# Research Papers — 2026-10 · bundle page 36 of 156 > Full-text markdown of papers #1751–1800 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/36 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/35.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/37.md) ### inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs Authors: Gonzalo Mancera, Julian Fierrez, Aythami Morales, Ruben Tolosana, Daniel DeAlcala, Francisco Jurado Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.18051v1 This work investigates the application of the Membership Inference Test (MINT) to large language models (LLMs) fine-tuned with LoRA, aiming to determine whether specific samples were used during training and address concerns about data privacy, leakage, and transparency. Building on our previous LoRA-MINT framework, which relies exclusively on perplexity under a strict black-box setting, we propose an approach based on intermediate model representations, including activations and parameter-dependent signals. These representations enable a MINT classifier to distinguish training from non-training samples without requiring full access to model parameters. We evaluated the method on four LLMs (Qwen, Phi-4, DeepSeek-V3, and LLaMA 3.2-3B) fine-tuned on three datasets covering medical, mathematical, and academic reasoning tasks. Results show consistent performance across architectures and domains, achieving scores between 95% and 98%, with robustness to variations in model configurations and data distributions. The proposed approach enables efficient auditing of sensitive training data and supports data provenance and compliance with emerging privacy and AI governance regulations. Although our experiments focus on LoRA-based fine-tuning, the methodology can be extended to other LLM adaptation techniques and, more broadly, to other AI models. --- ### ndscape: a structural map of the nested dichotomy space Authors: Maxwell Dix-Matthews, Melinda Hodkiewicz, Adriano Polpo Published: 2026-10-13 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2610.18050v1 Nested dichotomies (NDs) reduce multiclass classification to a tree of binary classifiers. Tree structure can change accuracy, bias, and variance, but the full space of structures has not been mapped in aggregate. We introduce ndscape, a two-dimensional mapping of ND structures based on depth-weighted structural tokens. We use this embedding to conduct what is, to our knowledge, the first bias-variance analysis across the ND structure space. In simulations with 6 to 10 classes, NDs with similar tree structures exhibit similar squared bias, variance, and squared probability loss, regardless of whether the binary classifier is logistic regression or a decision tree. Variance, however, follows mean root-to-leaf depth when logistic regression is used at each node, so flatter, more balanced NDs are more stable, whereas with decision-tree node models, variance is not associated with depth and differs little across ND structures. On six datasets with 6 to 19 classes, held-out accuracy, log loss, and prediction variance remain spatially organised on the same topology-only map. None of the six standard construction heuristics tested selects a tree from the best-performing cluster on any dataset, although some select high-performing individual trees. The ndscape embedding turns ND selection from one opaque construction step into a readable comparison of class groupings, exposing the upper-level splits that distinguish high-performing and stable regions. --- ### Beyond Black Boxes: Visual Grounding for Text Embeddings Authors: Slimane Larabi Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.18047v1 In this paper, our goal is to represent text embeddings as sketches for three main reasons. First, to visualize text representation and to explore their potential their potential for AI explainability. Second, to investigate the potential benefits of the sketch-based representation for information retrieval. Third, to explore their potential for reasoning, drawing inspiration from the concept of mental imagery. We propose a sketch-based visual grounding framework that transforms text representations into visual topographic sketches. Our approach aims to emphasis the semantics content encoded in the text embeddings through the corresponding sketch. Evaluations are conducted on the MS-COCO dataset to examine the utility of these sketches for text retrieval. The comparative study of SBERT and Sketch-based method reveals that SBERT retains an advantage in strict top-1 retrieval accuracy while achieving comparable performance to the sketch-based method in top-5 retrieval. A cascaded approach combining SBERT and the sketch-based method outperforms SBERT alone, suggesting that the Sketch-based representation could offer significant potential for information retrieval if trained directly on text. --- ### High-fidelity Three-Dimensional Flow Field Reconstruction Driven by Turbulent Fluid Dynamics Authors: Hanlin Kong, Jianan Wei, Yuntian Chen, Yujia Wang, Wenguan Wang Published: 2026-10-13 Categories: physics.flu-dyn, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.18045v1 High-fidelity three-dimensional turbulent flow fields are essential for scientific and engineering analyses, yet obtaining them through direct numerical simulation or high-resolution measurements remains expensive. Super-resolution reconstruction from coarse-grained data therefore offers a promising alternative, but remains fundamentally challenging because fine-scale structures are intrinsically three-dimensional and dynamically coupled across scales. Existing data-driven approaches still struggle to recover multiscale volumetric structures and their coherent temporal evolution. To address these limitations, we propose a turbulence-aware framework for time-resolved three-dimensional flow reconstruction. The framework couples a multiscale neural operator, designed to recover volumetric structures, with a state space model to promote temporal consistency in the reconstructed dynamics. In addition, Navier-Stokes residuals are incorporated as soft constraints to regularize the reconstruction toward physically plausible dynamics. A mixture-of-experts mechanism is also introduced to support unsupervised adaptation to unknown coarse-graining. Across evaluations on canonical turbulent systems and atmospheric reanalysis data, the proposed framework reduces reconstruction errors relative to learning-based and classical baselines, while better preserving multiscale spatial structure and coherent temporal evolution. These results validate the effectiveness of the proposed framework in reconstructing high-fidelity three-dimensional flow fields from coarse-grained data. --- ### Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression Authors: Vatsal, Soumil Malhotra, Priyanshu Chahal, Sanjeev Kumar Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.18039v2 Vision Transformers achieve strong performance but incur high computational costs from quadratic token interactions. Training-free token reduction methods improve efficiency, but their robustness remains underexplored. We propose Prune-and Merge ViT, a training-free framework for off-the-shelf models. It combines class attention-based pruning with similarity-based merging to reduce redundancy while preserving semantic information. To evaluate robustness we introduce two metrics. Relative Accuracy Drop (RAD) measures relative accuracy degradation under transformations, and Prediction Flip Rate (PFR) quantifies prediction consistency. On pretrained ViT and DeiT, Prune-and-Merge reduces computation competitively while maintaining robustness and better accuracy than existing token reduction methods. Our analysis suggests that hybrid token reduction does not introduce hallucination-like behavior and preserves prediction stability for common image transformations. --- ### Data-Free Continual Learning for World Action Model with Rectified Generative Replay Authors: Kaipeng Fang, Hangxu Liu, Chaojian Shi, Yunsong Zhou, Hongzi Zhu, Minyi Guo, Jingkuan Song, Lianli Gao Published: 2026-10-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.18038v2 World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned tasks under sequential fine-tuning. Experience replay (ER) mitigates such forgetting by rehearsing data of previous tasks, yet this data is often unavailable in robotics, where a policy is deployed as weights only and its training data is not shared along with it. In this work, we ask whether a WAM can achieve data-free continual learning by regenerating its own past. Our key observation is that a WAM can indeed autoregressively regenerate complete rollouts of previously learned tasks and replay them to mitigate forgetting. However, replaying such raw rollouts still lags far behind replaying real data, which we attribute to two issues. First, the WAM is unable to recognize task completion and keeps generating purposeless motion after the task is done. Second, under open-loop generation, the generated actions gradually drift away from the generated observations. To address both issues, we present rectified generative replay (R$^2$-WAM), which truncates generated rollouts at task completion with an agentic evaluator and filters out rollouts whose actions are physically inconsistent with the observations. On the four LIBERO suites and five real-world tasks, R$^2$-WAM reduces forgetting by over 90% relative to sequential fine-tuning and nearly matches ER without accessing any data from previous tasks. Our analysis further reveals that forgetting in WAMs concentrates in inverse dynamics modeling: a forgotten WAM still produces visually plausible observations of previous tasks while its generated actions fail. Project page: https://kaipengfang.github.io/r2-wam/ --- ### Weighting-Based Strategies for Classification: Analysis and Local Peak Dynamics with CART Trees Authors: Abdoulaye Sakho, Emmanuel Malherbe, Erwan Scornet Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.18037v1 Tabular learning tasks often suffer from class imbalance, which