed-decision ("System One") models return a label and a probability in a single forward pass at a small fraction of the cost of large language models (LLMs), yet their evaluation has been almost entirely English. We report a pre-registered evaluation of the commercial Jev model and the open Laya-multilingual model on Indonesian regional languages, using the parallel NusaX sentiment (12 languages) and NusaTranslation sentiment and emotion (7 languages) test sets. Jev is more often correct on sentences that are lexically closer to Indonesian in all three datasets, and presenting the human Indonesian translation instead raises its accuracy by up to 37.2 points, most in languages distant from Indonesian. Its expected calibration error does not grow on regional languages, but its ability to rank its own errors degrades in all three datasets. Retrained classifiers need more than 500 labels per language to match zero-shot Jev in 9 of 10 NusaX regional languages. A confidence-gated cascade that sends Jev's 10-30% least confident decisions to a local IndoBERT classifier matches or exceeds the better of the two systems, and routing to an LLM instead matches that LLM at 24-77% lower API cost. Of six further commercial LLMs (three Claude and three GPT models), five are 4-14 points more accurate than Jev, at several hundred times the API cost where it is reported, while the smallest (Claude Haiku) is less accurate. We release the pre-registration, code and all predictions. --- ### Can Language Models Play the Wikipedia Game? Authors: Alexander Hickey, Joanna Knight, James Bishop Published: 2026-10-09 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.13948v1 Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test language models on an analogous information retrieval task. In the game, players must reach a target article using only article links. We compared sentence embedding models and LLMs across five Wikipedia languages and five academic-literature datasets. We construct very large local graphs of Wikipedia pages and of paper citations using OpenAlex and provide code to build and navigate them. This allows the study of language models' navigation capabilities without relying on third-party APIs. We compared the models with human and TF-IDF benchmarks. The Wikipedia Game format enables robust comparisons across techniques, languages, and domains. No model significantly outperformed humans, although the best models (GPT-o3 mini, GPT-4o, QwQ:32B, and DeepSeek-R1:70B) achieved comparable success. Performance and rankings varied across languages and topics, with implications for practitioners utilising these techniques. --- ### Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark Authors: Xudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li, Marc Pollefeys, Shangzhe Wu, Andrea Vedaldi, Chuanxia Zheng Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13947v2 In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets. --- ### Towards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and Benchmark Authors: Xudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li, Marc Pollefeys, Shangzhe Wu, Andrea Vedaldi, Chuanxia Zheng Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13947v1 In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets. --- ### Splat2Act: From Captured Scenes to Personalized VLA Manipulation Authors: Xiaomeng Ye, Krishna Jaganathan, Gyubeum Lim, Gunjan Chhablani, Muhammad Zubair Irshad, Zsolt Kira Published: 2026-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.13945v1 A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables. Yet even a strong generalist like $π_{0.5}$ achieves 0% pickup success in our captured deployment scenes without adaptation, and collecting real demonstrations in every user's environment is prohibitively expensive. We present Splat2Act, an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objects. Unlike prior real-to-sim work that reconstructs individual tabletops, Splat2Act operates on building-scale indoor environments: it builds a photorealistic digital twin with 3D Gaussian Splatting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,000 pickup demonstrations. We fine-tune $π_{0.5}$ in two stages: Stage 1 adapts to hundreds of public object assets, drawn either from the deployment scene alone or from all 101 scenes; Stage 2 personalizes to the user's own objects on the deployment scene's receptacles. Our strongest personalized policy reaches 62.5% aggregate pickup success in the target scene. Deployed on a real Stretch 3, the same policy achieves 63.9% success on a 12-task subset, closely tracking its 66.7% simulated success on those tasks. These results suggest that automated real-to-sim-to-real training can personalize VLA manipulation policies using only simulation-oracle data. --- ### InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators Authors: Xuanlang Dai, Jiazi Bu, Yujie Zhou, Yuhong Liu, Beichen Zhang, Penghui Yang, Ziyu Liu, Yuhang Zang Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13944v2 Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilities, the cross-model alignment of latent representations and the consistency of their underlying denoising dynamics remain underexplored. In this work, we uncover an intriguing cross-model compatibility: independently trained generators exhibit similar latent spatial organization, while directly handing off intermediate states between unaligned models can still preserve coarse visual content. Motivated by these observations, we propose InstantFusion, a lightweight shared latent interface that connects the denoising trajectories of heterogeneous image generators. Specifically, to enable flexible cross-model state translation, model-specific Latent AutoEncoders (LAEs) are introduced to project intermediate states from different generators into a shared latent space and decode them into the latent space of a target generator. This shared space is constrained by two complementary objectives: aligning intermediate states derived from the same image at matched noise levels and synchronizing their corresponding local denoising velocities. Once trained, InstantFusion allows denoising to seamlessly transition across frozen generators without requiring