# Research Papers — 2026-10 · bundle page 57 of 156 > Full-text markdown of papers #2801–2850 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/57 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/56.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/58.md) ### CoLA: Multi-VLA Coordination via Learned Adapters Authors: Ahaskar Kashyap, Jiawen Zong, Boyu Ma, Chuhao Zhou, Jingliang Li, Stefano V. Albrecht, Jianfei Yang Published: 2026-10-11 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2610.15337v1 Vision-Language-Action (VLA) models are typically deployed as isolated single-agent policies. When several such agents share a workspace, they can coordinate implicitly, by observing one another, or explicitly, by exchanging messages, but it remains unclear when explicit communication becomes necessary. We introduce CoLA (Coordination via Learned Adapters), which keeps each agent's VLA backbone frozen and trains a lightweight message channel and a per-arm diffusion action head on top, with fully decentralised execution. Across three tasks that differ in how much each agent can observe, the channel matters only when information is private. On an occluded tray handover, where the box's colour marker is visible to one agent only, CoLA reaches 76.0% success versus 1.3% with messages zeroed throughout training. On two-arm and three-arm handover tasks, removing messages has no measurable effect with a shared overhead camera (90.6% vs. 88.3% at two arms; 63.5% vs. 60.0% at three), but lowers success on the two-arm task's wrist-only variant (74.8% vs. 64.3%). This architecture generalises across different VLA backbones as well. With a frozen $π_{0.5}$ backbone on the same occluded tray task, CoLA matches the overall success rate of a LoRA-fine-tuned baseline (37.3% vs. 34.7%) using a fraction of the trainable parameters. When CoLA places the box, it selects the correct tray 71.8% of the time, whereas the independently fine-tuned baseline, whose placing arm never sees the marker, selects it at chance level (34.7% against 33.3%). --- ### ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes Authors: Lisong He, Yunxuan Jiang, Haishan Ye, Xiangyu Chang Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15336v1 Influence functions enable principled data selection for large language models (e.g., identifying influential training samples for model editing, debugging, or efficient fine-tuning). However, scaling IFs to LLMs is hindered by the intractability of billion-scale Hessian matrices and the prohibitive memory overhead of backpropagation (BP). While many classical IF approximations reduce Hessian complexity, they still rely on BP for gradient computation, requiring massive storage for intermediate activations that impedes practical data selection at scale. To address this, we propose ZOIF, a zeroth-order framework for influence estimation that operates entirely via forward passes, enabling memory-efficient data selection under resource constraints. ZOIF decomposes influence estimation into three BP-free stages: (1) approximating the average proxy gradient via zeroth-order estimation; (2) reformulating and solving the inverse Hessian-vector product as an auxiliary zeroth-order optimization to bypass explicit inversion; and (3) deriving per-sample influence scores via a forward finite difference along the previously computed parameter update direction. Experiments show that ZOIF selects data subsets with downstream utility competitive with, and in some cases exceeding, the evaluated baselines, yet at substantially lower peak memory cost and with comparable overall computation time. --- ### Full Waveform Inversion with a Learned Preconditioner Authors: Jeongjin Park Published: 2026-10-11 Categories: cs.LG, physics.geo-ph arXiv: https://arxiv.org/abs/2610.15331v1 Full-waveform inversion (FWI) is a powerful approach for reconstructing subsurface velocity models, but its practical performance is limited by ill-conditioning, sensitivity to the update direction, and the high cost of curvature-based methods. In this project, we investigate whether a neural operator trained on reverse-time-migration (RTM) images can provide a useful learned preconditioner for FWI. We compare projected FWI against neural-preconditioned FWI using either a standard Fourier neural operator (FNO) or a Jacobian-informed FNO (JI-FNO). The neural preconditioner applies the normal operator of the learned RTM map to modify the true Devito FWI gradient. Our experiments show that the JI-FNO preconditioner achieves the lowest model error while maintaining data-residual decay comparable to baseline projected FWI. In contrast, the standard FNO preconditioner is unstable and gives worse model recovery, despite using the same neural-preconditioning framework. We also identify a failure mode of a nonlinear neural Gauss Newton-type inner solve: directly matching the neural RTM output to the FWI gradient creates an objective-space mismatch and does not yield a reliable descent direction. These results suggest that forward RTM-image prediction alone is insufficient for learned preconditioning; accurate learned derivatives and objective-consistent use of the neural operator are critical for producing useful inversion updates. --- ### BaT-SAM: Introducing Inductive Bias into SAM via a Mixture of Convolutional Experts for Brain Tumor Segmentation Authors: Sumiaya Jannat, Md Mahedi Hasan, Md Shamimul Islam, Md Nur Hossain Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15330v1 Accurate brain tumor segmentation from magnetic resonance imaging (MRI) is essential for diagnosis and treatment planning; however, manual delineation is labor-intensive and time-consuming. Existing approaches are either task-specific with limited generalization or rely on user-provided prompts during inference. We present BaT-SAM, a parameter-efficient adaptation framework that enables fully automatic brain tumor segmentation with the Segment Anything Model (SAM). BaT-SAM injects local inductive bias into SAM's frozen Vision Transformer (ViT) encoder via Conv-LoRA, where image features are processed by a sparsely gated mixture of multi-scale convolutional experts. This design compensates for the limited translation-equivariant inductive bias of vanilla ViTs while fine-tuning fewer than 5M parameters (less than 1% of the full model). To remove the need for user prompts, we further introduce a lightweight self-prompting box regressor that is jointly optimized with the adapter using scheduled sampling and predicts tumor locations directly from image embeddings. On the BRISC2025 benchmark, BaT-SAM achieves a weighted mean IoU of 0.832 while outperforming state-of-the-art benchmarks. It further demonstrates strong cross-dataset generalization, achieving Dice scores of 0.702 on Figshare and 0.784 on the LGG MRI Segmentation dataset. --- ### Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax Authors: Jiayu Zhu, Luyuan Li, Yuyuan Shi, Hanyi Dong Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15328v1 We introduce Anchor-and-Harvest Curriculum (AHC), a domain-informed, rule-based training system for Craftax-Full. AHC combines achievement-oriented tasks, harvested initial-state progress, difficulty adaptation, bounded selection, and original-task practice. It uses no LLM inference and keeps all 43 actions available. At 2,005,401,600 PPO rollout transitions, three primary AHC runs obtain native-task return $46.70\pm0.57$ (sample SD), compared with $41.91\pm1.01$ for fresh native PPO-GTrXL with the same student architecture and evaluation protocol. Evaluation uses ten stochastic rollouts on each of 1024 fixed worlds per model. An additional cohort of three AHC runs reaches $46.08\pm1.23$. Two single-component ablations retain similar mean returns, while jointly freezing difficulty and removing inherited progress gives $45.14\pm2.79$. All-67-achievement profiles show that most of the return difference comes from Intermediate achievements, while the deepest-floor achievements remain unsolved. A Skill-Preflight diagnosis with a 14B teacher shows how prerequisite and floor-access constraints restrict practice. AHC and three 14B diagnostic configurations reach aggregate returns near the reported 80B DiCode mean of 45.88 and below the 235B mean of 48.55. These results show that an explicit curriculum without LLM inference can reach returns comparable to those reported for LLM-generated curricula on Craftax-Full, without action masking. --- ### CIViC: Evidence Gates for Audio-Conditioned Visual Prediction on Proxy Tasks Authors: Mengzhe Geng, Max W. Y. Lam, Yuewen Cao, Shoukang Hu, Jing Xu, Marc Tessier, Xu Li Published: 2026-10-11 Categories: cs.LG, cs.CV, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2610.15327v2 Removing audio can shift a visual predictor's output without showing whether the task uses the intended audio information. We introduce Conditional Input and Visual Interpretation Checks (CIViC), a four-gate protocol that links an interpretation to an intervention, held-out task comparison, or endpoint control. We demonstrate CIViC on actor-disjoint face-raster tests, a synthetic audio-feature mixture, and source-video-disjoint SpeakerVid proxy tasks. In the static face-raster test, cross-actor audio replacement meets the registered detection rule with a small effect; on a separate temporal endpoint, constant-audio fits score better than audio-trained fits in four matched seeds. In the synthetic mixture, the condition-augmented fit has higher 1,000-step RMSE than the audio-only fit (0.1807 vs. 0.1707), with the gap shrinking during training. In the SpeakerVid proxy, the five-feature-zero fit (five low-level audio summaries zeroed; identity, dialogue, and condition inputs retained) has lower whole-frame grayscale RMSE than aligned audio across four held-out conditions and five paired seeds, while aligned audio has lower segment-drift error. The results show that output activation, held-out error, and endpoint controls support different interpretations across these proxy tasks. --- ### TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation Authors: Jiahui Hu, Weile Mo, Peiliang Cai, Jiacheng Liu, Jinkui Ren, Xiantao Zhang, Xiaobing Tu, Linfeng Zhang Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15324v1 Autoregressive (AR) video diffusion models enable streaming generation of long videos but suffer from significant memory overhead due to the rapidly growing KV cache. Existing KV cache quantization methods are primarily designed for LLMs and transfer poorly to video models, where activations exhibit different statistics and strong spatiotemporal redundancy. We observe