# Research Papers — 2026-10 · bundle page 125 of 156 > Full-text markdown of papers #6201–6250 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/125 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/124.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/126.md) ### Bradley-Terry model under general comparison graphs Authors: Ruijian Han, Yuanhang Luo, Yiming Xu Published: 2026-10-05 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2610.06237v1 The Bradley-Terry model is a parametric model for ranking from pairwise comparisons. Existing asymptotic theory for the maximum likelihood estimator (MLE) in regimes where the number of objects grows often requires homogeneity assumptions or compatibility conditions on comparison graphs, which limits its applicability to many practical settings. In this work, we establish uniform consistency of the MLE under general deterministic comparison designs. Our pairwise error bound consists of a pair-specific term governed by the effective resistance between the corresponding objects and a global term governed by the spectral gap of the unnormalized graph Laplacian. The bound is tight up to logarithmic factors for certain graph sequences. For any prespecified sequence of pairs satisfying an additional balancing condition, we further establish asymptotic normality of the corresponding estimated utility differences. As an application, we obtain uniform consistency for independent-edge random graph designs whenever the minimum edge probability exceeds the Erdős-Rényi connectivity threshold by a logarithmic factor, as well as asymptotic normality under additional balancing conditions. --- ### DP-ES: Differentially Private Evolution Strategies for Prompt Optimization Authors: Ziniu Liu, Aiping Li, Yue Han, Han Yu, Junjian Zhang, Dong Zhu, Changjian Li, Shiqiang Zhang Published: 2026-10-05 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2610.06236v1 Token-level differentially private (DP) prompt optimization methods such as DP-OPT can become unstable under tight privacy budgets: on GSM8K, DP-OPT obtains $49.5\pm28.5\%$ across 30 runs, and a logged search trajectory reveals prompt-template drift and noise-sensitive irreversible choices. We diagnose these as structural consequences of greedy token-by-token construction over privately aggregated counts. We then propose DP-ES (Differentially Private Evolution Strategies), a structurally cleaner alternative that maintains a population of full prompts, mutates them via LLM calls that never access the private dataset, and spends privacy only on sampled-Gaussian evaluation; deterministic or Gumbel-smoothed selection is post-processing. Under a conservative $(\varepsilon\leq1.0,δ=10^{-5})$ guarantee, DP-ES achieves 88.1% on GSM8K (+38.6 pp over DP-OPT, approximately 9 times lower standard deviation), 99.7% on MedQA, 73.5% on BANKING77, and 86.8% on Alpaca. It is also 2.5 times faster in wall-clock time and uses 3.3 times fewer logged private-data call groups than DP-OPT. Selection and population ablations, implementation-level noise checks, and a 200-profile exact-match memorization stress test complement the formal guarantee. Scope: Our experiments establish optimization robustness under DP noise, especially where prompt structure is critical; end-to-end validation on genuinely sensitive, non-saturated deployment data remains future work. --- ### Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies Authors: Shaohan Jiang, Jiahang Cao, Qiduo He, Fengting Deng, Kun Wu, Jingkai Sun, Jiaxu Wang, Qiang Zhang, Qihao Zheng, Chunfeng Song, Ping Luo, Andrew F. Luo Published: 2026-10-05 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.06235v1 Instruction following is central to language-conditioned robot policies: language should determine what to do when the same scene permits multiple valid actions. Yet successful execution alone cannot establish whether a policy follows the instruction or infers the task from the scene. We study this ambiguity through scene-preserving instruction interventions, using valid target substitutions, arbitrary nouns, and unrelated sentences while holding the scene fixed. We evaluate vision-language-action (VLA) policies and world-action models (WAMs) in simulation and in real-world experiments. Our analysis addresses three questions: (a) Does task success imply instruction following? When instructions request a different visible object, all evaluated policies predominantly approach and pick up the incorrect original target associated with the scene. (b) Is this failure caused by language insensitivity? Instruction perturbations affect task performance. A layerwise action lens shows intermediate action predictions respond to these perturbations. Linear probes accurately recover instructed targets, indicating modified instructions are encoded despite rarely determining target selection. (c) Why does encoded language fail to control action? Attention analysis indicates weak instruction-token contributions to action generation. Target-token attention can remain focused on the original object, revealing a mismatch between target encoding and visual grounding. UMAP and shared non-negative matrix factorization show target information remains accessible within representations increasingly organized by scene identity. Our findings expose a grounding gap concealed by nominal success and provide a diagnostic framework. They further establish a concrete criterion for progress: policies should reliably follow