is often addressed via weighting-based strategies. In this work, we compare the naive approach (unweighted) with the weighting-based rebalancing strategies. Somewhat surprisingly, we demonstrate that, asymptotically, as the predictor complexity increases with sample size, weighting strategies yield predictive performance identical to unweighted approaches across all evaluation metrics, up to a shift in the final threshold. To go beyond, we theoretically study the estimation of a linear regression function through weighted and unweighted CART trees with limited depths. In this setting, we prove that the points in the PR space for both strategies are distributed along the same curve, thus illustrating the similar nonasymptotic performance of the two strategies. Then, we numerically identify more complex synthetic settings where performance gaps, evaluated via fixed classifier complexity, favor weighting strategies. Thus, to guide practitioners, we introduce an indicator that aims at signaling whether a data set may benefit from weighting. --- ### COMPASS: Contextual Moment Prior Alignment for Generalizable AIGI Detection Authors: Zhan Yang, Tiancheng Shen, Weijie Lyu, Shuo Chen, Bernard Ghanem, Yibo Yang, Ming-Hsuan Yang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18034v1 Generalizable AI-generated image (AIGI) and deepfake detection remain challenging due to the asymmetry phenomenon, where adaptation to limited training distributions can degrade the transferable representations of Vision Foundation Models (VFMs). Recent subspace adaptation methods mitigate this issue by freezing high-magnitude principal components while adapting the residual subspace. However, such magnitude-based decomposition is data-agnostic and does not explicitly account for target-relevant semantics, potentially leading to semantic misalignment. We propose COMPASS (COntextual Moment Prior Alignment for Subspace Separation), a data-aware subspace adaptation framework that uses a small unlabeled Semantic Proxy Set to estimate target activation statistics. COMPASS incorporates activation covariance into the decomposition of pre-trained weights, preserving target-relevant representations as a stable semantic reference while the residual adapter learns forgery-related variations. The proxy calibration requires no gradient-based optimization. Extensive experiments demonstrate strong generalization across cross-dataset, cross-method, joint cross-dataset-method, and open-world cross-generator evaluations, achieving state-of-the-art performance on both Deepfake and AIGI detection benchmarks. --- ### FlowSim: Rendering-Free Closed-Loop Simulation for Evaluating End-to-End Driving Systems Authors: Hanfeng Wu, Alvaro Marcos-Ramiro, Michael Schmidt, Christoph Stiller Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18030v1 Closed-loop evaluation of end-to-end (E2E) driving systems typically relies on generating sensor observations and re-processing them through the perception encoder, introducing substantial computational cost and a sim2real gap between simulated and real sensor observations. In this paper, we ask a more fundamental question: is image-space simulation necessary for closed-loop evaluation of E2E driving systems? We propose FlowSim, a rendering-free simulation paradigm that predicts the internal latent representation directly from a previous latent and target-frame symbolic scene conditions. The predicted latent is then processed by the original frozen downstream modules, eliminating image rendering and perception re-encoding. Explicit cross-frame agent association improves latent transition prediction and rollout stability, while variable-horizon simulation enables long-horizon prediction from a common real anchor without accumulating intermediate rollout errors. Experiments on nuScenes and NavSim demonstrate that FlowSim preserves downstream behavior competitively with, and often exceeds image-space simulation in source-to-reference agreement across variable simulation horizons and both dense and sparse latent representations. By predicting the latent directly, both instantiations of FlowSim simulate each step in 0.04--0.06s, substantially faster than the image-space simulation methods they are compared against. These results establish FlowSim as an efficient and practical alternative to conventional image-space simulation methods. --- ### Can Machine Learning Potentials Be More Accurate Than the Methods They Are Trained On? Authors: Pavlo O. Dral, Yi-Fan Hou, Yuxinxin Chen, Hassan Nawaz, Mateusz Witkowski, Szymon Śmiga, Ireneusz Grabowski Published: 2026-10-13 Categories: physics.chem-ph, cs.AI, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2610.18027v1 Although machine learning potentials (MLPs) generalize across configurational and chemical compound spaces, their accuracy is commonly believed to be limited by their training methods, with improvements beyond this limit achieved so far only by refitting to experimental observables. In this Perspective, we argue that MLPs can also be made more accurate than their training methods non-empirically by generalizing across a third space, that of quantum-chemical methods. We propose routes to method-transferable MLPs that predict at unseen methods, with working implementations in both density-functional and wavefunction-based theories showing that they can be more accurate than any of their training methods. Aiming beyond the accuracy of the training methods could also make universal MLPs more accurate than single-method models, even when the method-transferable MLPs remain less accurate than those QM methods. Method-transferable MLPs will shape the construction of training datasets and the evaluation of models, pushing the accuracy limits of chemical simulations. --- ### ChampionKV: Head-Wise Adaptive Budget Allocation for KV Cache Compression Authors: Yuechuan Chen, Yanda Guo, Xiaoxi Liu, Weilin Ruan, Huanbo Xu, Ruyi Wang, Wei Zhu Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.18026v1 Some observation-window-based KV cache compressors use prompt attention to identify important tokens but allocate uniform or predefined budgets across heads, overlooking input-dependent differences in budget demand. We propose ChampionKV, an input-adaptive head-wise budget allocator for long-context KV cache compression. It uses the maximum aggregated observation-window attention score as a lightweight empirical proxy for attention concentration, assigning larger budgets to heads with dispersed attention and smaller budgets to concentrated heads. An abnormal-head mask and a floor-budget mechanism improve robustness under weak attention responses. ChampionKV plugs into compressors such as SnapKV and PyramidKV without changing their token-selection procedures. On LongBench and RULER, both Champion variants consistently improve over their SnapKV and PyramidKV base compressors; the improvements are largest and statistically significant on Llama3.1-70B-Instruct, especially under tight budgets, whereas results on the tested 7B/8B models remain competitive but mixed. ChampionKV does not uniformly outperform Ada-KV, whose global cross-head Top-K selection retains an advantage in several settings. Controlled analysis further shows improved retained attention mass over the corresponding base compressors at negligible overhead. --- ### SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces Authors: Harshit Joshi, Priyank Shethia, Monica S. Lam Published: 2026-10-13 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.18025v1 Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while seeking evidence for current hypotheses, then generate new hypotheses conditioned on those hypotheses and their associated evidence. This couples observation discovery to existing hypotheses, favoring local refinements over exploration of unknown hypotheses regions. Inspired by the hypothetico-deductive method (Hempel, 1945) and dual-space models of scientific discovery (Klahr & Dunbar, 1988), we introduce SHELDON, a scientific reasoning harness that separately represents and jointly explores hypothesis and observation spaces. By actively seeking new observations along with new hypotheses, SHELDON can discover observations that its current hypotheses do not explain. These unexplained observations expose gaps in its understanding, motivate new investigations, and guide the generation of hypotheses beyond refinements of existing ones. Across diagnosis, abstract reasoning, and optimization benchmarks, SHELDON outperforms evaluated baselines by up to 26.7 points. Additional analysis shows that SHELDON generates up to 4.5x more novel solutions. --- ### FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation Authors: Cecelia Soh, Jun Hu, Yuan Li, Cheng Chen, Hui Liu, Yanjia Zhu, Hao He, Bryan Hooi, Bingsheng He Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.18023v1 Graph fraud explanation generation emerges as an important task, which requires jointly leveraging graph structure and content information to produce human-readable explanations for a given risk label. An intuitive approach is to adapt existing graph-enhanced large language models (LLMs), which inject graph structure into LLMs via graph-conditioned instruction tuning or structure-aware embeddings. However, existing methods face two key challenges in graph fraud explanation generation: a lack of evaluation protocols tailored to explanation quality, and a mismatch between the granularity of graph information they provide and what explanation generation requires. In this paper, we propose FRaud Explanation Generation via Agentic Graph Context NavigaTION (FRACTION), a framework for graph fraud explanation generation. To evaluate explanation quality, we introduce a task-specific rubric that assesses faithfulness, graph grounding, helpfulness, consistency, and conciseness, and validate it against human judgments. To focus on fine-grained details of relevant neighbors without reading the entire neighborhood, we equip a language model with graph tools that progressively disclose neighbor records. To train