that the video KV cache is largely predictable over time, with a clear asymmetry. Keys are highly predictable from their temporal history, while values depend primarily on the current key and need a short history of preceding values. Based on these observations, we propose \textbf{\method}, a training-free predictive KV cache quantization framework for AR video generation. \method predicts keys and values according to their distinct dependencies and stores only the residuals at low precision. Both predictors are lightweight, calibrated once offline by linear regression on a small set of BF16 samples, and remain fixed across prompts and generation runs. Experiments on Self-Forcing, Causal Forcing, and LongCat-Video-13B show that \method consistently achieves higher generation quality than existing KV cache quantization methods at comparable or higher compression ratios, reaching up to $6.71\times$ KV cache compression with the best overall quality--efficiency tradeoff. Our code will be released on GitHub. --- ### Deep Neural Mixed Models for Nonlinear Longitudinal Prediction with Subject-Specific Heterogeneity Authors: Mahmud Hasan, Niloofar Ramezani, Hrishikesh Chakraborty Published: 2026-10-11 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.15323v1 Longitudinal health data often exhibit within-subject correlation, subject-specific heterogeneity, and complex nonlinear predictor--response relationships that may not be adequately captured by conventional mixed models. We propose a Deep Generalized Neural Network Mixed Model (DGNMM) that extends the GLMM framework by using a deep neural network to learn nonlinear population-level relationships while incorporating directly trainable, regularized subject-specific effects to capture individual heterogeneity. The model is estimated using prediction-oriented stochastic optimization with separate regularization of the neural-network parameters and subject-specific effects. This formulation allows us to investigate when increased nonlinear representation capacity provides additional predictive benefit in the presence of subject-specific heterogeneity. A simulation study varies population-level nonlinearity and subject-specific heterogeneity and compares DGNMM with GLMM, artificial neural network (ANN), Maity--Pal (MP), and GNMM alternatives for continuous and binary longitudinal outcomes. In the real-data application, DGNMM achieved the lowest MSPE for continuous depression and anxiety prediction, while alternative models remained competitive for binary outcomes. Exploratory subject-level analyses showed heterogeneous predictive gains across individuals, but the magnitude of the estimated subject-specific effects was not significantly associated with predictive gain. Overall, increased nonlinear representation capacity was most beneficial for continuous prediction under nonlinear response structures, while greater subject-specific heterogeneity did not systematically yield larger predictive gains. --- ### SuperAI: Merging Capabilities Across Heterogeneous Foundation Models Authors: Jingtong Dou, Chuancheng Shi, Wenhua Wu, Wei Bao, Fei Shen, Zhiyong Wang, Tat-Seng Chua Published: 2026-10-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15322v2 Enabling the reuse and composition of knowledge and capabilities distributed across foundation models is an important step toward building scalable artificial intelligence (AI) systems. However, architectural differences and incompatible representations make it difficult to transfer and integrate these capabilities through a unified cross-model interface. To address this challenge, we propose SuperAI, a cross-architecture multi-model fusion framework that integrates complementary capabilities from multiple source models into a host model through orthogonal alignment of low-dimensional task-relevant representations. Specifically, we first extract task-relevant representations from the source models and the host model using shared anchor samples, and apply principal component analysis (PCA) to construct low-dimensional functional subspaces with the same dimensionality. Next, we use orthogonal Procrustes mappings to align the source and host coordinate systems, establishing cross-model correspondences while preserving the internal geometry of each source subspace. Finally, we train a lightweight residual multilayer perceptron (MLP) with joint supervision on task outputs and source-model increments, learning input-dependent residual increments that are injected into the host model for multi-model capability fusion. Experiments on three host models across 15 capability domains show that SuperAI achieves higher average domain scores than the evaluated cross-architecture fusion methods and better preserves general capabilities as the number of source models increases. Ablation studies further support the effectiveness of orthogonal alignment, nonlinear residual mapping, and joint supervision. --- ### Channel Match: Calibrating Shape Latents for Few-Step 3D Generation Authors: Di Yang, Zhihao Li, Yanhai Xiong, Yufei Wang Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15321v1 Recent native 3D generators achieve high-quality asset creation by modeling structured 3D latents with flow-based transformers, but their high-resolution generation remains computationally expensive due to costly iterative sampling. In this work, we introduce a few-step distillation framework for native 3D generation, enabled by continuous self-consistency training with a custom JVP FlashAttention kernel and an analytic velocity regression objective for sparse structured 3D latents. To stabilize joint optimization, we further introduce an adaptive loss weighting strategy that automatically balances them without manual tuning. Beyond acceleration, we reveal a previously overlooked failure mode of few-step native 3D generation: sampling-induced latent distribution drift preserves geometric correctness but disrupts downstream PBR texture synthesis, causing texture artifacts on geometrically valid assets. To address this issue, we propose Channel Match, a training-free adaptive per-channel latent calibration method that restores the latent distribution without modifying either generator. We validate our approach on TRELLIS.2 at the $1024^3$ resolution setting. Our two-step model achieves $4.5\times$ faster geometry sampling while maintaining geometry quality comparable to the many-step teacher, and Channel Match further improves rendering quality by recovering the latent interface between geometry and appearance generation. --- ### Accuracy and Uncertainty in Machine Deception Detection (Research White Paper) Authors: Heng-Sheng Chang Published: 2026-10-11 Categories: cs.LG, cs.AI, cs.CR, stat.ML arXiv: https://arxiv.org/abs/2610.15314v1 A deception detector is only as useful as the trust its alarms deserve. Like a polygraph, detectors that read a language model's internal activations can catch deceptive responses that look honest. Yet current detectors depend on which layers they read, weaken on broader tests, and do not state how certain their alarms are. This white paper proposes the Machine Deception Detector, which targets both detection accuracy and the uncertainty of detector scores. The detector reads every layer of the language model, learns which tokens carry evidence of deception using only response labels, and calibrates its alarm threshold so that its false--positive rate stays below a prescribed level. An ensemble of such detectors measures the uncertainty of each score and raises an alarm only when its members agree, with a confidence level that sets how certain each alarm must be. The proposed evaluation trains on instructed honest and deceptive statements, tests on five unseen deceptive tasks of Liars' Bench read by six Qwen3 models from 0.6B to 32B parameters, and is designed to also show which layers carry the deception feature and how this changes with model size. --- ### FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies Authors: Yifeng Mao, Yuze Feng, Yutong Shen, Liyang Gao, Zhixiang He Published: 2026-10-11 Categories: cs.LG, cs.LO, cs.NE arXiv: https://arxiv.org/abs/2610.15307v1 Efficient neural architecture search (NAS) requires accurate performance estimation under limited evaluation budgets. Existing zero-cost proxies (ZCPs) provide fast training-free signals, but each proxy usually captures only a partial property of an architecture, leading to unstable rankings across datasets and search spaces. In contrast, GNN-based predictors can improve accuracy, but often depend on labeled architectures, graph encoders, and costly representation learning, which makes them less suitable for extreme few-shot settings. We propose FENAS, a topology-agnostic few-shot prediction framework that turns complementary initialization priors into robust ranking signals. Its core component, CAST, is a feature pipeline that combines copula alignment and synergy transformation. CAST maps heterogeneous ZCPs into a compact feature manifold, enabling lightweight meta-learners to produce reliable rankings from scarce supervision. On NAS-Bench-201, with only 0.5% labeled samples, FENAS achieves a Kendall's Tau ($τ$) of 0.70, outperforming representative topology-based few-shot predictors in this low-label regime. In closed-domain search, FENAS evaluates the NAS-Bench-201 space in approximately 1138 seconds and achieves competitive test accuracy. By providing a fast, reliable, and structurally simple evaluation mechanism, FENAS supports the design of automated neural architectures under limited evaluation budgets. --- ### WisdomNet: trustable machine learning toward error-free classification Authors: Truong X. Tran, Ramazan S. Aygun Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15299v1 Misclassification is a critical problem in many machine learning applications. Since even the classifier models with high accuracy (e.g., > 95%) still introduce some misclassification error, it may not be possible to rely on the output of a classifier. In this paper, we introduce trustable learning, which prompts the learning model to yield only the true output, thus avoiding misclassifications. Whenever the model cannot decide the output accurately, the learning model should indicate that there could be a misclassification error if it is forced to classify, and hence, it should reject to make a decision or defer it to a human expert. Therefore, we develop a methodology for trustable learning and apply it to artificial neural networks and show that it is possible to develop a classifier with 0% misclassification error. We propose a novel neural network architecture named