a dedicated mapping for every model pair. The versatility of InstantFusion is demonstrated across acceleration, multi-preference composition, cross-architecture on-policy distillation, and cross-model composition, achieving competitive performance across these diverse settings. --- ### InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators Authors: Xuanlang Dai, Jiazi Bu, Yujie Zhou, Yuhong Liu, Beichen Zhang, Penghui Yang, Ziyu Liu, Yuhang Zang Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13944v1 Diffusion/flow models have emerged as the de facto paradigms for image generation, giving rise to a diverse family of modern generators with increasingly heterogeneous architectures and representations. Despite their remarkable generation capabilities, the cross-model alignment of latent representations and the consistency of their underlying denoising dynamics remain underexplored. In this work, we uncover an intriguing cross-model compatibility: independently trained generators exhibit similar latent spatial organization, while directly handing off intermediate states between unaligned models can still preserve coarse visual content. Motivated by these observations, we propose InstantFusion, a lightweight shared latent interface that connects the denoising trajectories of heterogeneous image generators. Specifically, to enable flexible cross-model state translation, model-specific Latent AutoEncoders (LAEs) are introduced to project intermediate states from different generators into a shared latent space and decode them into the latent space of a target generator. This shared space is constrained by two complementary objectives: aligning intermediate states derived from the same image at matched noise levels and synchronizing their corresponding local denoising velocities. Once trained, InstantFusion allows denoising to seamlessly transition across frozen generators without requiring a dedicated mapping for every model pair. The versatility of InstantFusion is demonstrated across acceleration, multi-preference composition, cross-architecture on-policy distillation, and cross-model composition, achieving competitive performance across these diverse settings. --- ### Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback Authors: Yucheng Yang, Xiaoxiao Sun, Shusheng Yang, Jiakang Chen, Serena Yeung-Levy Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13941v2 Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about $1.2\times$ the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from $0.6661$ to $0.7479$; on SD3.5M, iSFG adds $+1.33$ HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at https://github.com/yyc1215lll-creator/SFG. --- ### Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback Authors: Yucheng Yang, Xiaoxiao Sun, Shusheng Yang, Jiakang Chen, Serena Yeung-Levy Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13941v1 Multimodal diffusion transformers (MMDiTs) allow the evolving image to update internal text representations through joint attention. These representations then guide subsequent image updates, raising a question: does this feedback help correct deviations from the prompt, or preserve them? We find that image-to-text (I2T) feedback can preserve the objects and attributes already represented in the evolving image, including errors. Transplanting I2T messages can rescue failures or disrupt successes. At matched intervention strengths, suppressing the influence of I2T feedback improves generation, whereas opposite controls degrade it. These findings motivate Semantic Feedback Guidance (SFG), which suppresses the influence of I2T feedback by guiding away from an auxiliary branch that strengthens this feedback and weakens text-to-image conditioning. The in-place variant, iSFG, directly suppresses I2T feedback and strengthens text-to-image conditioning, requiring no extra model evaluations. Temporal interventions motivate running the SFG branch during the first 20% of image sampling steps, requiring about $1.2\times$ the base NFE without classifier-free guidance (CFG). Experiments across three image-generation backbones show gains in alignment and preference-model scores. On FLUX, adding SFG to CFG raises GenEval from $0.6661$ to $0.7479$; on SD3.5M, iSFG adds $+1.33$ HPSv2.1 over CFG at zero extra NFE. The control also transfers to text-to-video and image-to-video generation, improving VBench scores. Code is available at https://github.com/yyc1215lll-creator/SFG. --- ### Hide and Seek: HIDE Concepts to SEEK explanations for black box models Authors: Bhanu Tokas, Rahul Nair, Rockwell Jackson, Hannah Kerner Published: 2026-10-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.13935v3 Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model weights or large concept-annotated datasets, and most methods cannot provide image-level attribution. We propose Hide and Seek (HnS), a new method for concept-level attribution that does not require access to model weights or labeled concept datasets. HnS can interpret a wide range of vision models. Given a concept and image set, HnS retrieves concept-aligned images using a vision-language model, localizes the concept within each image, masks the localized region, and measures attribution from the change in the black-box model's output between the original and masked images. This enables faithful attribution by directly measuring the model's behavior and supporting local attributions. We validated HnS on CelebA and COCO-Stuff. Compared to existing methods, HnS showed better agreement with ground-truth attributions. We demonstrated the applicability of HnS on diverse tasks, including image captioning and satellite image segmentation, where no existing concept attribution method can be used. We provided our anonymous code in the supplementary material. --- ### Hide and Seek: HIDE Concepts to SEEK explanations for black box models Authors: Bhanu Tokas, Rahul Nair, Rockwell Jackson, Hannah Kerner Published: 2026-10-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.13935v1 Interpreting machine learning model predictions is a central challenge, particularly for black-box vision models. Concept-based attribution methods interpret models using human-understandable concepts. Existing