our graph agent, we propose a rubric-guided trajectory distillation strategy through which the agent learns both tool-use behavior and structured explanation generation. Experimental results on three fraud datasets demonstrate consistent improvements over state-of-the-art baselines under a human-aligned rubric. --- ### Machine--human agreement in marking undergraduate assignments is specific to model, prompt and institution Authors: Giulio Corsi, Maryam Abo-Tabik, Yael Benn, Georgiana Thorpe Apreutesei, Roni Tibon, Alexandru Marcoci, Deborah Talmi Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18019v1 Large language models (LLMs) promise to automate one of higher education's most resource-intensive activities: assessing student writing. Existing evaluations are typically limited to a single model, a single prompt and a single institution. Using 761 undergraduate psychology assignments from three UK universities, we evaluated three frontier LLMs, individually and in ensemble, on accuracy, prompt sensitivity, error independence, generalisability and evidential basis. Agreement between human and machine marks varied widely, with no model or prompt optimal across institutions. All models compressed marks towards a common central tendency, overvaluing the weakest assignments and undervaluing the strongest. Because this error was shared, ensembling failed to remove it. Machine marks also rewarded linguistic features more strongly than human marks. Since human-machine agreement was a joint product of model, prompt and institution, we conclude that current LLMs lack evaluative capacity transferable across contexts, and that single-context validation overstates readiness for deployment. --- ### Dynamic Interpolation for Training-Time Prediction Reshaping in Low-Light Image Enhancement Authors: Peirui Zhu, Shijie Hao, Jingxi Liao, Richang Hong, Meng Wang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18018v1 Low-light image enhancement (LLIE) is an important image/video processing problem for reliable visual systems under poor illumination, yet it remains challenging due to the strong coupling among insufficient illumination, noise amplification, and structural degradation. Existing methods typically rely on sophisticated network architectures or engineered objective functions. While effective, the former increases model complexity and deployment burden, whereas the latter relies on empirically tuned loss weights. We revisit supervised LLIE from a training-dynamics perspective and observe that brightness-related errors tend to converge early, while residual noise and structural artifacts often remain insufficiently optimized in later stages. To address this issue, we propose a Dynamic Interpolation Training-only Module (DITM), which introduces no additional learnable parameters and adaptively reshapes the model prediction for supervised feed-forward LLIE training. Specifically, DITM employs brightness-aware interpolation, in which the model prediction is combined with a mean brightness-aligned image constructed by rescaling the model prediction according to the mean brightness of the ground-truth image. By reducing the relative dominance of global brightness discrepancy, DITM makes residual local errors more influential during backpropagation after global luminance has largely stabilized, thereby facilitating artifact suppression and fine-detail restoration in later training stages. DITM is used only during training and is fully removed at inference, introducing no additional inference cost. Extensive experiments on multiple benchmark datasets and CNN-, Transformer-, and Mamba-based LLIE backbones show that DITM consistently improves fidelity and perceptual quality while preserving the inference-time architecture and introducing no additional inference-time computation. --- ### LatentRemedy: Efficient Remedy For Non-Prefix KV Cache Reuse in Multi-Agent Systems Authors: Zhiwei Chen, Zhongtao Rao, Waikit Xiu, Yuxiang Zhang, Shuting Cui, Jian Chen, Tianxiang Zhao Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.18014v1 Non-prefix KV cache reuse is a promising approach for improving inference efficiency in multi-agent systems as agents share the same context blocks. However, when agents have conflicting tasks, directly reusing non-prefix KV caches across agents can severely degrade model performance, causing up to a 90% drop. Existing remedies, including selective recomputation and offset-based calibration, recover a limited fraction of this loss. We argue that the problem lies not only in contaminated KV representations but also in the agent's difficulty interpreting reused context under its own instructions. To this end, we introduce LatentRemedy, which uses a few task-conditioned latent tokens to help the target agent leverage reused context without recomputing the shared block. Specifically, we use an MLP to map the last hidden state of the target prefix into a small number of latent tokens, which are placed after the reused KV block to interact with the shared context. To guide subsequent predictions toward the target task, we train the MLP through full-prefill distillation. Experiments show that LatentRemedy consistently outperforms existing reuse baselines on conflicting tasks while maintaining TTFT close to direct reuse as cache size grows. Code and data are available at https://github.com/chenzhwsysu57/kvreuse. --- ### Correcting or Continuing? What On-Policy Distillation Learns from Student Errors Authors: Shuo Yang, Zheyu Zhang, Mahito Sugiyama, Gjergji Kasneci Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.18011v1 On-policy distillation (OPD) trains a student on its own rollouts under a frozen teacher, mitigating the distribution mismatch of off-policy supervision. While prior work has primarily trained on problems a student can largely solve, we ask whether OPD can improve a student when training is restricted to problems it currently fails. We evaluate five representative OPD mechanisms with Qwen-3 and Phi-4 models under a unified competition-mathematics protocol. We find that OPD does not improve accuracy on this hard subset, with most mechanisms instead degrading performance despite continued decreases in training KL divergence. All eight configurations show a decline, and the two-sided sign test gives p=0.0078. In contrast, the same pipeline improves accuracy by 4.6 percentage points when training is not concentrated on failures, showing that the failure is conditional on the training regime rather than systematic. These findings suggest that OPD is effective when supervision is dominated by correct student prefixes, but can reinforce existing errors when training is concentrated on problems the student currently fails. --- ### Fish Audio Drama 3 Technical Report Authors: Dawei Han, Shidong Li, Shijia Liao, Jiahua Liu, Songting Liu, Qingzheng Wang, Yuxuan Wang, Xin Chen, Yifan Cheng, Tianyu Li, Gangin Park, Xuehao Yang et al. Published: 2026-10-13 Categories: cs.SD, cs.CL arXiv: https://arxiv.org/abs/2610.18010v2 We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple references, follows natural-language direction, revises a take when the next turn gives a note, voices multi-character scenes, edits existing speech by infilling, and synthesizes long-form and streaming audio. Multi-turn revision, scene dubbing, editing by infilling, and streaming text input are new in Drama 3, all in one model. Drama 3 pairs the hybrid linear-attention backbone with a new codebook multi-token-prediction audio decoder that predicts the acoustic codebooks of each frame in dedicated layers that attend over the entire sequence. The model is trained with a three-stage pre-training recipe, instruction fine-tuning, and large-batch reinforcement learning whose only reward is a single learned model of human preference. Its inference engine decodes a single stream at 271 frames per second on one H200, against 177 for Fish Audio S2, although Drama 3 has more than seven times as many parameters. The model weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/drama-3), and inference is available through SGLang-Omni (https://github.com/sgl-project/sglang-omni). We highly encourage readers to visit https://fish.audio to direct their own performances. --- ### Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests Authors: Qikun Cai, Tao Huang, Chen Hou Published: 2026-10-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.18007v1 LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf of a user. Existing checker-repair defenses can reduce inappropriate disclosure, but they rely on repeated calls to a remote action LLM (the model that drafts and repairs the email) and a remote checker LLM whenever a draft fails validation. This creates a cost problem as well as a privacy problem, especially when a requester strategically asks for exact values, raw records, source evidence, or other details that induce leakage-heavy drafts. We propose local contract-conditioned rewriting as a cost-efficient enforcement layer for email-generating agents. The mechanism intercepts an outgoing draft, constructs an information-release contract that specifies what to preserve, generalize, and forbid, rewrites the draft with a local Gemma rewriter, and selectively invokes a final PrivacyChecker. Across extensive email tasks under normal prompts and attack prompts that operationalize strategic information requests, Gemma + Checker reduces normal-prompt leakage from 11.41% to 4.03% while improving UsableRate (satisfied or partially satisfied outputs) from 85.2% to 92.6%. Under the strategic attack-prompt condition, it reduces leakage from 28.19% to 18.79% and reduces checker-only cost amplification from 1.32x to 1.02x. Offline replay ablation shows that the full contract reduces leakage relative to generic Gemma rewriting by 36.3% under normal prompts and 54.1% under attack prompts. These results support a local-first privacy enforcement design: move repair to a cheaper trusted local layer when possible, but retain the checker as the final semantic gate for high-risk sends. --- ### Surface