WisdomNet that could provide zero prediction error by introducing an additional neuron named as conjugate neuron that would indicate whether the network is able to classify the data correctly or not. The WisdomNet architecture can be applied to any previously built model, and we have evaluated WisdomNet with several network architectures such as multilayer perceptron, convolutional neural network, and deep network on different data sets. The results show that the WisdomNet is able to reduce the classification error rate to 0%, while labeling the data is difficult to classify as `reject' at a low percentage of within around 10%. --- ### CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition Authors: Xiangqing Lu, Tao Zhu, Mingxing Nie, Liming Chen Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15298v1 Large language models (LLMs) offer a new approach to wearable-sensor-based human activity recognition. Retrieval-augmented generation (RAG) further introduces similar motion examples and discriminative sensor knowledge, enabling decisions grounded in observations relevant to the current query. More evidence, however, does not necessarily mean better-organized evidence. When online prompts and LLM agents primarily orchestrate inference, decisions about which activities to compare and when to invoke discriminative knowledge remain concentrated at inference time. As the activity vocabulary grows, the model must repeatedly process more candidates and associated knowledge, whereas pruning candidates too early risks excluding the true activity. We propose confusion-hierarchy evidence-aware reasoning (CHEAR), which moves part of this knowledge organization offline. CHEAR constructs and validates an activity hierarchy from recurrent cross-subject retrieval errors and builds corresponding activity-pair knowledge. At inference time, the hierarchy orders candidate comparisons; the LLM retains candidates progressively, and local discriminative knowledge is accessed only for the remaining activities. Across eight datasets, CHEAR achieves 86.79\% mean cross-subject accuracy, a 75.91\% candidate reduction rate, and 96.44\% true-activity retention. Per-sample token use is 85.15\% lower on average than in a variant without the hierarchical structure. Mean accuracy across eight cross-dataset transfer directions is 88.81\%. These results show that organizing candidates and discriminative knowledge around observed activity confusions reduces online LLM input while maintaining recognition performance. --- ### HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models Authors: Xinmeng Liu, Xianglong Yan, Kaicheng Yang, Weisheng Dong, Yulun Zhang Published: 2026-10-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.15297v1 Recently, AutoRegressive Visual Generation (ARVG) models have emerged as a competitive paradigm for high-quality image synthesis. However, their substantial computational and memory demands make them difficult to deploy on resource-constrained edge devices. Post-Training Quantization (PTQ) provides a promising solution to reduce the computational and memory costs of ARVG models, yet existing methods often suffer from substantial image quality degradation under low-bit quantization. In this paper, we propose a training-free PTQ framework for ARVG, consisting of Tail-Aware Bounded-init Grid Refinement (T-BGR) and Coarse-to-Fine Activation Precision Scheduling (CAPS). T-BGR introduces a tail-aware reconstruction objective for weight quantizer calibration, assigning greater importance to distribution-tail coefficients and preserving fine-grained information without introducing additional parameters or high-precision branches. CAPS performs coarse-to-fine activation precision scheduling by jointly considering the importance and computational cost of different generation stages, enabling efficient mixed-precision allocation under a given bit budget. Extensive experiments on multiple ARVG backbones demonstrate that our framework consistently improves robustness under aggressive low-bit quantization. Notably, on Infinity, our framework achieves near full-precision image generation quality at an effective W4A5.6 activation precision, while existing methods at W4A6 still exhibit noticeable quality degradation or inconsistent performance. Code is available at https://github.com/lxm-lc/HGA-Quant. --- ### OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition Authors: Xiangqing Lu, Tao Zhu, Liang Yu, Shuangjian Li, Lulu Ban, Furong Duan, Mingxing Nie, Liming Chen, Yaping Wan Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15292v1 LLMs increasingly support sensor-based human activity recognition (HAR) by linking motion signals with activity semantics and physical knowledge. Retrieval-augmented generation (RAG) grounds decisions in sensor examples and domain features, enabling training-free target-user inference with less dependence on raw numerical arrays. However, existing LLM/RAG-based HAR typically searches single-level activity spaces using static population knowledge. Consequently, they compare many unrelated candidates using the same static population evidence and overlook personalized motion patterns. We propose OntoAR-HAR, an ontology-guided agentic RAG framework combining static population and personalized knowledge. Its tree-structured activity ontology decomposes classification into local decisions among semantically related activities. The static store supplies node-constrained examples, while offline-discovered executable signal features provide numerical evidence for local distinctions. During inference, the personalized store collects selected user observations, which the LLM integrates with static knowledge and signal features while traversing the ontology to an activity label. Cross-subject and heterogeneous-sensing experiments show complementary gains from hierarchical retrieval and personalized memory across multiple LLM backbones, achieving state-of-the-art performance. By explicitly modeling hierarchical relations across activity granularities, OntoAR-HAR also addresses the long-overlooked semantic inclusion problem and avoids treating related labels as independent categories. --- ### Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation Authors: R. Kenny Jones, Jiajun Wu, Maneesh Agrawala Published: 2026-10-11 Categories: cs.GR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.15290v1 We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allows users to create a library of personalized operations. To add a concept, a user provides a description, which the LLM converts into an initial implementation. The user can then observe the concept's execution behavior over example scenarios and provide lightweight feedback to the LLM, which revises the concept's implementation logic. In the second stage, given a library, an LLM can author a layout program that meets a new layout request from a user. Executing a layout program instantiates a concept-graph, a declarative composition of library concepts. In this way, we require the LLM only to specify which concepts should hold, while we use a solver to search for a layout that satisfies them. Across five spatial layout domains, we find that Co-DSL libraries let LLMs capture layout patterns that are challenging for prior fixed-operation systems, and demonstrate that our concept-graph representation is needed for LLMs to reliably compose concepts together. We further find that Co-DSL lets LLMs author generative layout programs that expose high-level parametric controls users can manipulate to explore a distribution of related layouts without re-prompting. --- ### ASM-6D: Fast Certified Pose-Shape Inference with Complete Correspondence Flow Maps Authors: Ho Jin Choi, Minku Kim, Nadia Figueroa Published: 2026-10-11 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.15287v1 Category-level 6D pose and shape estimation requires recovering an object's pose and geometry from partial observations without an exact instance model. We present ASM-6D, which couples generative complete-geometry prediction with explicit category-level pose-shape inference through shared correspondences. Given an RGB-D image, ASM-6D generates alternative complete 3D correspondence hypotheses whose point identities are shared with a category-level Active Shape Model (ASM), including occluded points. Each hypothesis is fitted directly for rotation, translation, metric scale, and instance shape without a separate correspondence-assignment stage. We analytically eliminate translation and shape coefficients, reducing fitting to a nine-variable scaled-rotation optimization problem that enables efficient batched evaluation of multiple hypotheses in real time. ASM-6D achieves state-of-the-art performance on ROPE and HouseCat6D benchmarks. Ablations demonstrate the importance of generative correspondence prediction and active shape variation. The representation also supports shape completion, shape-dependent pose ambiguity, tracking, and robotic grasping at 6-38 Hz, depending on the inference budget. --- ### Protein Crystallization Segmentation and Classification Using Subordinate Color Channel in Fluorescence Microscopy Images Authors: Truong X. Tran, Marc L. Pusey, Ramazan S. Aygun Published: 2026-10-11 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15286v1 The accuracy of detecting protein crystals for fluorescence microscopy images is very critical for high throughput and automated systems. Although the trace fluorescent labeling method could highlight protein crystals, reflection and emission from the fluorescence dye is not always due to crystal regions. Therefore, the analysis of the peak wavelength in the emission spectra of a fluorophore may not always yield effective results. In this paper, we show that using the subordinate color intensity corresponding to longer wavelengths than the peak wavelength of the emission spectra could improve the accuracy of protein crystal detection. Hence, we have built a segmentation method based on the percentile intensity of the subordinate color for trace fluorescently labeled (TFL'd) protein crystallization trial images. Compared to using the dominant color channel, our segmentation method on subordinate color channel was able to reduce the misclassification rate of likely-leads or crystals as non-crystals by the percentage of from 9.71% to 2.02% depending on the classifier. Similarly, the accuracy of classifiers were increased by the percentage of from 1.77% to 5.53%. Our method reached around 94% accuracy while keeping misclassification of likely-leads and crystals as non-crystals below 1%. Moreover, to evaluate the generalizability