concept-based methods can only interpret classification and regression models. They require access to model weights or large concept-annotated datasets, and most methods cannot provide image-level attribution. We propose Hide and Seek (HnS), a new method for concept-level attribution that does not require access to model weights or labeled concept datasets. HnS can interpret a wide range of vision models. Given a concept and image set, HnS retrieves concept-aligned images using a vision-language model, localizes the concept within each image, masks the localized region, and measures attribution from the change in the black-box model's output between the original and masked images. This enables faithful attribution by directly measuring the model's behavior and supporting local attributions. We validated HnS on CelebA and COCO-Stuff. Compared to existing methods, HnS showed better agreement with ground-truth attributions. We demonstrated the applicability of HnS on diverse tasks, including image captioning and satellite image segmentation, where no existing concept attribution method can be used. We provided our anonymous code in the supplementary material. --- ### Constructive Bounds for the Topological Expressivity of Neural Networks Authors: Kosio Beshkov Published: 2026-10-09 Categories: math.AT, cs.LG arXiv: https://arxiv.org/abs/2610.13931v1 The expressivity of a neural network $Φ$ describes the class of functions that a network can express. The term topological expressivity refers to a family of measures particularly suited to understand binary classification and is often formulated in terms of the Betti numbers of a decision boundary $β(Φ^{-1}(0))$. Despite its popularity, this measure is not as useful for regression and other problems that do not involve a decision boundary. Instead, we propose to study topological expressivity in terms of the Betti numbers of the output of a neural network $β(Φ(X))$. We formally prove that a ReLU network with architecture $(d,\sum\limits_{k=1}^{d } β_k(3k+2),\sum\limits_{k=1}^{d}β_k(k+1))$ can express spaces homotopy equivalent to wedge sums of spheres with arbitrary Betti numbers. This gives upper bounds for any arbitrary connected ($β_0=1$) sequence of Betti numbers, but by constructing spaces homotopy equivalent to products of $N$ spheres of dimension $d_1,...,d_N$ we achieve much better bounds $(\sum\limits_{n=1} d_n, 3\sum\limits_{n=1}\limits^N d_n + 2N, \sum\limits_{n=1}\limits^N d_n + N) $ for Betti numbers given by $\prod_n (1+x^{d_n})$. Finally we conjecture a much stronger tight bound which gives the architectural bound $(d,d+1,d+1)$ for a space homeomorphic to the sphere. --- ### Chronos Policy: Learning Robot Policies on Physical Time Authors: Changhao Wang, Jaden Clark, Shuran Song Published: 2026-10-09 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.13929v1 Robot policies often convert sensing and control into fixed-rate observation-action sequences, leaving physical time implicit in sequence position. This assumption breaks when observation rates or delays vary, or when inference latency changes. We introduce Chronos Policy, which makes physical time explicit by conditioning on observation capture times and desired action execution times. We study two ways to incorporate time into a diffusion transformer: adding timestamp embeddings to token features, or encoding physical time in positional encoding through time-aware rotary positional encodings (time-aware RoPE). We find that time-aware RoPE is more robust, allowing attention to depend directly on physical time while keeping token content unchanged. During training, we temporally randomize which observations are sampled and when the action chunk begins, exposing the policy to a wider range of sensing and execution schedules that may occur during deployments. This also enables learning from asynchronous, multi-rate data without forcing all measurements onto a fixed temporal grid. Across simulation and real-world experiments, Chronos Policy improves performance on dynamic tasks, where observation-to-action timing is critical, and on multisensory tasks, where the relative timing between observations matters. On standard quasi-static tasks, it preserves nominal performance while improving robustness to changes in sensing and inference timing. --- ### AI Models Can Provably Hide Arbitrary Capabilities Authors: Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas, Christian Schroeder de Witt Published: 2026-10-09 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.13928v2 Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training, using a small chemical reaction prediction task as a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses. --- ### AI Models Can Provably Hide Arbitrary Capabilities Authors: Andis Draguns, Sumeet Ramesh Motwani, Raymond Douglas, Christian Schroeder de Witt Published: 2026-10-09 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2610.13928v1 Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. We show this assumption does not hold under adversarial conditions by constructing backdoor attacks that embed encrypted neural networks within host model weights, decrypting and executing them only upon receiving a secret trigger. Using digital lockers, these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights, extending prior work from hiding fixed strings to arbitrary computations. We implement our proof of concept constructions in PyTorch and evaluate elicitation through fine-tuning, weight noising, gradient-based trigger search, and latent adversarial training on a small chemical reaction prediction task - a proxy for CBRN-relevant capabilities. Our results demonstrate resistance to these methods and, together with our cryptographic guarantees, reveal a limit of elicitation-based capability audits. We release our models to support the improvement of defenses. --- ### Can machines reason non-verbally? Authors: Shaheer U. Saeed, Zion Tse, Gregory Slabaugh, Daniel C. Alexander, Yipeng Hu Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13925v1 Modern machines can solve equations, follow logic and reason through language, yet they still struggle with problems that require visual non-verbal reasoning. This is evident even in