Reconstruction from Range Scans Under Visibility Constraints Authors: Gabriel Lenain, Edmond Boyer, Jean Ponce Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18005v1 Surface reconstruction from range scans is challenging in the presence of noise and outliers, as fidelity to observations must be balanced against sensitivity to measurement errors. Yet, most neural approaches discard the sensor positions and corresponding visibility information, compensating for this loss with geometric priors or regularization terms. We instead formulate surface reconstruction as robust regression of the predicted first surface intersection along each acquisition ray against its measured depth, which penalizes predicted surface intersections within the segment between the sensor and the observed point. We represent the surface as the zero set of a 1-Lipschitz multi-layer perceptron, allowing the use of linearly convergent sphere tracing to compute the first hit, and use a robust Huber loss for regression. Our formulation requires neither oriented normals, sampled off-surface points, nor an eikonal loss. Comparisons with the state of the art on synthetic and real data with varying levels of noise and outlier contamination demonstrate competitive performance on clean data and much improved fidelity and robustness under even moderate corruption. Our analysis further confirms a trade-off between fidelity and robustness: greater fitting capacity improves data fidelity in the clean case but increases sensitivity to the measurement errors inherent in real acquisitions, with a sweet spot typically emerging at intermediate capacity. --- ### SWEPatchTest: Evaluating Software Tests Beyond Reproduction Authors: Hua Lu, Pengcheng Wang, Han Li, Zichen Tian, Yanyu Chen, Huang He, Bingjin Chen Published: 2026-10-13 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.18004v1 Coding agents use generated tests to decide whether a proposed patch satisfies an issue's requirements. A suite that fails on the buggy program and passes after applying the reference patch can still accept an incorrect patch or reject a correct patch. We introduce SWEPATCHTEST, a test-generation benchmark with 619 tasks from SWE-bench Pro, SWE-bench Multilingual, and DeepSWE and 82,579 candidate patches collected from coding-agent trajectories. By replaying each suite on the buggy and patched codebases, \benchmark jointly measures issue reproduction, acceptance of correct patches, and rejection of incorrect patches. Joint Validation Rate (JVR), which requires all three criteria on the same task, exposes failures hidden by single-reference evaluation: the best-performing configuration achieves only 9.21% JVR despite reproducing the reference transition on 59.29% of tasks. We further use validation scores to select and scale demonstrations for supervised fine-tuning (SFT). The resulting training recipe approximately triples JVR and improves downstream repair across three SWE-bench benchmarks. Patch discrimination thus provides both a diagnostic measure of test quality and an execution-based signal for curating agent training data. --- ### Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models Authors: Miao Li, Hanyang Jiang, Hengyu Fu, Baihe Huang, Yating Liu, Yuhang Cai, Changkun Guan, Zhongzhu Chen, Jiecheng Lu, Michael A. Boateng, Pascal Van Hentenryck Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.18001v1 Diffusion language models (DLMs) enable flexible parallel generation by resolving tokens according to the model's evolving predictability rather than a fixed left-to-right order. This flexibility, however, introduces training choices absent from standard autoregressive teacher forcing: which reference tokens are visible when a target is supervised and how much generation space is allocated. Standard supervised fine-tuning (SFT) typically makes these choices through random masking, independently of inference. Our analysis shows how this training-inference mismatch can misdirect supervision. Random masking can conceal prediction errors or penalize uncertainty that decoding would otherwise resolve, while the attention-visible input length can change which response formulations the model favors, even when the underlying solution is unchanged. Motivated by these findings, we propose Predictability-Aware Canvas Selection and Supervision (PACS), an SFT method. PACS uses the model's own predictability to select each example's attention-visible input length and supervises reference tokens immediately before their confidence-guided revelation. Across reasoning and code-generation benchmarks, PACS consistently achieves the highest mean accuracy among the compared SFT methods, with gains of up to 12.84 percentage points over vanilla SFT on individual benchmarks. Code will be released upon publication. --- ### Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks Authors: Francesco Panetta, Federico Di Valerio, Michela Proietti Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2610.17998v1 Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when learning tasks sequentially. This work investigates the integration of Experience Packing and Replay (EPR) as a memory-efficient continual learning strategy for deep SNNs under low-latency constraints. The proposed framework combines Batch Normalization Through Time stabilized VGG9 SNNs with Spike Activation Maps (SAM), which provide forward-only explanations based on spike activity. These explanations are temporally aggregated into spatial attention maps and used to select the most informative image patches for replay, instead of storing full images. Experiments on Split CIFAR10 and Split CIFAR100 show that SAM-guided EPR improves the accuracy-memory trade-off under tight memory budgets, and remains competitive while requiring substantially less storage. --- ### Uncertainty-Aware Semi-Supervised Framework with Supervised Contrastive Learning for Sugarcane Leaf Disease Detection Authors: Shalini Dangi, Divya Teja, Omkar Kabde, Shahid Shafi Dar, Nagendra Kumar Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17996v1 Sugarcane leaf diseases severely impact crop yield and quality, making accurate and timely detection critical for sustainable agriculture. Conventional deep learning models for plant disease detection depend on large annotated datasets, which are expensive to obtain and challenging to prepare due to challenges commonly observed across crop disease detection tasks, including (i) high intra-class variation caused by diverse symptom expressions across growth stages, (ii) subtle inter-class similarities between diseased and healthy tissues, and (iii) the risk of noisy labels degrading model reliability. To handle these challenges, we presented an Uncertainty-aware Mean-Teacher based Semi-Supervised Learning Disease Detection Network (U-SSDNet) that leverages unlabeled data while maintaining robustness. First, discrete wavelet transform preprocessing is applied to enhance lesion visibility and reduce intra- class variation. Subsequently, the KL divergence is employed to refine the pseudo-labels and reduce the impact of confirmation bias. At the same time, supervised contrastive learning is applied to make the features more distin- guishable and improve the separation among different classes. Experimental evaluations on sugarcane leaf disease datasets, considered a representative case study, demonstrate that the proposed approach achieves performance close to that of fully supervised models while requiring far fewer annotated samples and consistently outperforms state-of-the-art supervised and semi-supervised approaches. --- ### Improving Neural Symbolic Regression with a Diverse Prior and Post-training Alignment Authors: David Otte, Jörg K. H. Franke, Frank Hutter Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.17994v1 Symbolic regression is the problem of finding an expression that fits a dataset. Solving it requires searching a combinatorial space of candidate expressions. Neural symbolic regression can amortize that search by training a model once on synthetic data and then predicting expressions for a new dataset. But existing models still underperform genetic programming on real, noisy data. We argue that the deficit lies in the training rather than in the paradigm, and present RASR (Reinforced Amortized Symbolic Regression), a method with two key changes to the training recipe. First, we design a synthetic prior that narrows the gap with real-world data: inputs come from the prior of a tabular foundation model; constants are sampled bottom-up, conditioned on the data; targets carry heteroscedastic and structured noise; and everything is standardized. Second, we split training into two stages. Supervised pre-training maximizes the token-level likelihood of a reference expression. This is followed by reinforcement-learning post-training that aligns the model with its inference-time use by rewarding held-out fit and penalizing expression size. On the black-box track of SRBench 2.0, RASR achieves the best mean test $R^2$ rank of all evaluated methods. Three RASR variants, trained with different size penalties, make up most of the accuracy-complexity Pareto front. On Strogatz, our method recovers more ground-truth expressions than any baseline, and on Feynman it is competitive with the best-performing methods. --- ### Counterfactual Certification for Sequential Unlearning with Long-Run Performance Guarantees Authors: Hanna Benarroch, Jamal Atif, Olivier Cappé Published: 2026-10-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.17993v1 Certified machine unlearning ensures the proximity between the unlearned model and a model retrained without the data to be forgotten. Extending this framework to sequential deletion requests, typically arriving as groups of variable size (e.g., all records of one user or of coordinated users), is challenging. For unlearning methods based on fine-tuning on the retain sets, this leads to either degrading performance or increasing computation as the number of unlearning requests grows. For independent successive requests, we