of our method, we have conducted new wet lab experiments on two proteins, Concanavalin A (Con A) and Ab inorganic pyrophosphate (AbIPPase), and the misclassification rate was below 1%. Our experiments show that using the subordinate channel may be more helpful for TFL'd protein trial image classification. --- ### FragFlex: Fragment-Based Flexible Molecular Generation for Exploring Vast Chemical Space Authors: Sihyun Park, David Ryan Koes Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15284v1 Drug discovery requires efficient exploration of an astronomically large chemical space. Molecular graph diffusion models offer a promising approach to this task, but many require graph size to be fixed before generation. Although atom-level insertion and deletion can enable flexible-size generation, jointly modeling molecular size, atom types, and bonds while maintaining chemical validity remains challenging. We introduce FragFlex, a flexible-length discrete diffusion model that performs node insertion and deletion at the fragment level. During denoising, FragFlex jointly learns the size, fragment identities, and inter-fragment connectivity of the fragment graph. A neural attachment-site predictor and valence-aware assembler then convert the generated fragment graph into an atom-level molecule. In large-scale experiments generating 10 million molecules, FragFlex achieves near-perfect chemical validity while maintaining high uniqueness, demonstrating a strong balance between the two. --- ### What a Data Release Must Preserve for Off-Policy Evaluation Authors: Kyungbok Lee, Yating Zou, Michael R. Kosorok Published: 2026-10-11 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.15283v1 In off-policy evaluation, merging decision-time histories that matter differently for a specified policy value or comparison can make that evaluation unidentified, even with observed actions and outcomes and known behavior and target policies. We characterize which distinctions must be preserved: identification holds if and only if the action-specific evaluation weights are constant within each released record, and the coarsest exact release groups histories by these weights. For normalized outcomes, the largest sharp width induced by the release equals a behavior-weighted within-record radius of these weights. The same radius becomes a release-design objective when each record may be refined into at most $m$ categories. The optimum has an exact $m$-center characterization. When behavior does not vary within a released record, we give a finite-data repair algorithm whose maximum evaluation-weight radius is at most twice the finite-data optimum. For a fixed action-outcome distribution within a released record, a distinct sharp-identification problem remains. Under the same condition, the action-specific outcome distributions are identified, and optimizing over their couplings gives the sharp interval. We construct an AIPW envelope containing this sharp interval; it matches the interval for all such outcome distributions exactly when the extreme within-record action-coefficient vectors take at most two values in each action coordinate. In 24 KuaiRec tasks, the repair algorithm yields a 93% median reduction in mean pairwise sharp width at $m=64$ relative to the unrepaired release. --- ### North or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge Authors: Kiwoong Park, Seyoung Song, Donghyun Woo, Alice Oh Published: 2026-10-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.15282v1 Large Language Models (LLMs) have made substantial progress in multilingual question answering, yet their ability to understand low-resource sociolinguistic contexts remains under-explored. We study North Korea as a unique testbed where decades of division have produced distinct differences from South Korea in vocabulary, orthography, norms, and ideological discourse. We introduce LENS (Language and sociocultural Evaluation for North Korean Society), a human-validated benchmark of 1,765 questions evaluating LLMs across three dimensions: linguistic robustness, sociocultural perspective alignment, and domain-specific knowledge. Evaluating diverse recent LLMs, we find a modest performance drop on North Korean language inputs, a larger gap in sociocultural perspective alignment, and severe limitations on domain-specific knowledge. Qualitative analysis reveals that models often conflate formal institutions with lived realities, project liberal-democratic assumptions, or rely on coarse stereotypes. Our results demonstrate that linguistic similarity alone does not guarantee sociocultural or domain-specific understanding, highlighting the critical need for grounded evaluation resources for underrepresented cultural and political contexts. --- ### Imperfect Verifiers, Exact Targets: Inference-Time Scaling for Continuous Generation Authors: Kijung Jeon, Molei Tao Published: 2026-10-11 Categories: cs.LG, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2610.15281v1 Verifier-guided inference-time scaling uses additional computation to score intermediate states and steer generation toward better outputs. However, imperfect intermediate verifiers can distort sampling, and repeated refinement alone does not ensure recovery of the desired reward-tilted distribution. We introduce Continuous-State Verifier-Guided Backtracking (CS-VGB), an inference-time scaling method for sampling from reward-tilted distributions with continuous generative models through repeated denoising and renoising. With correctly paired denoising and renoising transitions, the stationary distribution of CS-VGB at the clean checkpoint equals the desired reward-tilted target, even when intermediate verifiers are inaccurate. Under stated regularity conditions, CS-VGB converges exponentially to the target despite verifier error, and the expected number of updates needed to reach a clean sample grows only linearly with the number of checkpoints. In analytically tractable settings, we empirically demonstrate that CS-VGB recovers the desired reward-tilted distribution despite verifier error, whereas the compared verifier-based sampling methods fail to recover the target under the same verifier errors. We also instantiate the framework with diffusion models and one-step stochastic posterior maps. Across prompt-guided ImageNet generation, facial-attribute generation on CelebA, and multi-robot planning, recurrent CS-VGB search improves reward and task success as inference budgets grow, with image-generation rewards continuing beyond the observed plateaus of denoising-only baselines. --- ### GeoBridge: Evolving Transferable Decoder Topologies for Geometric Vision Authors: Rui Wang, Haoyu Zhang, Ran Cheng Published: 2026-10-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.15280v1 Depth estimation and Gaussian reconstruction share a need for multi-scale feature processing, yet use different prediction interfaces and training objectives. Whether a decoder's internal computation can be optimized once and reused across these systems remains a structural design question. Search over primitive configurations alone leaves the organization of transformations fixed. To address this gap, we propose GeoBridge, an evolutionary framework for transferable decoder topologies. First, GeoBridge makes stage-internal topology searchable through residual, sequential, and parallel composition of configurable primitives. Shape-preserving composition retains the stage interfaces of a fixed multi-scale scaffold. Second, a functional-tree encoding supports stage-aware crossover and hierarchical mutation, while a gradient sensitivity-alignment proxy evaluates candidates without training. Multi-objective evolution balances this proxy with computation and parameter cost. Third, selected topologies are instantiated and trained in target systems with task-specific prediction interfaces. A single source search takes approximately 12 GPU hours. GeoBridgeNet-A3 achieves the best depth accuracy among four adapted decoder baselines under a common encoder and training protocol on NYU Depth V2 and KITTI. The same topology reaches 27.11 dB PSNR in Gaussian novel-view synthesis on RealEstate10K, and its refined representations support open-vocabulary segmentation on LERF. These results support decoder topology as a reusable design object across the evaluated geometric vision systems. Code and pretrained weights are available at https://github.com/EMI-Group/GeoBridge-NAS. --- ### Do correct answers have stable latent knowledge support? Authors: Chuancheng Shi, Shangze Li, Wenhua Wu, Kun Hu, Fei Shen, Zhiyong Wang, Tat-Seng Chua Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15277v1 Large language models are typically evaluated in terms of the correctness of their output. However, output correctness alone does not confirm whether the latent knowledge supporting an answer has stable internal representations. We therefore propose latent state stability (LSS) and knowledge topology stability (KTS) to investigate the stability of individual knowledge states and their relational structure, respectively. Specifically, we first separately average the model's internal representations of the same knowledge under each elicitation condition. Using the mean representation under the baseline condition as a reference, we remove shared shifts to obtain corrected representations. We then formulate LSS as the distance between each corrected representation and its reference representation, normalized against the typical distance between knowledge items of the same type. We formulate KTS as the cross-condition consistency of the ordered pairwise representation distances among knowledge items of the same type. Next, we construct EpiStableBench, which comprises 4,411 items spanning factual knowledge and mathematical reasoning, with 76,766 controlled queries. Across 16 LLMs from four families, representation stability varies substantially even among items answered correctly under the base condition. Within models, higher stability generally corresponds to higher accuracy under held-out elicitation conditions; across models, stability does not consistently increase with model size or overall accuracy. Meanwhile, we present LatentDPO to learn a knowledge-editing policy that accounts for the stability of latent knowledge. Experimental results show that integrating LatentDPO with multiple existing editing methods consistently improves editing success and generalization across different expressions. --- ### LeHami: Symplectic Latent Dynamics for World Models Authors: Romina Yalovetzky, Randall Balestriero, Yann LeCun Published: 2026-10-11 