advanced systems such as DeepSeek, ChatGPT and Gemini, which remain limited on visual tasks such as completing abstract patterns or delineating ambiguous regions-of-interest. Unlike explicit intermediate steps in verbal reasoning which can be verified through logic or automated tests, visual reasoning involves implicit intermediate steps with no clear methods for verification. Non-verbal reasoning is therefore challenging to model and, as a result, remains a fundamental limitation of current machine intelligence. Here we introduce GenVerOpt, a general framework that unifies generation, verification and optimisation into a reasoning pipeline for machines. By generating candidate solutions, verifying their correctness, and iteratively refining them, GenVerOpt enables per-sample optimisation rather than relying solely on dataset-level trends captured during model training. This process mirrors human problem-solving where multiple possibilities are imagined, evaluated, and refined until a correct solution emerges. Across diverse domains, GenVerOpt demonstrates capabilities beyond existing systems: it surpasses humans on abstract IQ puzzles, matches clinicians in prostate cancer segmentation, exceeds experts in liver vessel reconstruction and outperforms state-of-the-art approaches in tumour boundary alignment. These results show that machine reasoning can extend beyond language, establishing visual non-verbal reasoning as a foundation for more flexible and generalisable intelligence. --- ### KL Before and After Mixing: A Round-Complexity Separation in Parallel Sampling Authors: Tianyi Wu Published: 2026-10-09 Categories: cs.LG, cs.IT arXiv: https://arxiv.org/abs/2610.13924v1 A parallel sampler can choose at random which coordinates to generate together. For a target $p$ and the output law $q_U$ of a schedule $U$ drawn afresh for each output, we compare the schedule-averaged divergence $\mathbb{E}_U D_{\mathrm{KL}}(p\|q_U)$ with the output-law divergence $D_{\mathrm{KL}}(p\|\mathbb{E}_U q_U)$, in nats. Rounds commit independent draws from exact conditional marginals frozen at the round's start, each output's schedule is drawn before sampling from a finite mixture of schedules, and every scheduled round is charged. For the uniform distribution on binary strings of even length $n$ with $n/2$ ones, the least expected number of rounds at a fixed tolerance $\varepsilon>0$ is $Θ_\varepsilon((\log n)^2)$ under the first criterion but $(e^{-\varepsilon}+o(1))\log_2\ln n$ under the second, and the double-logarithmic order is attainable with the same round count on every run. For this target, a count-state recursion gives the exact least output divergence at every round cap over all causal randomized policies. The separation extends to weighted fixed-count targets with bounded weight ratios and quota fractions bounded away from zero and one, without permutation symmetry, and to the full-support Beta$(1,1)$--Bernoulli target, where the sharp expected cost under the output-law criterion is $(e^{-\varepsilon}/2+o(1))\log_2\log_2n$, attained with rare $n$-round runs. Prior work implies the order of the schedule-averaged cost on the balanced target and its $O_\varepsilon((\log n)^2)$ upper bounds on both extensions. --- ### Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning Authors: Sajjad Baghaee, Aimin Li, Shanmugarajan Balasubramanian, Elif Uysal Published: 2026-10-09 Categories: cs.NI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2610.13923v1 Deep-space communications operate under intermittent connectivity, long propagation delays, and relay storage constraints. In such networks, the Bundle Protocol enables store-carry-forward communication, requiring relay nodes to manage limited storage and scarce contact opportunities. Relay-side scheduling and dropping decisions are inherently goal-oriented: transmission resources should be allocated to bundles most valuable to downstream mission objectives. Conventional schedulers, such as FIFO, do not explicitly optimize task utility and may provide unfair service across heterogeneous planetary sources. This paper presents a closed-loop modeling and learning framework for relay-side bundle and flow management in a contact-driven deep-space network, where lunar and Martian updates are forwarded through a shared-buffer relay to Earth. We quantify destination-side information freshness using excess age $Δ_i^e(t)=(Δ_i(t)-d_i(t))^+$, where $Δ_i(t)$ denotes the Age of Information of source $i$ and $d_i(t)$ is a source-dependent delay baseline. Based on this metric, we define a goal-oriented loss that supports source-dependent nonlinear penalties, allowing prioritization according to mission relevance. We formulate relay control as a constrained semi-Markov decision process (CSMDP) and solve it using masked Lagrangian Proximal Policy Optimization (PPO). Feasibility-aware action masking restricts transmissions to bundles that can complete within the remaining contact window. DTNSim simulations indicate improved age-based utility and inter-flow fairness compared with baseline schedulers. The proposed framework jointly optimizes relay-side bundle scheduling, dropping, and flow control under contact-driven dynamics with explicit fairness considerations across heterogeneous sources. --- ### DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness Authors: Daniel Szelogowski Published: 2026-10-09 Categories: cs.NE, cs.ET, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2610.13918v1 Clinical sleep medicine repeatedly documents profound divergences between objective sleep duration and subjective daytime impairment, notably exemplified by sleep state misperception in paradoxical insomnia and boundary instability in narcolepsy type 1. Here, we present DyssomniaNN: a multi-scale biophysical computational framework coupling Borbély's two-process regulation of sleep homeostasis and circadian drive with Saper's hypothalamic reciprocal flip-flop circuit and a recurrent corticothalamic leaky integrate-and-fire spiking neural network. We formalize five clinical cohorts across an identical 72-hour photoperiod: healthy control, circadian rhythm sleep-wake disorder (delayed-phase), chronic insomnia, paradoxical insomnia, and narcolepsy type 1. The