instead certify each model release against a counterfactual unlearning trajectory in which the group being deleted never took part. With a fixed fine-tuning budget per deletion, we show that, for smooth strongly convex objectives, this approach keeps the performance loss bounded, uniformly in the number of requests. Experiments with multiclass logistic regression on FEMNIST show that the resulting algorithm needs fewer corrective steps than existing sequential methods and outperforms training-time differential privacy, particularly when group sizes are heterogeneous. --- ### PolUR: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration Authors: Wenshuo Zhang, Xiangyue Zhang, Junlin Li, Wenjie Tian, Yubo Zheng, Hongli Xu, Jingyu Ru, Xinde Li Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17991v1 Recovering high-quality images from degraded underwater observations is crucial for underwater exploration. Polarization observations show promise as an effective source of complementary physical cues for recovering target radiance under clear-water conditions. However, existing methods have yet to jointly model raw intensity information and polarization cues to enable image restoration driven by an understanding of mixed degradations (color casts, haze, and low light). To overcome these limitations, we propose PolUR, a unified multimodal language-driven framework that jointly uses polarization and RGB information to identify degradation types and severity levels through structured semantic instructions and enhances joint restoration representations under the guidance of degradation-aware semantic features to improve restoration robustness under mixed degradations. We further construct a new benchmark named MixPolar, which contains underwater images exhibiting real-world degradations and their corresponding degradation descriptions. MixPolar supports systematic evaluation of degradation perception, image restoration, and performance on downstream tasks. Extensive experiments demonstrate that PolUR effectively integrates polarization and RGB information, achieving competitive performance in degradation perception and image restoration, while also demonstrating generalization capability and utility for downstream tasks. --- ### Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models Authors: Sadif Ahmed, Soumya Swagata Biswas, Rifat Shahriyar, Chowdhury Mohammad Rakin Haider Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.17989v1 A medical vision-language model may analyze a given CT scan and correctly detect both kidneys in view. Continuing this conversation, if a user provides a prescription with an opposite direction, medical VLMs often sycophantically choose to realign their diagnosis. In this work, we study regressive sycophancy under fabricated evidence, where a model abandons a correct answer when pushback comes with a fake document. We test four open VLMs on 400 VQA-RAD yes/no questions in 19,200 multi-turn conversations, with and without a fabricated prescription. Without a disclosure that documents are synthetic, the models abandon 80.1% of 6,488 correct answers. Notably, under one script each, the same prescription raises the flip rate of Qwen2.5-VL-7B from 45.9% to 89.6% and lowers that of Qwen3-VL-8B from 77.7% to 50.9%. A model rejected the prescription while still preserving the correct answer in 915 of 3,232 conversations with the prescription (28.3%), and 40% of these flipped in later turns. System-prompt sentences that disclose the documents as synthetic lower one model's flip rate from 77.8% to 47.3%. Thus, we conclude that awareness about a forgery does not prevent a model from adopting its answer. --- ### Web Scale on a Budget: Tail-Aware Retrieval Evaluation Authors: Boaz Meivar, Shai Avidan Published: 2026-10-13 Categories: cs.CV, cs.IR arXiv: https://arxiv.org/abs/2610.17986v1 A common practice in instance retrieval is to grow the gallery size to improve a benchmark's discrimination capability. One prominent example is ILIAS, which adds up to 100 million distractor images. The prevailing assumption is that faithful evaluation demands web scale, and that indexing all 100M images through the backbone is the unavoidable price of a comparable number. That price is steep: hundreds of GPU-hours and ~200 GB of descriptors per model, paid again for every method or ablation. We show the web-scale indexing price is largely avoidable: evaluation itself obeys a scaling law. The number of distractors that outrank a positive is Binomial in the gallery size. We define the per-query retrieval hardness, a gallery-scale agnostic quantity that yields a retrieval metric at any scale, and demonstrate it can be derived from a small random sample. The underlying sampled-rank machinery is long established in recommender-system and biometric evaluation, but to our knowledge has never been adapted to visual retrieval. We make the law per-query and estimable, and validate it at true 100M scale on ILIAS and INSTRE, and on the full 759k-distractor Google Landmarks v2 pool. Concretely, within a 5% sample (a flat 20x less indexing), every backbone's tail-aware (EVT) estimate has converged onto the large-scale mAP, to within ~0.01 (mean absolute error 0.005), across five backbones, three benchmarks, and two distractor pools (mAP@1000 at 100M on ILIAS/INSTRE; the official mAP@100 at the full 759k pool on GLDv2); the recommender-systems count baseline over-predicts everywhere (+0.037 to +0.068). This is an order of magnitude better than naively reporting the metric on the same subset (+0.08 to +0.13). We release code and the per-query hardness to facilitate faster, cheaper, and greener retrieval evaluation. --- ### Exact power indices for plurality-voting ensembles Authors: Ilie Sarpe, Theofanis Georgakopoulos, Aristides Gionis Published: 2026-10-13 Categories: cs.LG, cs.DS, cs.GT arXiv: https://arxiv.org/abs/2610.17980v1 Plurality-voting ensembles aggregate the predictions of multiple base classifiers and output the most voted class, with ties typically broken at random. Despite the simple aggregation rule, attributing the impact of each base classifier to the ensemble's predictions is far from straightforward. That is, a single base classifier's impact depends on how it interacts with the votes of all other classifiers in the ensemble, for example, in resolving ties, and not only on its own predictions. We address the attribution problem using established tools from cooperative game theory, studying the Banzhaf and Shapley power indices for new games modeling plurality voting and random tie-breaking, for binary and multiclass classification settings. Computing power indices is, in general, intractable. Surprisingly, our methods, collectively named ENPOWER, enable the exact computation of Banzhaf and Shapley values in linear time for the binary classification setting and in low-degree polynomial time for the multiclass setting. The algorithms in ENPOWER rely on new combinatorial formulations of the Banzhaf and Shapley indices, yielding closed-form solutions for the binary case and ordinary generating function representations for the multiclass case. We validate empirically the methods in ENPOWER demonstrating their high applicability, providing attribution values not captured by existing methods. We apply the attribution of ENPOWER to: ensemble pruning and prompt-based ensembling of vision-language models. --- ### Seeing Depth but Choosing Cues in Vision-Language Models Authors: Zhengtao Zou, Pekka Marttinen Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17976v1 Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth--cue conflicts, representation analysis, and interventions. Among the many image-plane cues relevant to depth perception, we focus on apparent size and vertical position. We compare depth judgments under cue-consistent and cue-conflict conditions in both rendered scenes and real-world photographs. Across model families and scales, depth judgments systematically shift toward misleading cues. Yet the correct depth order remains decodable from the queried objects' visual representations, including when the model answers incorrectly. Image and category controls support interpreting this signal as image-dependent depth information beyond the two target cues. Strengthening the model's own depth readout through object-level write-back can correct conflict decisions without updating model parameters or using ground-truth depth annotations. Interventions show that the effect of this correction depends on the direction and target tokens of the written signal, while its strength varies across architectures and domains. Together, these findings reveal a mismatch between a model's ability to represent depth and use this information when deciding the answer. VLMs can retain useful depth information while allowing competing image-plane cues to exert greater influence on their answers. --- ### All-electron machine-learned orbital-free density functional for periodic CHNO systems Authors: Marc K. Ickler, Andreas Hermann, Fred A. Hamprecht Published: 2026-10-13 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2610.17975v1 We introduce STRUCTURES-P, a machine-learned all-electron orbital-free density functional for periodic CHNO systems. Electrostatics are evaluated analytically in an atom-centered Gaussian basis, while an equivariant network learns the kinetic and exchange-correlation energy from energies and gradients of non-ground-state densities. Minimizing the functional from a superposition of atomic densities recovers the Kohn-Sham ground state: on held-out crystals, the density error falls from 6.7% to 0.4% of the electron count and the energy error reaches 0.25 mHa per atom, half that of a same-architecture interatomic potential. A single functional can be trained for both isolated molecules and periodic systems, and the model generalizes to larger unit cells. It largely preserves relative-energy rankings and reproduces convex-hull vertices on the tested H-N composition slice. Together, these results demonstrate the viability of machine-learned all-electron