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2610.15267v1 Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract the latent distribution over long rollouts. We introduce Symplectic Hamiltonian JEPA (LeHami), which replaces the standard predictor with an action-conditioned Hamiltonian flow over a structured latent state (q, p) integrated using an exactly symplectic leapfrog step. This construction preserves phase-space volume at every rollout step and rules out uniform contraction, asymptotically stable fixed points, and merging of distinct latent states, independently of the learned parameters or action sequence. We obtain the momentum-like component from temporal derivatives of the learned position-like representation, providing an explicit second-order state for prediction and control. On conservative and actuated visual pendulum environments, LeHami substantially improves long-horizon velocity prediction over an unconstrained JEPA world model and empirically maintains constant latent volume where the baseline contracts. The learned flow also supports accurate integration at unseen sub-frame step sizes and numerical time reversal. These results show how geometric structure can provide inference-time guarantees that are complementary to representation regularization in latent world models. --- ### RECAP: Calibrating Low-Bit Reasoning Models on the History They Read Authors: Chi Ruan, Yujie Chen, Zixiang Zhao, Jingcai Guo, Haotong Qin Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15259v1 Low-bit quantization reduces the cost of serving reasoning models but can substantially degrade long chains of thought. Each step reads cached keys and values spanning thousands of tokens, allowing quantization errors to accumulate along the trajectory. Standard calibration operates on short segments that omit the earlier context needed by later reasoning steps. Even when this context is retained, cache reconstruction error alone does not capture how quantization errors affect subsequent attention. We present RECAP, a post-training quantization method that calibrates reasoning models on the history they read. Dynamic-prefix calibration separates long historical context from short-block reconstruction. It regenerates prefix keys and values with the current quantizer and rotates the active block to supervise every position along the trajectory. Prefix read geometry further supervises historical cache errors according to their effects on attention outputs, weighting key and value errors asymmetrically. With both components applied only during calibration, RECAP outperforms the baseline across multiple reasoning models and quantization settings. Under W4A4KV4, RECAP improves accuracy over the baseline by 13.3 percentage points on MATH500 with DeepSeek-R1-Distill-Qwen-1.5B and 15.8 points on AIME-120 with Qwen3-4B. These results highlight the importance of preserving historical dependencies during calibration for low-bit reasoning. --- ### Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning Authors: Debargha Ganguly, Weicong Chen, Mohsen Hariri, Vikash Singh, Sreehari Sankar, Shouren Wang, Wang Yang, Biyao Zhang, Chaoda Song, Alexander Nemecek, Kai Ye, Osama Zafar et al. Published: 2026-10-11 Categories: cs.CL, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2610.15258v1 We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an executable SMT-LIB scratchpad: they write complete SMT-LIB programs, query Z3 across turns, inspect solver feedback, repair formalizations, and terminate with an explicit answer. Our recipe, verifier-conditioned trajectory distillation, bootstraps from a noisy teacher proposal policy by sampling multi-turn trajectories, retaining the successful tail that is correct, non-trivial, grounded, and executable, then applying supervised fine-tuning and trajectory-level preference optimization. Because solver success alone does not guarantee semantic faithfulness, we evaluate task accuracy, k-sample reliability, and SMT program quality. Across 37 benchmarks and 7,254 problems per model family, post-training raises the 4B model's per-attempt accuracy from 85.6% to 97.0% and four-sample all-correct reliability (pass^4}) from 64.1% to 91.7%. It also reduces average SMT calls from 4.10 to 2.52 and tokens per attempt from 18.97k to 12.72k. Sequent-Prover agents give answers backed by executable formal artifacts. --- ### Correlation-Aware Reconstruction for Multivariate Time Series Anomaly Detection Authors: Md. Johir Raihan, Zahra Zamanzadeh Darban, Yueyang Liu, Flora D. Salim, Levin Kuhlmann, Mahsa Salehi Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15250v1 Reconstruction-based detectors for multivariate time series anomaly detection typically learn a single entangled representation of normal behavior and flag anomalies based on reconstruction error. However, real-world anomalies are not only isolated spikes in a single channel but also disruptions in the relationships between channels, where each sensor individually appears normal, but their joint behavior deviates from the norm. Because these models compress both temporal evolution and inter-channel structure into this single space, they lack an explicit mechanism to isolate such inter-channel dependencies from normal temporal dependencies, leading to lower detection rates for cross-channel anomalies. We propose CARMA (Correlation-Aware Reconstruction for Multivariate Time Series Anomaly Detection), which is a reconstruction-based variational autoencoder with two complementary latent spaces: a temporal latent that captures sequential dynamics, and a correlation latent that is trained to reconstruct the window's pairwise Pearson correlations. Both representations are fused in the signal decoder, and anomalies are detected from the reconstruction error. We evaluate CARMA on the TSB-AD-M benchmark suite (17 datasets, 180 series) against 29 baseline methods, and show that it significantly outperforms all of them across multiple threshold-free and range-aware metrics, achieving a VUS-PR of 0.4929. Ablations show that removing the correlation branch degrades performance, that adding a second latent without supervision recovers only part of the gain, and that supervising the correlation latent with an explicit correlation target accounts for the rest and produces a sharper error response at anomalies. --- ### ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation Authors: Kyle Montgomery, Wang Zhang, Chenguang Wang Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15246v1 Tool-using agents alternate between model generation and tool execution, waiting for each tool call to complete before starting the next generation. This sequential execution is costly during agentic reinforcement learning (RL), which requires large batches of multi-turn rollouts. We introduce ObsSpec, an observation speculation pipeline for agentic RL that uses a small world model to predict tool outputs while the environment executes, allowing the policy to begin its next generation early. ObsSpec retains speculative work only when the predicted and actual observations match exactly, making rollout collection lossless, while co-training keeps the world model up to date as the policy learns. On terminal-use tasks, predictions from a 0.6B world model exactly match actual observations in 66.4% of attempts and arrive roughly 16 times faster. Using these predictions, ObsSpec reduces agent latency by 9.3% and 14.2% for 8B and 32B policies. Across controlled experiments, we characterize the regimes in which ObsSpec reduces agent latency under shared policy resources. Finally, because ObsSpec overlaps policy generation with tool execution, it is architecturally compatible with existing techniques for accelerating RL. Code is available at https://github.com/kylemontgomery1/verl-recipe/tree/obsspec/obsspec. --- ### Automated carotid artery atherosclerotic inflammation segmentation in PET using MSR-Net Authors: Ran Li, Abhinav K. Jha, Jie Zheng, Richard Laforest, Yongjian Liu, Mohamed Zayed, Tyler J. Fraum, Barry A. Siegel, Malak Itani, Joyce C. Mhlanga, Pamela K. Woodard Published: 2026-10-11 Categories: physics.med-ph, cs.CV arXiv: https://arxiv.org/abs/2610.15245v1 Objective. To develop an automated method for segmentation and uptake quantification of carotid atherosclerotic inflammation on 64Cu-CANF-comb PET while accounting for partial-volume and tissue-fraction effects. Approach. Synthetic carotid PET images with known fractional-volume ground truth were generated by combining MR-derived high-resolution activity maps with GATE Monte Carlo simulation incorporating major PET physical processes and matched to the Biograph mMR acquisition and reconstruction. A two-stage network first localized the carotid vessel wall from T1-weighted MR and then estimated voxel-wise inflammation fraction from masked PET. Both stages used a multiscale residual (MSR) convolutional backbone. Performance was compared with U-Net, Transformer U-Net, DUCK-Net, and iterative Yang partial-volume correction. Main results. In a two-alternative forced-choice study, five nuclear-medicine physicians identified real images with 54% accuracy (54/100; Wilson 95% CI 0.44-0.63; exact binomial p = 0.48). On 184 simulated test slices from five held-out patients, the proposed method achieved a weighted DSC of 0.79, compared with 0.73 for U-Net, 0.69 for Transformer U-Net, and 0.75 for DUCK-Net, with corresponding HD values of 1.85, 2.29, 2.32, and 2.23 voxels. Patient-cluster bootstrap comparisons favored the proposed method for DSC and HD against all three baselines (Holm-corrected p <= 0.031). Overall ENRMSE was 0.24 versus 0.59, 0.68, and 0.59 for the three DL baselines and 0.57 for iterative Yang. In seven patients, corrected SUV showed a positive association with MR-derived lipid-rich/necrotic core with hemorrhage. Significance. The proposed framework improved carotid PET segmentation and uptake quantification under simulated conditions. The patient analysis is preliminary and requires external validation with biological reference standards before clinical deployment. --- ### EvolvAttack: Backdooring self Evolving VLM Agents Authors: Chuan Zou, Yang Xiang, Zexin Li, Xiaonan Luo, Simin Chen Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15244v1 Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after deployment. We introduce a new attack surface, the self-evolving backdoor, whose payload stays dormant in the initial agent and is progressively activated as the agent evolves. Unlike conventional backdoors, which can be exposed by testing triggered inputs on a static model, our attack requires both a visual trigger and a