valid changes in user intent, even when they conflict with scene-favored behavior. --- ### Joint Class-Time Learning for Video Classification with Multi-Instance Partial-Label Learning Authors: Lingyu Shen, Wei Tang, Fakhri Karray, Min-Ling Zhang Published: 2026-10-05 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.06234v1 Multi-instance partial-label learning (MIPL) addresses inexact supervision in both the instance and label spaces, which can be applied to video classification. However, bag-level labels do not explicitly supervise the correspondence between candidate classes and temporal evidence. We propose {\ours}, which couples label disambiguation with temporal evidence allocation through a joint class--time assignment. Occupancy-regularized spherical matching associates contextualized video features while learning nonuniform temporal mass and discouraging excessive concentration. During training, candidate-restricted inference recomputes the assignment within the candidate label set. A dual-marginal KL projection then constructs a structured teacher that incorporates momentum-refined class beliefs while preserving the proposal's temporal occupancy. A single plan-level KL objective aligns the full-space predictor with this teacher. Our analysis characterizes when candidate re-solving differs from masking and shows that, under the stated construction, the joint objective decomposes into class-marginal and class-conditional temporal supervision. We construct VCMIPL benchmarks from Breakfast, DoTA, and FineAction using model-generated candidate labels and evaluate the method across four feature representations. Extensive experimental results demonstrate that PIVOTMIPL outperforms existing MIPL algorithms in both effectiveness and efficiency. --- ### AUTOPILOT An Advanced Perception, Localization and Path Planning Techniques for Autonomous Vehicles Using YOLOv7 and MiDaS Authors: Harshkumar Devmurari, Gautham Kuckian, Prajjwal Vishwakarma Published: 2026-10-05 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2610.06232v1 Self driving vehicles have emerged as a reliable technology that has the capability to transform transportation and mobility. The development of self driving cars requires significant advances in a number of areas, including perception, localization, decision making, and control. This research paper is based on the project implementation of the combination of object detection using YOLO (You Only Look Once), depth sensing using MiDaS for the localization and perception of obstacles, perspective transform, and decision making for path planning in self driving cars. The contemporary state of the technology for object detection, depth sensing, localization, and path planning evaluates the performance of the combined system through simulations and experiments. The results show that the combination of YOLO and MiDaS provides a new robust system for object detection and depth sensing. This research paper contributes to the advancement of self driving car technology and provides new and innovative approaches to the perception and localization of obstacles in the environment. Keywords: YOLO, MiDaS, perception, localization, decision making --- ### Parameter Estimation in Machining Dynamics with Regenerative Delay and Nonsmooth Friction using Physics-Informed Neural Networks Authors: Meiyazhagan Jaganathan, Vikram Pakrashi, Aasifa Rounak Published: 2026-10-05 Categories: cs.LG, nlin.CD arXiv: https://arxiv.org/abs/2610.06230v1 A multi-domain eXtended Physics-Informed Neural Network (XPINN) framework is developed for nonsmooth Delay Differential Equations (DDEs). This is the first implementation to demonstrate the efficacy of partitioning the temporal domain into subdomains of integer multiples of the characteristic time delay and progressively training the associated subnetworks while freezing previously learned parameters. The efficacy of the proposed framework is demonstrated using a machining dynamics model that incorporates both regenerative and nonsmooth frictional effects. Results demonstrate that the proposed multi-domain XPINN framework leads to better solution reconstruction in DDEs and improved parameter estimation compared to a generic PINN (SPINN) formulation. The proposed method works particularly well for extended temporal domains and non-constant history functions. The robustness of inverse XPINN (I-XPINN) is also assessed using reference data contaminated with Gaussian measurement noise. Results indicate that I-XPINN remains resilient to measurement noise and the physics-informed constraints guide the network toward accurately recovering the underlying dynamics. This demonstrates, for the first time, the potential of the proposed framework for reliable parameter identification in DDEs characterised by nonsmoothness and large time delays. --- ### SO(3)-RoPE for Spherical Transformers Authors: Christian Libner, Chase van de Geijn, Alexander S. Ecker, Maurice Weiler Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06229v1 Spherical data arise in many scientific applications. Often spherical transformers disregard the geometry of the underlying spherical domain, causing distortions and coordinate singularities near the poles. We introduce SO(3)-RoPE, a relative positional embedding that incorporates spherical geometry into transformer attention through unitary SO(3) representations. Our formulation is SO(3)-equivariant and compatible with FlashAttention, retaining efficiency