synthetic local field potential converges closely with empirical human electroencephalography spectra from the PhysioNet Sleep-EDF database across all canonical frequency bands (spectral mean absolute error of 0.33--0.35). Furthermore, we introduce the Well-Rested Index to quantify restorative efficacy. Simulations reveal that sleep duration fails to predict restorative recovery: paradoxical insomnia achieves normal total sleep time (21.15 h) yet yields low restoration (37.6%) from unsuppressed cortical beta-band intrusion, whereas hypocretin deficiency in narcolepsy produces severe nocturnal fragmentation (781 min of wake after sleep onset) and 35 sleep-onset rapid eye movement periods. DyssomniaNN provides an in silico platform for mechanistic sleep research and virtual neuropharmacology. --- ### Designing Protein Structures from Natural Language Authors: Joseph Lee, Yanjing Li, Bo Qiang, Gregory Lau, Allyson Ettinger, Noah A. Smith, Rory Donovan-Maiye, David Baker, Hanna Hajishirzi, Pang Wei Koh Published: 2026-10-09 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2610.13917v2 A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design objectives they support. We develop Prompteina, the first all-atom structure generation model that supports new and broader design objectives specified in natural language, analogous to text-to-image generation. To train Prompteina, we construct Prompteina-Data, a paired text--protein structure dataset of 1.8M structures and 50M+ captions describing global and residue-specific structural and functional properties. We adapt Proteina-Complexa, a pretrained structure generation model, through text-conditioned pretraining and finetuning that aligns residues with their corresponding text. Prompteina outperforms baselines on 15 of 18 structural properties and generates proteins that more closely match descriptions of their intended functions. In binder design, it leads baselines on at least 13 of 20 targets and improves interface confidence by 14% over the strongest baseline. With iterative in silico feedback, Prompteina's gain over non-iterative generation is 57% larger than the next-best baseline on the hardest targets. Finally, we experimentally validate Prompteina designs against GM2A, a target with no reported de novo binders. We identify nine binders, with the strongest at an apparent $K_{\mathrm{D}}$ of 107 nM. These results establish natural language as an effective and powerful conditioning interface for protein structure generation. --- ### Designing Protein Structures from Natural Language Authors: Joseph Lee, Yanjing Li, Bo Qiang, Gregory Lau, Allyson Ettinger, Noah A. Smith, Rory Donovan-Maiye, David Baker, Hanna Hajishirzi, Pang Wei Koh Published: 2026-10-09 Categories: cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2610.13917v1 A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design objectives they support. We develop Prompteina, the first all-atom structure generation model that supports new and broader design objectives specified in natural language, analogous to text-to-image generation. To train Prompteina, we construct Prompteina-Data, a paired text--protein structure dataset of 1.8M structures and 50M+ captions describing global and residue-specific structural and functional properties. We adapt Proteina-Complexa, a pretrained structure generation model, through text-conditioned pretraining and finetuning that aligns residues with their corresponding text. Prompteina outperforms baselines on 15 of 18 structural properties and generates proteins that more closely match descriptions of their intended functions. In binder design, it leads baselines on at least 13 of 20 targets and improves interface confidence by 14\% over the strongest baseline. With iterative in silico feedback, Prompteina's gain over non-iterative generation is 57\% larger than the next-best baseline on the hardest targets. Finally, we experimentally validate Prompteina designs against GM2A, a target with no reported de novo binders. We identify nine binders, with the strongest at an apparent $K_{\mathrm{D}}$ of 107 nM. These results establish natural language as an effective and powerful conditioning interface for protein structure generation. --- ### Markov Chain Convergence in Kernel-Induced Geometry Authors: Oleksii Kachaiev, Luc Brogat-Motte, Silvia Villa, Lorenzo Rosasco Published: 2026-10-09 Categories: math.PR, stat.ML arXiv: https://arxiv.org/abs/2610.13916v1 We study the convergence of Markov chains in the geometry induced by Hilbertian embeddings associated with positive definite kernels, also called Maximum Mean Discrepancy (MMD). Under a contraction assumption in the kernel-induced geometry, and a standard spectral gap assumption, we establish non-asymptotic, high-probability bounds for the convergence of the empirical occupation measure to the invariant measure. The obtained bounds separate the roles of the two conditions: the spectral gap determines the effective sample size in the leading term, while the kernel contraction enters only through a linear correction. As an application, we study one-step prediction of dynamical systems from a single trajectory, deriving fast learning rates for a nonlinear least-squares estimator. The rates highlight the interplay between mixing properties in the kernel-induced geometry and the classical source and capacity conditions used in the analysis of least-squares. --- ### Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning Authors: Junkai Liu, Le Zhang Published: 2026-10-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.13915v1 Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining. However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundancy that make regions inherently unequal in their value for representation learning. To this end, we first show through controlled crop-quality manipulations that better sub-volumes lead to better downstream transfer, revealing the observation policy as an overlooked bottleneck in 3D medical SSL. Motivated by this finding, we revisit sub-volume sampling as a \emph{where-to-look} problem. We propose \textbf{\method}, a plug-and-play framework that replaces random cropping with an offline coarse-to-fine probe bank guided by \textit{anatomy-awareness}, \textit{informativeness}, and \textit{diversity}. We instantiate \method as a lightweight \lite variant using geometric and image-statistical cues, and a diagnostic \feat variant using frozen visual features, to examine whether lightweight volume-intrinsic priors suffice or richer semantic cues reliably provide additional value. Extensive experiments across multiple 3D medical SSL backbones and downstream tasks demonstrate that \method-\lite consistently improves transfer performance over random sampling. Mechanistic analyses further attribute these gains to more anatomically plausible and informative observations, reduced spatial redundancy, more efficient learning dynamics, and more structured representations. --- ### RSI-Anything: Unlocking Recursive Self-Improvement with World Models Authors: Taoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao, Shuhan Xue, Qiang Gao, Wanli Ouyang, Pheng Ann Heng, Zhenfei Yin, Yingcheng Wu, Ling Yang Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.13912v1 Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments. --- ### When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors Authors: Shubh Garg, Chen Shani Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.13910v1 Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully encode the structured relations required for such reasoning. We introduce EICS (Evaluation-Invariant Concept Stability), a metric for testing whether representations consistently encode concepts under controlled one-concept interventions, and CASP-VL (Causally controlled Spatial Perturbations for Vision-Language models), a benchmark of causally controlled spatial perturbations derived from Visual Genome scene graphs. Across multiple VLM architectures, we find that spatial relations are represented substantially less faithfully than lexical information, even when the same models score well above chance on compositional benchmarks. Further analysis shows that the relation is identifiable at the predicate's own tokens but is lost when the sentence is aggregated into a global representation, whether through the (EOS) token or by mean pooling. These findings reveal a systematic failure invisible to output-based evaluation: VLMs do not preserve, in the representation used downstream, relational information that is present in their own input. --- ### Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping Authors: Danil Rudenko, Georgii Bulgakov, Nikolay Kartashev, Ivan Rubachev, Daniil Krasylnikov, Artem Babenko Published: 2026-10-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.13909v1 While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Mean Squared Error (MSE), but differences in datasets, backbones, and evaluation protocols make their practical benefits difficult to compare. In this work, we address this gap by performing a systematic re-evaluation of regression objectives across a broad collection of established tabular datasets and multiple neural backbones. Our comparison reveals that many proposed objectives provide limited or inconsistent gains over a properly tuned MSE baseline, while quantile loss yields consistent aggregate improvements over MSE across the tested backbones. We then identify a limitation that remains even with this strong objective: regions with different levels of target noise can reach their best predictive performance at different training epochs. Consequently, a single global early-stopping checkpoint can impose a compromise between uncertainty regions, even when the objective can represent heteroskedastic target distributions. Motivated by this limitation, we introduce a heteroskedasticity-aware extension of quantile loss that uses input-dependent label smoothing as a potential remedy and improves over quantile loss on several backbones. Overall, our results provide a modern empirical picture of regression objectives for tabular deep learning and highlight how differences in optimal stopping times across uncertainty regions can limit the effectiveness of global early stopping. The code is available at https://github.com/yandex-research/tabular-regression. --- ### Hitting-Time Bounds for Asynchronous Q-Learning Authors: Yang Peng Published: 2026-10-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.13901v1 We study the last iterate of standard asynchronous Q-learning from a single trajectory of a finite Markov decision process. The trajectory follows a fixed behavior policy whose state--action chain is irreducible and may be periodic. For discount factor $γ$, write $H=(1-γ)^{-1}$, and let $μ_{\min}$ be the minimum stationary state--action probability and $\mathfrak h_\star$ the largest expected hitting time of the reverse state--action chain. We prove that zero-initialized Q-learning with a constant step size achieves sup-norm error at most $\varepsilon$ with high probability using $\widetilde{O}(H^4/(μ_{\min}\varepsilon^2)+\mathfrak h_\star)$ transitions, for $0<\varepsilon\le1$. The statistical term retains the quartic effective-horizon dependence of standard Q-learning, while initialization cost is additive in $\mathfrak h_\star$. For aperiodic behavior chains, a comparison with mixing time yields a transient term $\widetilde{O}(t_{\mathrm{mix}}/μ_{\min})$. An empirical state--action count rule selects a constant step size for a subsequent training run and attains the same rate without prior knowledge of model parameters, target accuracy, or confidence level. The output is the last training iterate, with both stages included in the sample count. The proof uses two deterministic Bellman envelopes to separate statistical error from fixed-policy initialization error and adapts reverse-time hitting-cost compensation from TD learning to state--action propagation. An exploration lower bound holds for arbitrary predictable step sizes. Together with the existing statistical lower bound and its extension to pilot-selected constant steps, it yields matching mean-square rates up to logarithmic factors on the stated large-sample parameter classes. --- ### Structural Automata for Neural Semantic Parsing Authors: Xiao Zhang Published: 2026-10-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.13896v1 Neural semantic parsers generate meaning