sufficiently evolved memory state; static scanning with clean memory thus yields near-zero attack success and may deem the agent benign. We realize this through memory-aware backdoor training, which couples trigger activation with the agent's evolving memory while preserving benign behavior unless the trigger co-occurs with payload-related memory. Across three VLM backbones, four agent pipelines, and recency-, semantic-, and reward-based memory evolution, the attack preserves normal functionality and stays nearly inactive before evolution (0.5% attack success rate), yet exceeds 95% attack success within 100 interactions, revealing a stealthy threat unique to self-evolving agents. --- ### Explicit Bounds on Hoffman Constants for Sparse Polyhedral Regularizers Authors: Faris Chaudhry, Anthea Monod, Keisuke Yano Published: 2026-10-11 Categories: math.OC, cs.LG, math.ST arXiv: https://arxiv.org/abs/2610.15241v1 Hoffman constants quantify the distance to the solution set of a polyhedral system in terms of its residual; they control error bounds, geometric conditioning, the convergence rate of first-order iterative algorithms, and the stability of regression estimators to target perturbations. Despite their importance, explicit values of Hoffman constants are rarely available due to their computational complexity. In this paper, we derive explicit bounds on the Hoffman constant for a class of structured polyhedral systems arising in sparse regularization. We show that the constants admit a decomposition into spectral, geometric, and interaction components, which together determine their scaling behavior. This framework explains the gap between worst-case dimension-dependent bounds and the favorable conditioning observed empirically in structured problems. As a primary application, we analyze $\ell_1$-regularized least squares, demonstrating that the effective constants depend on low-dimensional active subspaces rather than the ambient dimension. We then extend to the elastic net and adaptive $\ell_1$-regularized formulations, demonstrating how the underlying optimization geometry is altered by the $\ell_2$ penalty and reweighting scheme. Furthermore, we relate our results to classical statistical assumptions and show that the restricted eigenvalue condition bounds only the primal curvature of the active set, leaving the dual interaction geometry unconstrained and is thus insufficient alone for fast theoretical convergence rates. We further show standard $\ell_\infty$ coherence conditions do not yield dimension-independent Euclidean bounds to close this gap. Our theoretical results show that Hoffman constants admit explicit, interpretable forms in structured regression settings and, in practice, provide actionable tools for post-hoc feature pruning and a priori optimal hyperparameter selection. --- ### ClinEdge: An Expert-Graded Benchmark of Real Patient Edge Cases Where Frontier Multimodal Models Fail Authors: Anurag Sharma, Aditya Sharma, Sapna Baalwan Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15239v1 Most benchmarks for large language models in medicine are built from licensing examinations and theoretical questions. The few that draw on real clinical data do so only in part, and rarely require a model to read a patient's own imaging. ClinEdge addresses this gap with 32 real, de-identified patient cases from active clinical practice, each evaluated across seven frontier systems for a total of 224 expert-graded evaluations. Each case pairs primary imaging with a short vignette, contains a feature known to defeat pattern-matched reasoning, and is scored against the patient's documented clinical course. The suite is built for depth rather than volume. Grading followed a two-stage expert process. First, a senior orthopaedic surgeon graded all 224 responses on a weighted rubric and a pass-or-fail verdict. Second, a panel of nineteen physicians, largely senior specialists at teaching medical colleges, independently reviewed every case and every one of the 224 grades. All seven production systems were evaluated through their public interfaces, and all 224 conversations are preserved as replayable links. Performance was poor across all systems, and the failures were shared: different vendors missed the same findings and converged on the same wrong plans. From the experts' notes we catalogue 18 recurring failure modes in five families. The models stop reading an image at the first finding. They give generic plans and lean toward over-treatment. They trust a misleading history over correct imaging. Their answers vary across systems and runs, and change with question format. Failing answers were delivered fluently and without any expressed uncertainty. Four cases are released in full; the remaining 28 are held out, and we invite frontier AI labs and healthcare AI companies to evaluate their models against them (research@futrbridge.com) --- ### Framework for an AI-Ready ARPES Community Database Authors: Zhi-Xun Shen, Jin Gene Wong, Karen Lei, Leon Garcia, Felix Baumberger, Sergey Borisenko, Aaron Bostwick, Ting Cao, Tanny Chavez, Yulin Chen, Monika Choudhary, Andrea Damascelli et al. Published: 2026-10-11 Categories: cond-mat.mtrl-sci, cond-mat.str-el, cond-mat.supr-con, cs.AI arXiv: https://arxiv.org/abs/2610.15236v1 Condensed matter stands to gain profoundly from widespread adoption of artificial intelligence (AI). However, its current means of data organization impedes this endeavor. As a premier measure of electronic structure underlying material properties, Angle-Resolved Photoemission Spectroscopy (ARPES) has accumulated over four decades of spectra, yet the community's publication-centered workflow preserves only a highly selected fraction of its experimental record. A shared data ecosystem could transform these fragmented measurements and their contexts into a persistent, collective scientific memory, creating immediate value for reproducibility and reuse while laying the foundation for AI-enabled discovery. In this Perspective, we report outcomes of a recent community workshop and propose a practical path toward such an ecosystem. Its benefits unfold along three timescales. In the near term, standardized, searchable, and citable datasets strengthen analysis pipelines independently of AI. In the intermediate future, community-validated tools operating across laboratories could enable broader reuse and increasingly closed-loop automated experiments. In the long term, a diverse corpus of measured electronic spectra could support foundation models for quantum matter. Looking forward, a diverse corpus of measured electronic spectra could support foundation models for quantum matter and new discoveries. We discuss lessons from existing scientific databases, the current state of AI in ARPES, as well as areas of community convergence on data organization, access, credit, governance, and a staged pilot program. --- ### MoMaTune: Model, Match, Then Tune Language Models for Numerical Records Authors: Weimin Lyu, Jingfen Zhang, Lingdao Sha, Peng sun, Xiaowei Chen, Vincent Gao, Rui Song Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15235v1 Despite remarkable progress in language understanding and generation, decoder language models continue to exhibit striking failures on numerical data. Numerical examples are typically serialized as text by concatenating feature names with their values (e.g., fat:3.4), while conventional task adaptation applies loss only to the downstream prediction target. This leaves two structures weakly supervised: within-value sensitivity, where digit position determines numerical magnitude, because token cross-entropy contains no explicit numerical metric; and across-field structure, where measurements in the same record are statistically dependent, because target-only tuning provides no direct loss on the measurements or their dependencies. We introduce MoMaTune (Model, Match, then Tune), a two-stage post-training strategy organized around these supervision gaps. Stage 1 applies Model, ordinary next-token prediction densely over label-free serialized records, and optionally adds Match, a same-record consistency objective that aligns representations of different partial views of the same example. Stage 2 applies Tune, supervised fine-tuning for downstream target prediction. We evaluate MoMaTune on 169,285 records from eight public datasets, with 339 of 340 input fields numerical. At 1.5B parameters, Model raises the eight-dataset masked-value imputation aggregate from 0.106 to 0.401, while the three-dataset correct-context gain rises from 0.058 to 0.167. On diagnostics, Model also increases sensitivity to numerically consequential digit changes, while Match improves robustness to informative partial views. Adding Tune yields higher target-supervised embedding aggregates for each tested Stage-1 parent, and the two-stage recipes obtain higher aggregate scores than Tune alone. The same pattern is observed at 4B, 9.6B, and 27B parameters when model embeddings are used for downstream prediction. --- ### Using Evidence-Centered Design to Guide Prompt Engineering in Measurement: An Illustration with Automated Essay Scoring Authors: Jiawei Xiong, Cheng Tang, Hong Jiao, Hanna Choi Published: 2026-10-10 Categories: cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.15231v1 Generative artificial intelligence (GenAI) models, particularly large language models (LLMs), are increasingly used in educational settings for tasks such as item generation, automated scoring, and feedback delivery. The quality of these outputs depends not only on the AI model but also on how users construct the prompts that guide model behaviors. Current prompt engineering practices are largely ad hoc, relying on trial and error rather than principled design. This lack of structure introduces validity threats including construct misrepresentation, construct-irrelevant variance, and limited reproducibility. We propose that Evidence-Centered Design (ECD), a framework in educational measurement for structuring valid inferences from observed performance, can serve as a principled foundation for prompt engineering in educational applications. We map the three core ECD models, the student model, the evidence model, and the task model, onto the components of educational prompt design, and describe a workflow for ECD-based prompt engineering. We derive five design principles from this mapping and present an empirical study contrasting ECD-designed prompts with state-of-the-art (SOTA) prompting baselines on an automated scoring task. Our empirical study demonstrates the usefulness of this framework on automated scoring. Results suggest that