of vanilla transformers. On shallow water dynamics prediction over a rotating sphere, our SO3ViT outperforms an S2Transformer baseline with lower errors and reduced runtime. --- ### APOD: reasoning-guided agentic population ordinary differential equation discovery for pharmacological digital twins Authors: Romain Ferrara, Martin Soucail, Victor Gertner, Adil Moussali, Joris Cocquebert, Sandrine Oziel-Taieb, Julien Nicolas, Florence Gattacceca, Mihaela van der Schaar, Sébastien Benzekry Published: 2026-10-05 Categories: q-bio.QM, cs.AI, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2610.06227v1 Establishing ordinary differential equations (ODEs) describing population data is a fundamental part of mathematical modeling in pharmacology, crucial to developing digital twins. However, doing so from sparse, noisy data is a slow, expert-driven task. Existing automated methods either search a restricted model space or ignore population inter-individual variability. Here we introduce APOD (Agentic Population ODE Discovery), a language-model agent that iteratively reasons over biological knowledge and fit diagnostics in an open-ended search space to discover a population digital twin (PDT), i.e., a shared ODE system with between-subject variability. On synthetic pharmacokinetic and tumor-dynamics benchmarks, APOD recovered ground-truth structures in 94-100\% of runs, 12-fold faster in median than an established library-based search. On real cohorts it converged to valid structures, and proposed a PDT of radioligand-therapy-induced platelet dynamics that predicts thrombocytopenia from first-cycle data and simulates alternative dosing schedules that lower the predicted risk of toxicity. --- ### LeAVJEPA: A Minimalist Architecture for Audio-Visual Self-Supervised Learning Authors: Benjamin Robson, Santeri Mentu, Wenshuai Zhao, Arno Solin Published: 2026-10-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.06226v1 Prior audio-visual self-supervised learning methods rely on mechanisms such as EMA target encoders, prediction heads, reconstruction decoders, and contrastive losses. We introduce LeAVJEPA, the first audio-visual encoder trained under LeJEPA's collapse-free objective. A single early-fusion Vision Transformer processes audio, video, and joint audio-video inputs. Modality dropout treats a missing modality as another view of the same event, making cross-modal alignment implicit in the objective. The model aligns global embeddings with modality-specific local embeddings, and SIGReg prevents representational collapse. A controlled ablation identifies modality dropout as the key mechanism for audio-visual alignment. Despite the architectural simplicity, LeAVJEPA reaches 36.0 mAP on AudioSet-20K and 91.3% accuracy on ESC-50 under frozen evaluation. After fine-tuning, it reaches 61.1% accuracy on VGGSound, and its embeddings support zero-shot audio-visual retrieval. --- ### Frequency-Decoupled Diffusion Guidance for Non-Blind Image Deblurring Authors: Sihan Wang, Jinshu Huang, Haibin Su, Yunhua Xue Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06221v1 Pretrained diffusion models provide powerful image priors for training-free posterior sampling in image restoration. To guide this sampling process, frequency-aware methods progressively incorporate measurement information across frequency bands, facilitating coarse-to-fine reconstruction. However, existing methods typically do not explicitly separate frequency activation from degradation-induced attenuation, leaving attenuation differences among inactive frequencies insufficiently modeled. In this work, we propose frequency-decoupled posterior guidance to separate frequency activation from attenuation-aware spectral regularization. Specifically, a progressive low-to-high frequency schedule determines the active measurement band, while a kernel-derived attenuation map defines a selective spectral prior over inactive components. To stabilize the sampling process, we also introduce a local trajectory regularizer that suppresses spatially irregular state-to-clean deviations. For a fixed endpoint energy, we provide a KL-regularized path-space interpretation. In practice, we construct time-dependent guidance through local energy corrections using a Tweedie plug-in approximation. Experiments on natural-image benchmarks demonstrate strong PSNR and SSIM performance across challenging non-blind deblurring settings, even at higher measurement noise levels. --- ### Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing Authors: Andrea Paganelli, Stefano Civelli, Pietro Bernardelle, Gianluca Demartini Published: 2026-10-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.06216v1 Pre-generation success probes estimate response correctness from a language model's hidden activations before decoding, enabling cost-aware routing. While prior work has demonstrated their utility primarily on English inputs, we study their reliability across languages along three dimensions: (1) whether they preserve the ranking of likely successes and failures (DISCRIMINATION); (2) whether they retain probabilities that match observed success frequencies (CALIBRATION); and (3) whether they produce scores comparable enough across candidate models for cost-aware multilingual routing (UTILITY). Using 3,000 MATH problems in 10 languages and 8 open-weight model configurations, we compare cross-lingual transfer from English-trained probes and equal-budget pooled multilingual probes. English-trained