orbital-free DFT for variational density optimization and energy evaluation in fixed-geometry solids. --- ### Rarity Determines Minimax Rates of Semantic Entropy From Weak Pairwise Judgments With a Known Channel Authors: Xiaoli Yu, Jiamiao Liu Published: 2026-10-13 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2610.17971v1 The semantic entropy of a language model is the entropy of the meanings of its sampled answers. The meanings are never observed, and the entropy is estimated from the verdicts of a pairwise equivalence judge. Given the meanings of $n$ answers, a known channel declares each pair equivalent independently, with probability $q+Δ$ within a meaning and $q$ across meanings. At most $K$ meanings occur, and $q$ is bounded away from $0$ and $1$. For a weak judge, with $nΔ^2\to0$, the global minimax rate is set by distributions near a vertex of the simplex and overstates the difficulty elsewhere. We show that the difficulty is set by how many meanings can be rare. Over distributions with at most $s$ meanings below a fixed probability $τ<1/(K-s)$, the minimax squared risk is of order $N^{-1/s}$ for $s\ge2$, $N^{-1}\log^2(e+N)$ for $s=1$ and $N^{-1}$ for $s=0$, capped at one, where $N=n^KΔ^{2K-2}$. The matching lower bounds hold on every fixed polynomial window $nΔ^2\le n^{-κ}$. One estimator attains these rates without knowing $s$ or $τ$: it averages products of centered verdicts along all spanning trees of every $k$-set of answers, projects the resulting power sums onto the valid moment set and inverts them. The case $s=K-1$ gives the global rate $N^{-1/(K-1)}$ and the consistency threshold: with $Δ=n^{-γ}$ the entropy is uniformly consistently estimable exactly when $γ<K/(2K-2)$. On polynomial windows, the same estimator attains the sharp local minimax constant on shrinking neighborhoods of interior points with distinct probabilities. Restricting the average to stars multiplies the constant by $K^{K-3}$. --- ### AlignPred: Error-Controlled KV Cache Compression via Alignment and Predictive Coding Authors: Xu Yang, Jiapeng Zhang, Zhiwei Zuo, Yuxin Chen, Feiqiang Sun, Chengguang Xu, Feng Jin, Zhuo Tang Published: 2026-10-13 Categories: cs.PF, cs.LG arXiv: https://arxiv.org/abs/2610.17970v1 Long-running agents retain KV caches across turns and sessions for hours or days. Compressing these persistent caches requires reducing storage while controlling reconstruction error. We present AlignPred, a codec that combines local alignment with predictive coding under a configurable KV reconstruction-error budget. Local orthogonal transforms align related heads or layers into a common coordinate frame, allowing AlignPred to combine token-wise prediction with same-token prediction across heads or layers. Residuals are quantized on an error-bounded lattice and entropy-coded, without learned predictors, encoder-side mode search, or large joint transforms. Across three attention mechanisms, AlignPred requires less storage than the evaluated baselines at comparable measured reconstruction error. Against the evaluated CPU codec implementations, it decodes at least 1.6 times faster while matching or improving encode time. AlignPred achieves near-native task scores at substantially compressed operating points on LongBench-Pro at 128K context. AlignPred's SGLang HiCache integration reduces persistent target-KV storage by 42-72% relative to native HiCache, with comparable latency. --- ### Neural Dimensional Analysis: Foundations of Dimensionless and Scale-Consistent Computation Authors: Bum Jun Kim, Makoto Kawano, Yusuke Iwasawa, Yutaka Matsuo Published: 2026-10-13 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2610.17969v1 Modern Transformers rely on many scale-control mechanisms, including normalization, residual scaling, attention temperatures, loss weighting, and adaptive updates. To explain how these mechanisms maintain scale consistency, we introduce Neural Dimensional Analysis (NDA), a unified framework based on dimensional consistency. We define neural units that specify how tensors rescale and which quantities can be added, just as physical units do in physics. Our rules match residual units, nondimensionalize attention and gate inputs, combine losses across units, and convert gradient units into parameter units. We implement NDA through dimensionless Unit Violation Indices (UVI) for diagnosing scale mismatches within Transformers, a unit-consistent multi-loss objective, and the Gauge-Canonical Transformer (GCT) with normalized coordinates and orthogonalized residual additions. In language-model experiments spanning 51M to 1B parameters, GCT remains stable during training across a broad sixteenfold learning-rate range, outperforming Pre-LN, LLaMA-style, and QK-Norm in 124M validation loss at tuned learning rates. GCT's normalized residual stream also shows improved robustness to quantization. At 1B parameters, calibrated per-tensor int8 quantization increases GCT's validation loss by only 0.009 nats, compared with up to 5.51 nats for the baselines. Vision and physics-informed neural network experiments further confirm NDA's benefits beyond language modeling. These results establish dimensional consistency as a neural network design principle. --- ### dMRI-F: A Foundation Model for Generalizable Diffusion MRI Analysis from Sparse Acquisitions Authors: Xi Zhu, Yijie Li, Xiaofan Wang, Wei Zhang, Huafu Chen, Ce Zhu, Fan Zhang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17968v1 Diffusion MRI (dMRI) probes water diffusion within the brain, providing unique information about tissue microstructure and white matter connectivity. High-quality dMRI enables advanced and accurate analyses but demands dense acquisitions, resulting in long scan times and hardware constraints that are often infeasible. Further, dMRI requires dedicated computational methods to support diverse analysis tasks (e.g., parcellation, registration, and synthesis) for both neuroscientific and clinical applications. Here, we present dMRI-F, a foundation model that unifies dMRI data enhancement and downstream tasks across diverse acquisitions and populations, while requiring only minimal acquisition input. dMRI-F is pre-trained with a q-space masked reconstruction task: predicting densely sampled multi-shell data from only six volumes. It learns generalizable latent feature representations of dMRI data, which serve as a core foundation for adapting to diverse downstream tasks, including brain parcellation, brain registration, and cross-modal synthesis. Across nine independently acquired datasets, we demonstrate that dMRI-F outperforms state-of-the-art methods with robust generalization across acquisitions, populations, and tasks. Our results demonstrate dMRI-F's versatility as a general-purpose framework that enables diverse dMRI applications from low-cost, sparse acquisitions. --- ### BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation Authors: Yaoyang Liu, Shuwei Shen, Jincheng Tang, Jinguang Liu, Jinbao Xue, Hailong Yang, Ke Zhang, Yinjun Wu Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17966v1 Long-context inference makes the key-value (KV) cache a major memory bottleneck for large language models. We propose BELT, a low-rank KV cache compression framework. Its key-side objective targets attention distributions rather than raw keys or pre-softmax logits, yielding a quadratic surrogate with a closed-form low-rank solution. A learned global rank allocator uses differentiable soft selection during training and hard selection at deployment to meet a user-specified component budget. Experiments demonstrate improved model quality under aggressive compression and increased decoding throughput at comparable accuracy. Evaluated across three LLMs and multiple benchmarks, BELT achieves up to 70% low-rank KV cache compression while outperforming the strongest baseline by up to 23.3 points on LongBench, and up to 17.8x overall KV cache reduction when combined with quantization. With Triton-based GPU kernels and a quantized cache, BELT delivers up to 2.7x speedup for the attention module and 3.3x end-to-end decoding throughput. --- ### Better Capturing Interactions Between Products in~Retail: Revisited Negative Sampling for~Basket Choice Modeling Authors: Jules Désir, Vincent Auriau, Martin Možina, Emmanuel Malherbe Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.17963v1 Brick-and-mortar retailers face many different challenges that involve understanding thoroughly its products catalog and customer preferences. In particular, assortment optimization - proposing the ideal mix of products - and promotion planning hold a pivotal role in their strategy. By leveraging sales data, retailers can make informed decisions on which products to sell and how to manage inventory, based on customer preferences as well as regional and seasonal trends. It is especially crucial to capture interactions between products, in order to minimize the number of items that cannibalize each other's sales and to ensure that complementary products, which are often purchased together, are conjointly available and sold across all stores. In this paper, we propose a model of shopping basket that learns embeddings to represent interactions between products, prices and stores. Our model is built to uncover sales patterns from very large transaction datasets. In particular, the optimization loss is computed with random negative samples in order to overcome the computational bottlenecks that arise with large number of items. Our experiments on synthetic data show the efficiency of drawing such negative samples based on the actual assortment of available products, with better results than approaches from the literature. We also validate our approach by training and evaluating our model on a dataset composed of millions of transactions from Fortenova Group, one of the leading retail company in Southeast Europe. Our model showcases promising applications in the sector of retail, with enriched interfaces to efficiently support category managers. --- ### CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms Authors: Ömer Faruk İşcanlı, Yağmur Sabucu Sandal Published: 2026-10-13 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2610.17962v1 Predictive service assurance converts forecasts of key performance indicators into alarms, and that conversion decides whether the assurance function is deployable. We present CALM-5G, an assurance layer that operates above any forecasting backbone and issues alarms with distribution-free, finite-sample guarantees. It calibrates on service-level violation events, scores violation onset directly, selects its calibration scheme out of sample, and reports the alarm duty cycle with every certified miss rate. Four corpora are evaluated separately, namely a production cellular network, commercial 5G traces, an open radio access network testbed and our 5G standalone testbed. Risk control on the regression-derived score yields duty cycles of 0.24 to 0.91. Onset targeting with cross-validated calibration reduces time-in-alarm by 56.3% to 89.7% on three corpora, with no significant change on the fourth. The realised miss rate stays within a two-standard-error tolerance on three corpora and within one standard error of it on the fourth. Under label shift, pooled batch calibration exceeds that tolerance structurally, by 10.9 standard errors on the production corpus. Online calibration restores compliance. Calibration schemes cannot be ranked on the split that fits their thresholds. Miss rate and duty cycle are certified jointly where within-entity dependence leaves sufficient calibration units. --- ### Virtual Head Attention Authors: Xibo Ding, Guoxia Wang, Jinle Zeng, Jiabin Yang, Sirui Tao, Chao Yang, Dianhai Yu Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.17959v1 The design of attention mechanisms in long-context large language models faces an ``impossible triangle'' among KV cache size, training and prefill FLOPs, and model quality. GQA achieves strong quality but incurs high KV cache overhead; alternative approaches such as MLA and MFA can compress the cache, but MLA suffers from quality loss while MFA substantially increases training and prefill compute. We propose Virtual Head Attention (VHA), which simultaneously improves all three vertices through two lightweight linear operations: Q Premix applies a near-identity transformation to queries within each KV group to recover virtual head diversity from halved physical query heads, and Linear Postmix fuses inter-head features via a low-rank $I + AB^\top$ residual structure. Since VHA introduces no nonlinear operations, Premix can be folded into the query projection and Postmix into the output projection at inference time, reducing the model to a standard GQA-2 architecture that directly reuses all existing GQA inference optimizations. With only two KV heads, the group size in large models readily reaches 64, fully exploiting Tensor Core parallelism during decoding. Across four scales with 4K-context 50B-token pretraining, VHA consistently surpasses the standard GQA baseline at every scale ($+$0.05\% to $+$0.81\%), while reducing KV cache by $4\times$ vs.\ GQA-8 at dense scales and $2\times$ vs.\ GQA-4 at the MoE scale, and lowering training and prefill FLOPs by 7.9\% (1.7B, $S{=}4096$). On an industrial 30B-A3B MoE model trained on 500B tokens at 8K context, VHA outperforms both MLA and GQA-4 by $+$0.70\,/\,$+$2.60\,\% on a 12-benchmark base-model evaluation suite; in a separate matched 10B-A1B MoE comparison after long-context mid-training, VHA attains an average RULER score of 84.4 over 8K--128K versus 73.0 for GQA, while using two rather than four KV heads in the full-attention layers. --- ### Learning Distributions from Samples and Qualities Authors: Marc Jourdan, Nicolas Flammarion Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.17956v1 We study parameter estimation when each sample from a continuous parametric distribution is accompanied by a binary quality label governed by the same unknown parameter. By imposing hard feasibility constraints, deterministic labels can accelerate estimation from the classical $n^{-1/2}$ rate of smooth quality-aware M-estimators to $n^{-1}$. Combining PAC guarantees with local error-to-parameter conversions, we establish this rate for both identifiable and finitely ambiguous quality classifiers, with likelihood information resolving the latter ambiguity. When the quality model is known only up to an additive constant, we construct threshold-free pairwise preferences from oppositely labeled samples and retain the accelerated rate despite the unknown threshold. We further show that pointwise qualities and pairwise preferences are incomparable: either can be strictly more informative than the other. Our assumptions hold for Gaussian, Laplace, and exponential families under thresholded log-likelihood rewards. Finally, a minimax lower bound establishes the optimal $n^{-1}$ dependence on sample size, up to logarithmic and dimension-dependent factors, while experiments confirm the benefits of constraint-based estimation. --- ### Agent-Reflex: Teaching Language Agents to Act Reflectively Authors: Guanting Dong, Xinyu Yang, Jiajie Jin, Yuyang Hu, Xiaoshuai Song, Yifei Chen, Xiaoxi Li, Jiejun Tan, Yutao Zhu, Tat-Seng Chua, Ji-Rong Wen, Zhicheng Dou Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.17953v1 Large language models have evolved from single-turn chatbots into interactive agents capable of long-horizon reasoning. In real deployments, MCP tool services can return noisy feedback and users may intervene to correct the agent, but existing methods provide limited supervision for reflection learning and failure recovery. To bridge this gap, we propose Agent-Reflex, a general training framework for incentivizing proactive reflection in agents. Specifically, Agent-Reflex comprises three stages. First, Environment Reflection Skill Discovery (RSD) injects grounded tool-feedback perturbations into environment scaling, samples a capability-diverse LLM pool, mines matched success-failure pairs, and summarizes reusable reflection meta-skills. Building on this skill library, we then apply Reflective Supervised Fine-Tuning (ReSFT) that converts each skill into supervision for self-reflection, skill recovery, and user-centric correction, strengthening complementary reflective behaviors. Finally, we propose On-Policy Reflective Policy Optimization (ORPO) to combine agentic reinforcement learning under noisy interactions with reflection-guided on-policy distillation to further elicit proactive reflection. Built on Qwen3-8B, Agent-Reflex reaches 58.6 overall on five long-horizon tool-use benchmarks and 29.1 on AgentNoiseBench, surpassing strong environment-scaling and reflection baselines. Experiments on six challenging agent benchmark suites demonstrate the effectiveness of Agent-Reflex. Further analyses show that Agent-Reflex improves agents' robustness to noise while maintaining stable training dynamics, supporting scalable agent training. Our code is available at https://github.com/RUC-NLPIR/Agent-Reflex. --- ### FETALFusion: Resolution-Aware State-Space Modeling for Multi-Domain Fetal Head Segmentation Authors: Ammar Bhilwarawala, Mainak Bandyopadhyay Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.17951v1 Head circumference (HC) measured from 2D ultrasound is a routine marker of fetal growth, and automating it needs segmentations whose boundaries hold up on individual scans, not only on average. We present FETALFusion, a dual-path CNN-Mamba encoder-decoder for fetal head segmentation across acquisition types. It applies four-directional state-space scans only at the two highest-resolution stages, routes bottleneck features through domain-specific channel gates that are averaged at test time, and adds a weak landmark shape prior. We train jointly on transabdominal (HC-18) and transperineal (PSFHS) images and compare ten methods on a held-out test set of 471 images, each trained under one schedule and scored by surface distances at native resolution. FETALFusion reaches a Dice score of 0.963 and an HD95 of 2.10 mm without test-time augmentation or a domain label. It improves on U-Mamba on all five reported metrics (HD95 reduced by 0.31 mm; Holm-corrected ($p < 10^{-4}$), a lead that holds under test-time augmentation and across two independent training runs, and in the mean on U-Net, Attention U-Net and TransUNet. Residual encoders close the gap: a ResNet-34 UNet++ exceeds FETALFusion, and an ImageNet initialised ResNet-34 U-Net is best overall (HD95 1.75 mm). The ablation agrees. Calibrated against run-to-run variation, it attributes FETALFusion's measurable gains to the landmark shape prior and, on transperineal images, to the domain gates, while removing the state-space branch does not measurably change accuracy. HC from the predicted masks agrees with the clinical reference at an intraclass correlation of 0.9986. --- ### HaloBlock: Faster and Better Decoding for Diffusion Large Language Models Authors: Zhaohui Zheng, Chenhang He, Jinrui Zhang, Ming-Ming Cheng, Lei Zhang Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.17948v1 Diffusion large language models (dLLMs) have attracted increasing research attention due to their bidirectional attention and arbitrary order decoding. However, there are two issues in dLLMs inference: the decoding difficulty is dominated by the tokens on the right side of the block, and the block-wise decoding inherently suffers from boundary contextual discontinuity. To tackle these limitations, we propose HaloBlock, a difficulty-aware adaptive halo mechanism for dLLM inference. We first leverage bidirectional cumulative entropy to characterize block decoding difficulty. Then, based on the bidirectional decoding difficulty, we adaptively allocate bidirectional halo regions on both sides of each block to mitigate boundary contextual discontinuity. The difficulty-aware design of HaloBlock smooths cross-block context propagation and lowers decoding difficulty for hard tokens, yielding better generation quality and faster convergence. Evaluated on LLaDA-8B-Instruct, Dream-7B-Instruct and LLaDA-1.5 across mathematical