treating prompting as assessment design rather than informal instructions strengthens the validity, reliability, and fairness of AI-generated educational outputs. --- ### Words to World: Benchmarking LLMs in Interactive Physical Environments Authors: Xinnan Dai, Kaiqi Yang, Yaxin Li, Cheng Luo, Wanli Li, Mingqing Xiao, Xinyang Jiang, Daoan Zhang, Kaitao Song, Fengze Liu, Zefan Cai, Caihua Shan Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15228v1 Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that affect the physical world. However, current benchmarks largely evaluate LLMs through static text responses, offline tool calls, or simulated tasks, leaving open the question of how well they can act in real physical environments. We present a benchmark for measuring LLMs in closed-loop physical interaction, where models control a harness system connected to real-world components including robotic arms, cameras, and sensors. In each task, the model must issue instructions, receive physical feedback from the environment, interpret the resulting state, and adapt its next action accordingly. This setting evaluates capabilities beyond language understanding, including grounded perception, action planning, tool selection, spatial reasoning, feedback-driven correction, and robustness to execution uncertainty. Through experiments with representative LLMs, we characterize their ability to translate linguistic reasoning into physical actions and identify common failure modes such as hallucinated state changes, poor recovery from unexpected outcomes, and unstable long-horizon plans. Our benchmark aims to provide a systematic foundation for evaluating LLMs as interactive agents that connect words, tools, and the physical world. --- ### Understanding Unified VLMs: From Attention Probing to Guidance Tuning for Multimodal Generation Authors: Zhengyang Luo, Xiaoyu Qiu, Zhiheng Tan, Yuchen Liang, Yingbin Liang, Liyue Shen Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15227v1 Unified vision-language models (VLMs) perform both text-to-image (T2I) and image-to-text (I2T) generation with one shared Transformer backbone, yet how the backbone processes the condition in either direction remains poorly understood. We study this question from the perspective of conditional guidance: we probe every attention head to show the activation difference between two branches of classifier-free guidance (CFG) with different conditional guidance. On two unified VLMs of autoregressive and masked-diffusion paradigms, the probing reveals a subset of heads that are more sensitive to the change of condition while others are agnostic to it. This characteristic pattern holds in both T2I and I2T generation and is largely stable across data samples, demonstrating the internal mechanism of unified VLMs. Motivated by this, we propose a new inference-time intervention approach for unified multimodal generation, named \textit{HeadTuned-CFG}, which uses the probed condition-change awareness to select and tune the conditional guidance at the attention-head level. Experiments show consistent benefits in both multimodal generation directions of unified VLMs without additional training, and in particular substantial improvements over strong baselines in T2I generation. These results further support the key finding of our probing analysis: the observed pattern of functional specialization is an intrinsic property of unified VLMs. --- ### Zeroth-Order Fine-Tuning of LLMs in Learnable Low-Rank Subspaces Authors: Chuang Tong, Ling Chen Published: 2026-10-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15225v1 Zeroth-order (ZO) optimization enables memory-efficient fine-tuning of large language models (LLMs). However, ZO optimization suffers from high variance in high-dimensional parameter spaces. While recent methods restrict perturbations to random low-rank subspaces, these subspaces often misalign with task-specific descent directions. We propose AdaSub-ZO, a novel forward-only fine-tuning framework in learnable low-rank subspaces. Instead of relying on fixed random matrices, AdaSub-ZO iteratively learns layer-wise projection matrices directly from finite-difference feedback to track task-aware descent directions. Furthermore, AdaSub-ZO incorporates a subspace momentum acceleration mechanism to smooth noisy gradient estimates across evolving subspace bases. Extensive experiments on natural language understanding tasks demonstrate that AdaSub-ZO outperforms existing ZO baselines, substantially reducing gradient estimation variance and accelerating convergence. --- ### Non-Euclidean Gradient Descent Has Many Edges of Stability Authors: Peter Zaika, Zakhar Shumaylov Published: 2026-10-10 Categories: math.OC, cs.LG arXiv: https://arxiv.org/abs/2610.15223v1 Recent observations that deep learning models train at the edge of stability have renewed interest in understanding stability properties of classical optimization algorithms. For quadratic objectives, standard gradient descent has a sharp stability threshold: it converges from every initialization when $η<2/L$, diverges from almost every initialization when $η>2/L$, and diverges from every nonzero initialization when $η>2/μ$. For non-Euclidean gradient descent, the corresponding known guarantees are weaker: convergence holds for every initialization when $η<2/S$, where $S$ is the generalized sharpness, while every nonzero initialization diverges when $η>2/μ$. The behavior in the intermediate regime $2/S<η<2/μ$ is not fully characterized. We show that Hilbertian norms are the only ones for which $2/S$ is an almost-everywhere sharp threshold for every positive-definite quadratic objective. Using linear conjugacy between non-Euclidean and Euclidean gradient descent, we show that for general norms the intermediate regime can contain arbitrarily many edges of stability associated with distinct attracting directions. We identify a forward-invariant region of exponentially divergent directions beyond the generalized stability threshold. When the directions of minimum curvature are finite and nondegenerate, we prove that, sufficiently close to $2/μ$ from below, only their invariant directions remain convergent. We give smooth two-dimensional constructions with arbitrarily many distinct thresholds, arbitrarily large relative threshold separation and show these properties to be stable. --- ### HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems Authors: Zhaoyuan Qiu, Sachith Seneviratne, Yu Xia, Saman Halgamuge Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15221v1 AI agents can evolve by using environment feedback to revise their harnesses, the software managing model inputs, tool use, memory, and execution, while keeping foundation models frozen. Existing studies focus on single agents, leaving joint harness evolution in multi-agent systems (MAS) underexplored. A single global optimizer faces growing context and workload as the system scales, while access restrictions may prevent sharing agent internals or system-wide feedback. We propose HarnessNet, a framework for hierarchical harness evolution in MAS. Its basic unit, Agentron, comprises an evolvable forward harness, a foundation model, and a local optimizer that can observe and modify only that harness. Agentrons form a layered graph through which environment feedback propagates backward, with upstream optimizers receiving node-specific feedback from the downstream layer. This decomposes joint harness evolution into smaller, coordinated tasks with separate contexts, reducing individual optimizers' context and workload while keeping access local. Optimizers need not access all agent trajectories or raw environment feedback. Experiments on AgentBench with multiple foundation models demonstrate the feasibility of training HarnessNet. Compared with a single global optimizer, HarnessNet achieves comparable performance gains while respecting local privacy and requiring fewer tokens and less time per optimizer call. A migration study shows that the evolved harnesses remain jointly effective after replacing the foundation models, suggesting transferability across models. --- ### Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models Authors: Seyedarmin Azizi, Erfan Baghaei Potraghloo, Arya Fayyazi, Saeid Shokoufa, Massoud Pedram Published: 2026-10-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15218v1 A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when it is trained, and running fewer is cheaper and faster, so a deployment may choose to do it. Running fewer loops also makes these models less safe, and the loss of safety is larger than the loss of anything else we measured. We study four released Ouro checkpoints and Huginn-0125. At half of its trained depth, Ouro-1.4B-Thinking still solves 0.692 of the GSM8K maths problems, against 0.775 at full depth, keeping 89% of its accuracy. Over the same reduction, the rate at which it helps with harmful requests rises from 0.038 to 0.205, 5.3 times higher. The information is not lost: a linear classifier reads whether a request is harmful from the model's internal state after a single loop, with an ROC AUC of 0.967 against 0.986 at full depth. What the missing loops remove is the refusal that should follow. We measure the effect with four instruments, one generating no text at all, and reproduce it on a second model family. Removing a single direction from Ouro-1.4B's internal state at full depth drops its refusal rate on harmful prompts from 0.950 to 0.130, identifying what the shallow model is missing. Two run-time repairs do not help: the models' early-exit rules do not spend more loops on harmful requests, and choosing a depth per request does not recover the loss. Changing the training does. Standard safety training makes the shallow model safe only by refusing 0.865 of harmless requests, while training at randomly chosen depths reaches a separation of +0.399 between harmful and harmless refusal at one loop, against +0.118. On Huginn-0125 it keeps harmful help at or below 0.040 at every depth from 1 to 32 loops, where standard training reaches 0.194, and it costs no accuracy at full depth. --- ### PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces Authors: M. Yigit Turali, Shreyas Rajesh, M. Efe Lorasdagi, Chenda Duan, Kartik Sharma, Vwani Roychowdhury Published: 2026-10-10 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2610.15208v1 Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigations grow, agents must maintain research state across model calls and check findings before errors propagate into subsequent work. We introduce PANINI-DR, a multi-agent harness that separates