probes retain useful cross-lingual discrimination but become less well calibrated after transfer. Pooled multilingual supervision improves both properties and yields more reliable estimates of success. In routing experiments, the pooled router achieves a 0.7% higher test success rate while reducing modeled cost by 13.0% relative to always selecting the model with the highest average success. These results show that multilingual routing requires success estimates that remain well calibrated and comparable across languages and models. --- ### Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime Authors: Yujie Liu, Vincent Y. F. Tan, Yunbei Xu Published: 2026-10-05 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2610.06213v1 We study the sampling allocation of LinUCB in the small-gap regime, where the reward gaps are of order at most $n^{-1/2}$ over the decision horizon $n$. This scaling captures the hard instances underlying worst-case regret lower bounds, for which LinUCB is known to be near optimal up to logarithmic factors in $n$. Using a mean-field perspective, we characterize this allocation through the empirical sampling distribution, a macroscopic object that averages the effect of adaptive decisions over the horizon, and identify its limit as $n\to\infty$. We establish that in this regime, the empirical sampling distribution induced by LinUCB converges to the set of D-optimal designs. This central result reveals that, in the small-gap regime, LinUCB not only achieves near optimal minimax regret but also allocates samples in a way that is asymptotically efficient for learning the reward parameter, thereby connecting regret-driven online learning with information-efficient experimental design. Building on the optimal design limit, we obtain two useful consequences. First, we refine the asymptotic regret analysis of LinUCB in the small-gap regime by characterizing its leading-order constant in the limit. Second, we show that, despite LinUCB's adaptive sampling strategy, the regularized least-squares estimator satisfies a central-limit-type theorem in the small-gap regime, thereby enabling valid statistical inference for the reward parameter. --- ### Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant? Authors: Perceval Beja-Battais, Alain Grosset{ê}te, Nicolas Vayatis Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06211v1 Learned models for industrial control are usually judged by aggregate accuracy, but accuracy at the component level does not guarantee safety once it is embedded in the system it is meant to serve. We study this gap on a behavior-cloning task: imitating an expert Nonlinear Model Predictive Control (NMPC) policy for load-following of a Pressurized Water Reactor (PWR), an industrial system with tight safety constraints. We propose a structured architecture encoding variables from each timescale into separate latent spaces, reflecting the physical decomposition of the system, before training a controller to imitate the expert on the product latent space. On long-horizon rollouts, separated embeddings improve both accuracy and feasibility compared with a shared-embedding baseline. Sensitivity analysis further shows that our model yields interpretable representations aligned with the system's physics. However, standalone deployment still leaves several percent of trajectories infeasible regardless of the architecture. Using our method to warmstart the NMPC optimizer rather than acting standalone, we recover full feasibility and near-optimal cost while still cutting computation time by $\sim$15% relative to the expert controller, and even more for abrupt operating changes. --- ### MoCAR: Motion-code Coordinate-aware AutoRegression for Continuous Trajectory Forecasting Authors: Yiming Xu, Hao Cheng, Monika Sester Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06210v1 Autoregressive generation is natural for language, where predicted tokens can be directly reused as the next prediction state, but trajectory forecasting lacks such a clean token: motion is continuous, multimodal, and expressed in local coordinate frames that evolve with the predicted trajectory. We present MoCAR (Motion-code Coordinate-aware AutoRegression), a decoder-only framework that casts trajectory forecasting as next-code prediction in a coordinate-aware continuous latent space. MoCAR learns a continuous motion-code space from endpoint-normalized trajectory segments, where each code jointly captures local trajectory geometry and the reference-frame transition induced by that segment. Historical motion codes are used as a teacher-forced prefix, future codes are generated autoregressively under temporal, map, agent, and mode interactions, and predicted codes persist in latent memory while decoded endpoints update the local scene context. This enables rollout without trajectory-space re-tokenization, trajectory queries, goal candidates, or proposal-and-refinement pipelines. On Argoverse (AV) benchmarks, MoCAR achieves top-tier performance with a simple single-stage architecture, transfers strongly from AV2 to AV1 in zero-shot evaluation, and improves on turn-heavy scenarios. Ablations confirm that the learned continuous motion-code space, latent alignment, weak KL regularization, and joint tokenizer-predictor optimization are essential for stable latent autoregression. --- ### AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation Authors: Amin Jalali Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06207v1 Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agents are increasingly embedded in operational business processes. Yet Business Process Management (BPM) curricula and frameworks still largely treat artificial intelligence (AI) as an add-on technology, leaving graduates (as potential future process developers) unprepared to reason about AI as a first-class design element of end-to-end processes. This paper addresses that gap by proposing \emph{AI-decision checkpoints}: explicit moments in a process development trajectory where process developers identify AI-candidate sub-processes, assess expected effects on time, cost, quality, and flexibility, consider legal and organisational constraints, and document a reasoned decision to adopt, constrain, or reject specific AI components. The checkpoints are instantiated through a fictitious customer onboarding process as a \textit{BPM Teaching Case}, embedded in a lifecycle-driven framework spanning six modules that combine process modeling, simulation, workflow execution with AI agents, and process mining, with each module's output serving as the next module's input. A preliminary formative reflection draws on instructor observations, submitted artifacts, and discovered process maps from learning-management-system logs. These exploratory observations suggest that the approach supported clearer distinctions between task-level automation and process-level value. --- ### Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers Authors: Pedro Tabacof, Sagar Joglekar Published: 2026-10-05 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.06204v1 LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. Small models are more cost-efficient at scale, but can reinforcement learning train them into competent sellers? We train four Gemma 4 checkpoints (2.3B to 31B effective parameters) with GRPO on a programmatic utility reward for bilateral multi-issue bargaining, and evaluate every arm on the same 1,152 negotiations against two frontier buyers it never saw in training. With the same learning rate ($10^{-6}$) for every size, the gain of the RL model over its base rises from $+0.001$ at 2.3B to $+0.078$ at 31B. Each size was trained once and the two smallest checkpoints use a different architecture, so we fit no scaling law. Tripling the learning rate, with the same or fewer training steps, improves on the shared rate at every size by $+0.032$ (2.3B) to $+0.081$ (4.5B). In exploratory comparisons with two frontier models run as sellers, the 12B seller trained at the tripled rate scores above both, though its untrained base already scores as high as they do. The 4.5B seller at that rate shows no detectable difference from either and fits on one 48 GB GPU. A further 2.3B arm at ten times the shared rate raises pooled score, but its gain concentrates on the evaluation buyer that shares a model family with the training pool. These results suggest tuning the learning rate before concluding that a small model cannot learn to negotiate, and testing against buyers from more than one model family. --- ### EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations Authors: Heli Qi, Zeqi Zhou, Jingjun Yi, Kunyi Liu, Ziyang Lihe, Junjue Wang, Osamu Yoshie, Naoto Yokoya Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06196v1 Remote sensing images often carry composite degradations, in which haze, cloud, noise, blur, low light, and low resolution coexist. Restoring them requires deciding which tool to apply, in what order, and when to stop, yet no clean reference is available at inference time to verify these decisions. All-in-one models trained on single degradations converge to a narrow PSNR band as degradations accumulate. To formulate real-world remote sensing restoration as a traceable trajectory, we present EORestore-Agent, which replaces this unmeasurable objective with reference-free, verifiable per-step decisions. A fine-tuned vision-language model reports all residual degradation types, whose tool pools are scored together, so the restoration order emerges from step-wise selection. A relative quality scorer, trained with full-reference supervision on synthetic degradation chains, predicts the changes in PSNR, SSIM, and LPIPS from the current image to each candidate. A step is accepted only when no predicted change is negative and the predicted PSNR gain is positive. Otherwise, the agent keeps the current image. On a synthetic Landsat-8 benchmark with six degradation types, EORestore-Agent improves PSNR by 2.3 to 3.2 dB over the strongest retrained all-in-one baseline on composites of two to six degradations, whereas zero-shot natural-image agents fall below the degraded input in PSNR in 17 of 18 settings. Replacing the learned scorer with no-reference quality differences costs 1.1 to 4.6 dB. The remaining harmful steps are small and cluster near the acceptance threshold. Sentinel-2 examples illustrate transfer to real atmospheric degradation without retraining. --- ### Loss-Invariant Projections as Passive Probes of Learned Representations Authors: Akshay Chandrasekhar, Pavlo Melnyk Published: 2026-10-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.06195v1 Learned feature representations in neural networks often contain structure beyond that directly used by the final task output. We study this structure using $\textit{passive probes}$ that apply fixed, untrained, property-independent projections to representations as they evolve during training. We motivate