representations token by token, yet well-formedness depends on references, scope, and graph relations that unfold during generation. Constrained decoding prevents locally invalid tokens but does not guarantee that a valid prefix can be completed within a fixed output-length limit. We investigate structural automata at three stages of DRS parsing (decoding, post hoc processing, and training) and additionally evaluate decoding on AMR. For decoding, we introduce accepting-path decoding (APD), which maintains a verified completion within the remaining length limit and follows the model's preferred token whenever that token can also be completed. APD guarantees an accepted output without retracting tokens. Under tight length limits, it improves Smatch++ over local masking by 5.1 and 2.4 points on DRS and by 6.4 and 3.2 points on AMR, comparable to rollback under the same limit, which retracts tokens. For post hoc processing, invalid outputs concentrate on the same inputs: eight unconstrained samples yield no valid output for 10.2% of inputs with limited training data, compared with 0.4% with full data, where filtering comes within 0.2 Smatch++ points of APD. For training, penalizing automaton-rejected tokens improves development Smatch++ by 3.6-11.0 points after 10% of training, but this advantage diminishes as cross-entropy alone reduces the probability assigned to rejected tokens from 14% to below 2% within the first sixth of training with limited data. --- ### Task Context Shapes Component Roles in Language Models Authors: Sovesh Mohapatra, Dani S Bassett Published: 2026-10-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.13895v1 Large language models reuse the same attention heads across tasks, but identifying these shared heads does not explain what they do differently in each task. A natural source of inspiration is task-dependent interactions among shared brain regions, which motivate a network view of language-model computation. Here, we compare fixed model components across tasks using identical graph facts, statements specifying which directed connections are present. We measure how interventions affect attention heads and the activation state in later layers (influence), as well as the answer (importance). Task changes redistribute the influence in five open-weight models spanning four families and 1.5-14 billion parameters. In Gemma-2-9B and Qwen3-14B, an activation edit changes an early internal activation vector and switches which fact the model reads while the written instruction stays fixed. The same heads then respond to different graph facts and influence later components differently. For each prompt, we construct two linear response maps, one before the edit and one after it. Each map predicts a later head's response from a measured change in an earlier head. For a separate factual intervention, the map for the corresponding condition reduces mean squared prediction error by 53.6% in Gemma and 5.0% in Qwen compared with the average of the two maps. These findings show that task context changes both which graph facts the shared components respond to and how their outputs affect later computation. A network account may help explain how models use shared parameters to perform different computations. Measurements of task-dependent influence could also guide interventions intended to alter one behavior while preserving others. --- ### Beyond the Snowflakes: Disentangling Weather Effects from Confounding Meta-Factors in LiDAR Object Detection Authors: Yiming Yang, Jeremy P. Bos Published: 2026-10-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.13891v1 Light Detection and Ranging (LiDAR) is critical for autonomous perception, yet its performance is known to degrade in adverse weather. While existing literature models snow as atmospheric noise that degrades performance, our granular evaluation on the WADS-3D and CADC datasets reveals a counter-intuitive phenomenon: detection accuracy consistently improves as snow intensity increases. Through ablation study and meta-information analysis, we reconcile this by confirming that while falling snow acts as noise, its negative impact is outweighed by a dominant, concurrent factor: significantly increased object point count. We hypothesize that this object point count boost acts as a geometric enhancement, driven by snow accumulation increasing vehicle surface area and a shift from specular to diffuse reflectance. Our findings demonstrate that evaluating perception systems using broad weather-severity bins without accounting for correlated object-level data can lead to misleading conclusions about detector robustness. We conclude that accurate evaluation requires decoupling atmospheric noise from surface accumulation effects and outline future research to validate these physical models. The WADS-3D dataset is available at: https://digitalcommons.mtu.edu/wads-3d/. --- ### RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics Authors: Weiliang Chen, Song Liao Published: 2026-10-09 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.13889v1 As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a retrieval framework that combines robust semantic matching with dynamic reliability adaptation. RATED employs a frozen dual-encoder with contrastive fine-tuning for semantic matching, and a lightweight contextual bandit module that re-ranks candidates based on real-time execution feedback. This design enables rapid adaptation to runtime tool failures without expensive model retraining. We introduce EcoAgent, a benchmark of 5,172 real-world tools and over 210,000 query-tool pairs for offline retrieval and dynamic reliability evaluation. Experimental results demonstrate that RATED achieves a 52.2% relative MRR improvement over the ToolLLM API retriever on real-world queries, and reduces fault selection rate from 86.2% to 2.9% under severe API outage scenarios with a 30% failure rate, while incurring negligible latency overhead of less than 1 ms over encode-only inference. The code and dataset are available at https://github.com/Elliotes/EcoAgent. --- ### X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems Authors: Yeonsung Jung, Zhiyuan Wang, Zifan Wang, Vítor Albiero, Benjamin Newman, Edoardo Debenedetti, Ivan