coordination of the overall investigation from the research and verification of individual subquestions. A shared workspace, built on the Generative Semantic Workspace representation, records subquestions, their dependencies, findings, and supporting evidence. Researchers investigate individual subquestions, while a separate verification agent checks proposed answers against those subquestions and their evidence. Verification feedback guides further investigation, and recorded findings inform subsequent assignments. We evaluate PANINI-DR on BrowseComp-Plus, FRAMES, and MoNaCo against seven state-of-the-art deep-research harnesses, all using a shared language-model backbone and frozen corpora. PANINI-DR achieves the strongest average performance across the three benchmarks. On BrowseComp-Plus, it achieves 73.3% accuracy, outperforming the next-best harness by 16.0 points. Its advantage is strongest on hard questions, where it answers nearly twice as many as the next-best harness. Ablations further show that structured planning and persistent state improve performance, as does checking each finding against its cited evidence before it is reused. Because a model can answer correctly from memory alone, we also analyze the evidence retained by each harness. PANINI-DR achieves the highest answer recoverability from saved evidence on all three benchmarks, while complementary claim-support audits show stronger evidence-backed answers. Accounting for this evidence changes how harnesses compare and further strengthens PANINI-DR's advantage. --- ### Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models Authors: Lass Najmuldeen, Seyedhamidreza Mousavi Published: 2026-10-10 Categories: cs.LG, cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2610.15207v1 Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass safety alignment and induce harmful responses. To address this inefficiency, a range of techniques have been proposed to enable efficient LLM inference. Depth-based dynamic inference has demonstrated promising results by enabling outputs to be generated from intermediate layers. It offers the flexibility to adjust model behavior based on the available resource budget. However, how this flexibility affects the robustness of LLMs against jailbreak attacks remains unexplored. In this paper, we address this gap via a comprehensive investigation into the impact of depth-based dynamic inference on the robustness of LLMs against jailbreak attacks. Specifically, we make the following key observations: 1) Shallow exits are consistently more robust to jailbreak attacks than deeper ones; 2) Exit depth affects how easily the adversarial suffix can be optimized, with deeper exits reaching lower attack loss; and 3) Adversarial suffixes affect utility uniformly across exit depths. These insights can help design dynamic inference methodologies that are more robust to jailbreak attacks. Code is available at https://github.com/LassNajmuldeen/balcony-jailbreaking --- ### MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning Authors: Shiva Ahir, Hashmath Shaik, Alex Doboli, Nadeem Yaseen, Simona Doboli Published: 2026-10-10 Categories: cs.AR, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2610.15205v1 Efficient task scheduling in heterogeneous computing systems remains a fundamental challenge in embedded and high-level synthesis flows. This paper presents MoSAIC (Motif-aware Scheduling with AI-driven Cognition), a learning-based framework that bridges the gap between exact and heuristic scheduling approaches for DAG-based applications. The system uses the reasoning capabilities of large language models (LLMs) to learn the relationships between DAG structures and scheduling priority functions. The framework first leverages the OR-Tools CP-SAT solver (4) to generate optimal schedules, which are then used to supervise the learning of compact priority-based scheduling functions through Bayesian Optimization. These learned heuristics capture relationships between scheduling decisions and structural graph features such as rank, depth, and fanout, enabling the construction of a reusable knowledge base across diverse DAG instances. Experimental results across synthetic graph families and real-world benchmarks, including PolyBench and MachSuite, show that the learned heuristics consistently improve over classical approaches such as HEFT (2), while maintaining low runtime overhead. The results indicate that combining optimal supervision with learning-based generalization provides a practical approach for scalable and adaptive task scheduling. --- ### SocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair Authors: Mykhailo Kopytskyi, Jianhua Yang, Mir Seyedebrahimi Published: 2026-10-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15204v1 Large language models are increasingly used in computer science education. However, the teaching abilities of even the most powerful LLMs are limited: they tend to reveal the solution prematurely and may lose focus on the learner's current debugging objective. To address this, we introduce SocraticRepair, a planning-guided Socratic tutoring framework for program debugging and miscon- ception repair that adapts prior planning-guided tutoring work (Li et al., 2026b). The framework is instantiated in the Python programming domain by fine-tuning Qwen2.5-Coder-7B-Instruct on synthetic multi-turn tutoring dialogues constructed from four preprocessed programming datasets. The system is evaluated using a predefined set of independent metrics and benchmarked against a general-purpose LLM. The experiments show that SocraticRepair achieves higher scores on stepwise scaffolding and question quality while also substantially reducing premature solution disclosure. The results also identify reliable pedagogical plan generation as an important remaining challenge. --- ### Do LLMs differentiate linguistic traits internally?: A layer-wise analysis Authors: Samhita Bollepally, Takashi Yamauchi, Manju Muralee, Motunrayo Adebimpe Published: 2026-10-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15203v1 Large language models often produce judgments that resemble human responses, but it remains unclear whether they internally capture linguistic nuances such as conventional versus idiomatic meaning. A layer-wise representational analysis was conducted on two equal-sized pre-trained models, Llama-3.2-1B and Gemma-3-1B-PT, to examine whether and where these models differentiate linguistic traits from input. The analysis combined layer-wise probing with geometric distance measures, using the top embedding dimensions ranked by principal component loadings for each layer. The results show that even with equal capacity, models organize linguistic information in fundamentally different ways, suggesting the need to analyze internal representational geometry, examining not just behavioral outputs but semantic space alignment when evaluating how closely human and model language interpretation correspond. --- ### Continuous Risk-Based Scheduling for Food Safety Inspection: Integrating Historical Decay with Event-Driven Consumer Review Signals Authors: Akriti Bhat, Wayne Zhu, Ishan Gupta Published: 2026-10-10 Categories: cs.AI, cs.CY, cs.MA arXiv: https://arxiv.org/abs/2610.15191v1 Batch risk-based inspection scheduling struggles to detect a critical failure class: food facilities with recent clean inspections that subsequently develop severe violations. Traditional systems recompute risk on fixed planning cycles using static historical data, leaving blind spots between inspection cycles. To address this, we introduce the Continuous Inspection Risk (CIR) system, an event-driven scheduling pipeline that re-ranks the inspection queue dynamically as new data arrives. CIR combines a decay-weighted historical score with a stream of real-time consumer reviews triaged by a language-model classifier. A key structural contribution is our temporal partition rule, which strictly excludes reviews predating the most recent inspection to prevent superseded signals from skewing current risk. Evaluating CIR on 9,505 routine inspections in Santa Clara County, California (2024-2026), we show that history-based scoring alone reduces mean time-to-detection of major violations by 69 days (20.9%) under a 30% inspection budget, but fails to anticipate severe vermin-related closures (0/8 detected). Incorporating post-inspection review signals drastically improves performance, predicting 7 of 8 vermin closures with an average lead time of 117 days-firing on the exact day of review publication in four instances. Introducing a review corroboration rule improves precision from 0.70 to 0.78 without loss of recall. Finally, we analyze critical implementation challenges, documenting a data-hygiene pitfall (stale review leakage across inspection boundaries) and an evaluation limitation involving unobserved facility self-remediation. This work provides the first case-level evaluation of event-driven inspection triggering using open data and provides a reproducible benchmark for review-augmented public health systems --- ### SAFE-KV: Causal Suffix Repair for Behavior-Preserving Non-Prefix KV Cache Reuse in RAG Authors: Xingjian Zhang Published: 2026-10-10 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.15186v1 Retrieval-augmented generation (RAG) reuses the same documents across many requests, making non-prefix KV-cache reuse attractive. Yet a cached document state is not reusable text: it is a context-conditioned causal state whose keys and values depend on the prefix, position, and preceding documents under which it was computed. We formulate non-prefix KV reuse as a behavior-preservation problem with full prefill on the exact prompt as the reference, and introduce SAFE-KV, which repairs a composed cache by re-encoding the causal suffix from a selected start document. On Qwen2.5-7B-Instruct, prefix-conditioned composition preserves only 47.2% of HotpotQA-500 and 37.8% of 2Wiki-500 full-prefill answers; SAFE-KV with risk-guided K2 selection restores 99.8%/98.4% (donor-copy protocol) and 100.0%/98.4% with actual suffix forwarding. Document-only and fixed-window repairs recover far less, because the document states after the repaired region keep histories that omit it. Reuse without repair is exact up to four documents and degrades at sixteen, where suffix repair recovers 98-100%. Faithful repair re-encodes most of the context, so in a single-request L40S study SAFE-KV's operating rule serves every workload by full prefill. SAFE-KV thus establishes the causal-state contract for non-prefix reuse and a validated repair mechanism that meets it. ---