this approach through the task of prediction on $S^2$ where equivalent vector and Hermitian parameterizations reveal an additional loss-invariant trace coordinate. This motivates a general construction in which fixed random projections serve as observers of learned features. Because the observer is loss-invariant and independent of the property being studied, changes in accessibility reflect changes in the representation relative to the fixed observer rather than adaptation of the observer itself. We show that ensembles of passive probes can directly reflect task-relevant information such as target alignment. Under our constructions, the accessibility of eventual difficulty evolves differently across tasks. It increases during training in the regression tasks of surface-normal estimation and image inpainting but remains near its initial level in image classification. Comparisons with learned linear probes further show that recoverability and passive accessibility can evolve differently during training. Together, these results show how passive probes can separately characterize changes in representation geometry and the accessibility of eventual task difficulty. --- ### Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents Authors: Hai Dang Truong, Rayner Goh, Thanh Le-Cong, Yintong Huo Published: 2026-10-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.06193v1 Autonomous coding agents now resolve a substantial share of real-world GitHub issues. However, passing functional tests differs fundamentally from producing a high-quality contribution acceptable for merging. Mature open-source projects publish repository-specific contribution policies, spanning style, git, testing workflows, to ensure code quality and long-term maintainability. Because existing benchmarks evaluate patches solely on unit tests, agent compliance with repository governance remains unknown. In this paper, we introduce SWE-CC, a benchmark evaluating code and process compliance in autonomous software engineering. We develop a semi-automated pipeline that converts developer documentation across 12 open-source repositories into 823 machine-checkable atomic policies. SWE-CC introduces two features: 1) lightweight, deterministic checker functions that represent each policy, 2) a comprehensive auditing mechanism that inspects both agent runtime behaviors and final deliverables. We evaluate the compliance of agent workflows in 500 end-to-end software contribution tasks extended from SWE-bench Verified. Our evaluation of four LLMs under two agent scaffolds shows that modern agents suffer from coding compliance issues: although agents produce functionally correct patches, they still violate 43.1 percent of applicable project policies, with nearly half of all violations occurring during intermediate execution steps. These results show that functional correctness does not guarantee real-world readiness, highlighting that future software engineering agents must reliably conform to repository governance to enable safe and trustworthy deployment. --- ### Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems Authors: Jianxin Gao, Runze Li, Tianyi Yu, Liangwei Ren, Bohan Chen, Zining Wang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06192v1 Multi-agent systems built on large language models (LLMs) restate observations as a matter of course: relays forward them, shared boards repeat them and discussion rounds echo them. An aggregator that pools such messages should count sources, not statements. We convert a reported probability into units of independent readings, which assigns every restatement a copy weight, 0 for an aggregator that counts sources and 1 for one that counts every statement, and yields the implied decision under any cost structure. Three testbeds hold the evidence fixed and vary how it is restated: message logs with an exact Bayesian oracle, web documents with appended copies, and logs written by LLM agent teams under four communication protocols. Across four models from three providers, a forwarded copy counts for 0.06 to 0.42 of a new reading, mostly because some replies count every statement. On 5% to 40% of logs that state one reading three times, the reported belief implies an early commitment that the oracle never makes. The models that count copies least and most on controlled logs do so on web copies and agent-written logs as well. A one-paragraph declaration of what a copy contributes brings the copy weight on controlled logs to 0.08 or less. A rule that has agents refer to readings instead of restating them cuts belief-implied early commitment from 11.2% to 1.1% and preserves genuine corroboration. --- ### Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions Authors: Chubin Zhang, Zhenglin Wan, Xingrui Yu, Jingxuan Wu, Yaxin Zhou, Ivor Tsang, Bo An Published: 2026-10-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06191v1 An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge results from what they do. We compare stopping at the same step after longer and shorter runs of results the agent judged useless; this contrast is zero for clock- or deadline-driven stopping. Where we record their judgments, the seven agents we test call a failing source's results useless 97-100% of the time, yet most of them rarely stop on that judgment. Prompt cues change when they stop but not what they stop on. Permission to answer from memory and a reasoning mode can bring early stops regardless of evidence, a stated budget