Evtimov, Ninareh Mehrabi Published: 2026-10-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.13886v1 Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proactively identifying these compositional failures requires systematically exploring diverse cross-service paths. Existing red-teaming methods often simply prompt LLMs to identify potentially harmful paths from task and environment descriptions or decompose harmful objectives specified by humans or LLMs into seemingly benign action combinations. However, generation is biased toward patterns learned during training, potentially favoring familiar tool combinations and leaving novel cross-service interactions underexplored. To address this, we propose X-AgentRed, a self-evolving red-teaming framework that discovers harmful tool call paths through a graph of tool dependencies and expands and refines them using execution feedback. By analyzing each tool's effects, potential harms, and preconditions for execution, the red-teaming agent constructs a directed graph that captures how one tool's effects can satisfy another's execution preconditions. Recipes sampled from this graph are instantiated as realistic scenarios in which agents can produce harmful outcomes. Execution feedback enables self-improvement by diversifying paths that produce harm through tool substitution and refining preconditions at blocked steps in unsuccessful paths to enable further execution. Across four frontier agentic models, X-AgentRed achieves $1.77\times$ the harmful path rate of STAC and explores a more diverse set of tools, yielding $2.99\times$ the tool coverage on average. --- ### Prediction Is Not a Sufficient Memory State Authors: Robert Jenkinson Alvarez Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.13881v1 A memory that reproduces every current prediction may still have forgotten how to learn from the next observation. We characterize this distinction for exact cumulative learning and attention. For smooth convex residual losses with unrestricted real features and labels, a continuous recurrent state of fixed dimension exists exactly when the loss is polynomial. With ordinary, unweighted observations, degree $D$ requires precisely $r=\binom{d+D}{D}-1$ coordinates; even among histories with one fixed current predictor, exactly $r-d$ coordinates can remain necessary for continuation. Nonpolynomial losses have unbounded requirements on such equal-prediction histories. Bounded scalar logistic examples retain this obstruction after fixing any finite derivative jet. For ridge regression, the hidden evidence is the design matrix: the exact state costs $dp+d(d+1)/2$, versus $dp$ for the predictor. On a well-conditioned zero-prediction family, optimal $B$-bit compression has average one-update error of order $d^{-1}2^{-2B/s_d}$, $s_d=d(d+1)/2$, even with arbitrary randomized codes. Kernel attention gives a second exact closure classification. The results identify what future updates reveal, rather than proposing a new regression algorithm or asserting trained-model gains. --- ### Tracking the Invisible: Self-Supervised Wheel Track Detection with Thermal-RGB Fusion Authors: Yiming Yang, Jeremy P. Bos Published: 2026-10-09 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.13872v1 Accurate detection of drivable area is essential for autonomous driving and advanced driver assistance systems. While state-of-the-art methods focus on general traversability estimation, they prove inadequate for snow-covered roads where following existing wheel tracks offers crucial advantages: improved traction, predictable vehicle dynamics, and verified path stability. To address this, we propose a low-cost, self-supervised approach detecting safety-critical wheel tracks using synchronized RGB-I (RGB + Long-Wave Infrared) imagery. Our method automatically generates training labels by projecting future wheel trajectories from recorded GNSS data. A neural network is designed to identify wheel tracks with the 4-channel RGB-I images from challenging, white-out road surfaces. Experimental results demonstrate the effectiveness of our approach in visually monotonous and featureless adverse environment, offering a robust and cost-effective alternative for winter autonomy. The newly introduced ThermalTrack dataset is available at: https://digitalcommons.mtu.edu/thermaltrack/. --- ### Partially Informed Stochastic Optimization via Zeroth-Order Residual Tracking Authors: El Mahdi Chayti, Alireza Mirrokni, Martin Jaggi Published: 2026-10-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.13871v1 Many optimization problems provide direct access to only part of the gradient, while the remaining component must be inferred from function evaluations. This structure arises in performative prediction, performative reinforcement learning, and bilevel optimization with a black-box lower level. We introduce Partially Informed Stochastic Optimization (PISO), which combines the available gradient component with a running estimate of the residual. By centring each zeroth-order observation on this estimate, PISO makes the variance due to random probing depend on the tracking error rather than the residual's magnitude. This yields a randomized sketch iteration with an explicit contraction mechanism and a principled interpretation of momentum. For smooth nonconvex objectives, we establish convergence guarantees that depend on the residual's variation and initial magnitude, without requiring a uniform bound on the unavailable gradient component. With independently sampled function evaluations and Gaussian or spherical probes, PISO attains leading function-evaluation complexities of \(O(d^{2}\varepsilon^{-6})\) under Lipschitz gradients and \(O(d^{2}\varepsilon^{-5})\) under an additional Lipschitz-Hessian assumption. These rates require only one probe direction, two function samples, and one known-component sample per update. The analysis also quantifies how batching trades observations for fewer deployments. Across five settings, PISO variants improve on the tested baselines with comparable oracle access in three, reach a comparable solution faster in bilevel routing, and perform best among methods without response-model derivatives in performative reinforcement learning. ---