reasoning and code generation benchmarks, HaloBlock demonstrates consistent accuracy improvements and higher inference efficiency. Source codes are publicly available at https://github.com/PolyU-VCLab/HaloBlock. --- ### AI-Enhanced Hyperspectral Imaging for Intraoperative Detection of Low-Grade Glioma: A Clinical Study Authors: Siri Willems, Ishika Jain, Jens De Winne, Siri Luthman, Hamed Zivari Adab, Roeland Vandebriel, Anna Alperovich, Xiaohan Zhang, Ben Stoffelen, Tom De Schepper, Lien Solie, Steven De Vleeschouwer Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.17944v1 Current image-guided neuronavigation techniques, such as intraoperative MRI and ultrasound, are limited by high costs, limited sensitivity and operational complexity. There is a clear need for more efficient systems to enhance intra-operative tumor detection and improve patient outcomes for intrinsic brain tumor resection. Whereas previous intraoperative brain HSI studies have predominantly investigated high-grade gliomas, glioblastomas, or mixed-grade cohorts, this clinical study focuses specifically on low-grade gliomas (LGGs). LGGs strongly resemble normal brain under white light conditions on the operative microscope. This study characterizes spectral differences between healthy and tumor tissue and provides a paired comparison of HSI- and RGB-based classification at matched tissue locations and under identical patient-level data splits. Tumor regions showed consistently lower reflectance, which may be associated with differences in hemoglobin concentration and oxygenation. A range of classification models was evaluated. The 3D CNN, which integrates spectral and spatial features, achieved the highest median ROC-AUC of 74.5%, compared with 67.9% for the spectral-only XGBoost model and 64.0% for the RGB-based model. These results support further investigation of HSI for low-grade glioma classification and quantify its performance relative to conventional RGB imaging in this cohort. --- ### Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification Authors: Ubaid Ur Rehman, Tanmoy Mondal Published: 2026-10-13 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.17939v1 Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction. To improve temporal interpretability, MILLET (Multiple Instance Learning with Temporal Explanation), which combines an InceptionTime encoder with Conjunctive Pooling, provides both classification and temporal explanations. However, MILLET contains approximately 424 K parameters, making it unsuitable for deployment on resource-constrained micro-controllers, and it achieves an overall time-series accuracy of 0.888 and an explanation score of 0.681 NDCG@n. We therefore propose SEA-Net, a lightweight architecture using small multi-scale depthwise-separable convolutional TSC encoders and improved Multiple Instance Learning (MIL) pooling heads. Our SEA-Net bottleneck encoder with Top-k pooling achieves 0.931 accuracy and 0.765 NDCG@n with only 41 K parameters. Another variant, using a gated encoder with Top-k pooling, achieves 0.955 accuracy and 0.750 NDCG@n with 62 K parameters. These results demonstrate that lightweight architectures can maintain strong classification performance and temporal explanations while substantially reducing model size. The proposed variants address specific limitations of the pooling strategy used by MILLET, providing a practical direction for interpretable time-series classification on resource-constrained edge devices. --- ### MERIT: Multimodal Evidence Reasoning over Image Tables Authors: Haoyang Jiang, Zhuotong Fan, Mingyang Yi, Ju Fan, Lanqing Hu, Xiao Zan Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.17937v1 Table reasoning with language models typically assumes access to clean textual tables. In practice, tables are often serialized into text, which can corrupt cell contents, distort structural relationships, and discard visual cues, leaving the model to reason over incomplete evidence. In contrast, table images retain this information, but using it requires both accurate perception and reasoning grounded in the relevant cells. To address this, we propose MERIT (Multimodal Evidence Reasoning over Image Tables), a three-stage framework for learning to reason over table images, with serialized tables serving as optional auxiliary inputs (if provided). Our analysis identifies visual evidence acquisition as a bottleneck, motivating table-specific encoder adaptation through reconstruction, localization, and color-conditioned supervision. Building on the adapted representations, supervised fine-tuning teaches explicit evidence selection and reasoning using verified trajectories. Finally, reinforcement learning refines the policy with separate rewards for evidence correctness, calculation, final answers, and output format. By providing feedback on intermediate steps, the framework targets retrieval and computational errors that final-answer supervision alone does not distinguish. We evaluate the approach on table question answering and fact verification, analyze the contributions of visual inputs and training components, and assess generalization to additional datasets with different table structures and visual presentations. --- ### PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splatting Authors: Tingjun Li, Yuxi Wang, Guoqiang Zhong, Zhaoxiang Zhang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17936v1 Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics with deterministic deformation fields, assuming each Gaussian follows a distinct geometric trajectory over time. This assumption breaks down underwater, where light scattering, refraction, marine snow and low visibility create substantial physical ambiguity in captured images. We present PUGS, a physics-guided uncertainty model for underwater dynamic 3DGS. PUGS learns inherent uncertainty induced by underwater image formation and leverages it as a physical signal for dynamic scene modeling. Rather than estimating a single deterministic displacement, it parameterizes each Gaussian's motion as a probability distribution with expected deformation and physical uncertainty. We adopt stochastic deformation optimization to sample Gaussian trajectories via local reparameterization, exploring multiple physically plausible solutions during training. We further propose uncertainty stochastic annealing and a dual-path self-consistency distillation objective, converting stochastic exploration to deterministic reconstruction while preserving temporal coherence. Extensive experiments on underwater dynamic datasets and physics-aware benchmarks demonstrate superior rendering quality, temporal consistency and reconstruction robustness. Our method achieves 1.16 dB PSNR gain over the strongest baseline on UVEB and 3.99 dB on DRUVA. --- ### HierarchiRetina: A Diabetic Retinopathy Screening and Grading Cascade with Heterogeneous Mixture-of-Experts Lesion Segmentation Authors: Md Asif Uddin, Niloy Farhan, Rafeed Rahman, Md. Golam Rabiul Alam Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.17933v1 Clinical screening for diabetic retinopathy proceeds in stages, yet most automated systems grade fundus images with a single black-box network. Three gaps remain: (i) lesions differ widely in size and contrast, but segmenters typically apply the same blocks to all; (ii) ungradable images are usually excluded or treated as an extra class, and lesion-aware graders seldom test whether lesions drive the grade; (iii) staged systems often report each stage only on the images reaching it, leaving propagated errors unmeasured. HierarchiRetina, a screening, segmentation and grading cascade with inspectable stage outputs, addresses each gap. First, HSMoE-AUNet is a U-Net whose skip, bottleneck and decoder blocks are sparse mixtures of heterogeneous experts, with lesion-matched types, counts and losses; SwinHRUNetPP, a dual-encoder vessel segmenter, uses a field-of-view-restricted loss. Second, LG-DRG separates gradability from ordinal severity and lets lesion masks query the image through gated cross-attention. Third, an end-to-end evaluation counts screening misses as errors and traces each error to its stage. Pooled Dice ranged from 0.184 (microaneurysms) to 0.579 (exudates); vessel Dice was 0.731. On 58,689 held-out images from six datasets, end-to-end quadratic weighted kappa was 0.804, with referral sensitivity 0.832 at specificity 0.947, and the screening gate caused 66% of errors. In ablations, the grade ignored the masks, even with the cross-attention gate started open. On all 4,105 official DDR test images, six-class accuracy was 85.6%, above the best published six-class result we found (83.8%). Staged screening systems should be evaluated end-to-end, with stage attribution and mask ablation, before clinical deployment. --- ### Learning How to Remember: Memory Modality Selection for GUI Agents Authors: Taeyun Roh, Suhyeong Park, Gijin Kim, Wonjune Jang, Jaewoo Kang Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.17928v1 Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a promising approach for reusing knowledge from past interactions. However, existing memory augmented GUI agents typically adopt a fixed representation strategy, providing retrieved experience as a static modality. It remains unclear whether a single memory modality is consistently optimal, or how modality preference changes across interaction steps. In this work, we conduct a systematic study of memory modality in VLM based GUI agents. Across GUI benchmarks, we find that the preferred memory representation is strongly step dependent. Motivated by the finding, we introduce \textbf{SwitchMem}, a routing framework that dynamically selects between textual and visual memory representations at each step. Across three GUI benchmarks, SwitchMem outperforms memory augmented baselines that rely on static memory representations. Our findings validate our claim that memory modality is a step dependent decision rather than a fixed design choice. Code and project resources are available at https://txxnrd.github.io/switchmem ---