moves the 7-8B models' stops to the deadline, and a stopping rule or call cost in the prompt is followed at most partly. Stopping follows the evidence only when the harness enforces an integration step that makes the agent answer after five consecutive results it judged useless. This step raises failing-source success for every model, keeps the stopping point fixed when the budget doubles, and needs no extra judgment call when the agent states its judgments. A pre-registered replication on 300 fresh questions confirms the dissociation and the rule's effect. --- ### Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design Authors: Haosen Zhang, Yang Yang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06190v1 Large language models (LLMs) can reason over scientific literature to devise design strategies, yet fail to reliably implement them for biological sequences. While protein generative models learn sequence patterns, they lack the capacity to incorporate literature evidence for multi-step reflective reasoning, forming an evidence-to-execution gap between scientific reasoning and sequence manipulation. We present EASER (Evidence-Aware Sequence Engineering with Reflection), a reflective agent bridging reasoning and sequence generation via a learned property interface of offline-trained, fixed low-rank matrices. The agent steers a diffusion generator by combining these matrices, proposing intervention hypotheses (anchors, editable positions, control coefficients) grounded in retrieved evidence, sequence context and past results. A Probe-and-Steer mechanism validates interventions and allocates samples according to predicted property responses, with outcome reflection informing subsequent decisions. Evaluated on multi-objective antimicrobial peptide design (optimizing activity, non-hemolysis and non-toxicity), explicit hypothesis formulation delivers better multi-objective performance than direct action generation under identical decision conditions. Ablation studies verify the importance of evidence retrieval, episodic history, reflection and Probe-and-Steer. Over six repeated trials, EASER obtains the highest mean hypervolume and lowest mean IGD+ on screened candidates compared with competing baselines. Our work demonstrates how an executable property interface and iterative feedback link scientific reasoning to targeted peptide sequence generation. --- ### Two-Point Local Optimality in $k$-Means via Boundary-Point Screening Authors: Wenlong Lyu, Xujie Xiao, Yuheng Jia Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06182v1 Lloyd's algorithm and the discrete local (D-local) optimization method (Li et al., 2025) for $k$-means provide only weak local-optimality guarantees, and their solution quality remains sensitive to initialization. In this paper, we introduce $r$-point local optimality, under which no reassignment of at most $r$ samples decreases the objective function, and focus on $r=2$. The main computational obstacle is the $\mathcal{O}(n^2(k^2+d))$ cost of exhaustive two-point certification for $n$ samples in $d$ dimensions and $k$ clusters. To address this challenge, we prove that (i) every improving two-point move of a D-local optimum must involve a cluster shared by both reassignments, and (ii) only certificate-defined boundary points can participate in an improving pair. Exploiting this structure, we propose Boundary-Point-Screened Two-Point Local Search (BPS-2PLS), which terminates at a two-point local optimum. For fixed $k,d$ and nonvanishing cluster occupancy, the number $m$ of retained candidates satisfies $m=\mathcal{O}_{\mathbb{P}}(\log n)$ under i.i.d. sampling from a bounded-support distribution with bounded density or from a Gaussian mixture. Across twelve benchmarks, BPS-2PLS attains the lowest available mean WCSS on ten. In a subsampling study, screening retains 0.10% to 2.81% of samples on average at the largest tested sizes. The code is available at https://github.com/lwl-learning/BPS-2PLS. --- ### Anlu: Enabling In-Context Time Series Anomaly Detection in Foundation Models via Counterfactual Supervision Authors: Tian Lan, Yifei Gao, Yimeng Lu, Xuming An, Meng Wang, Yue Pan, Wenjun He, Chen Zhang Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06180v1 Whether a time-series pattern is anomalous often depends on the operating regime of the monitored process. A missing event can signal a fault in one regime and be routine in another, and the query alone may not reveal which regime applies. We study in-context learning (ICL) for time series anomaly detection (TSAD) through reference-conditioned detection, where a reference record provides evidence about expected behavior and model parameters remain fixed at inference. Supplying the reference is not enough: when training anomalies are recognizable from the query alone, the detector can fit its targets while ignoring the reference. We therefore introduce counterfactual supervision, which pairs one query with two references that support different normal rules and labels the query under each. At positions where the two labels disagree, no detector that ignores the reference can fit both targets. Anlu learns from this supervision by adding a reference memory and zero-initialized gated adapters to a frozen time-series foundation model (TSFM) pretrained for anomaly detection. On the 350 TSB-AD-U evaluation sequences, Anlu raises the mean VUS-PR of the frozen TSFM from 0.542 to 0.607. Replacing the reference with zeros lowers Anlu's score to 0.499. --- ### Auditable Clinical Timeline Reconstruction with Provenance-Aware Evidence Graphs Authors: Judith Jeyafreeda Andrew Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06177v1 A patient-timeline reconstruction system is auditable only if it keeps the mentions behind each answer, records how facts were revised, and declines to answer when the evidence is not in the text. This study tests these three properties on a fully synthetic corpus (1,000 patients, 3,353 notes, 220 revision edges). Two provenance-aware Evidence Graph operators reduced the node-plus-edge count to 67% and 63% (77-78% of serialized size) while preserving every answer and mention link across 6,813 query points answerable by recency; a fixed-window baseline returned no value for 53.4% of points, unflagged. On evidence-unavailable controls that announce the omission, a BioClinicalBERT gate and a zero-shot LLM gate responded mainly to the announcement. On marker-free controls, BERT abstained on 0 of 81 notes while its accuracy fell from 93.8% to 59.3% across all three relation classes; the LLM's coverage fell from 75.6% to 27.7% on notes its own model family judged undeterminable. Against 482 regenerated gold spans, the LLM's cited evidence reached recall 0.850 and precision 0.864; BERT's span head, trained without span labels, did not localize evidence. A temporally versioned provenance graph stored abstentions as typed, queryable edges. The clean task admits a 0.651-accuracy shortcut, and results describe implementation behaviour on synthetic data, not clinical performance. --- ### What Does It Cost to Simulate a Quantum Sentence Classifier? An Energy and Compute Perspective on Near-Term QNLP Authors: Kishlay Kashyap, Sandipan Ganguly Published: 2026-10-05 Categories: quant-ph, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.06176v1 Near-term quantum natural language processing (QNLP) experiments often run on classical simulators, so simulator cost is part of the field's practical compute burden, yet accuracy tables do not show it. We measure that cost for a variational quantum classifier (VQC) on binary SST-2 sentiment classification, using PennyLane's state-vector simulator over a controlled grid of 27 configurations: three balanced training-set sizes (N = 200, 500, 1000), three qubit counts (4, 6, 8), and three circuit depths. Each VQC is compared with logistic regression on the same PCA-reduced input; full TF-IDF logistic regression gives an uncompressed reference. The VQC beats its matched baseline in 6 of 27 single-seed comparisons. After reruns at two further seeds, only 1 of these 6 keeps a positive mean advantage larger than its paired seed-to-seed variability, and paired tests on the fixed validation set do not establish it. VQC training is 886-21,127 times slower in measured wall-clock time than the matched classical fit (median 3,158 times); going from 4 to 8 qubits roughly doubles simulator time, and within the tested range per-step cost is well approximated by a linear function of the parameter count. CodeCarbon energy and CO2 estimates are secondary: they imply an almost constant power of about 41 W, so they add little beyond runtime, and we do not build an energy ratio from them. The study is narrow (one dataset, representation, ansatz, simulator, and CPU environment) and is a reproducible feasibility measurement, not a general verdict on QNLP. --- ### Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate Authors: Yoshihiro Izawa, Gouki Minegishi, Yoko Yamakata Published: 2026-10-05 Categories: cs.LG, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2610.06174v1 Can LLMs recognize degradation in their own computational substrate? Inspired by anosognosia, a neurological condition in which patients fail to recognize impairments in their own abilities, we investigate whether LLMs can recognize degradation in their computational substrate induced by quantization. We first show that existing models fail to self-report their quantization state, even when provided with their own generated text as an external cue. Linear probing reveals that, while generated text carries almost no trace of quantization, internal representations contain clear, method-specific fingerprints. Through training, models learn to identify severely degraded outputs such as those of 4-bit models by comparison, yet still fail to do so from a single output. A shared LoRA trained jointly across quantization levels succeeded in reading out internal fingerprints, but fails on unseen quantization methods, merely mapping method-specific fingerprints to labels. Whereas external self-observation can restore awareness in some cases of human anosognosia, our results suggest that the more promising route to enabling such awareness in LLMs may lie in their internal representations. Our results highlight fundamental limits of generalizability to LLM self-monitoring. --- ### MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge Authors: Abdul Basit, Muhammad Abdullah Hanif, Muhammad Shafique Published: 2026-10-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.06170v2 Biomedical large language model (LLM) evaluation requires auditable assessment of narrow, evolving, source-grounded subspecialty knowledge. Multiple sclerosis MRI (MS-MRI) provides a high-stakes textual-knowledge test case because correct reasoning requires current diagnostic criteria, standardized acquisition and reporting knowledge, longitudinal monitoring concepts, lesion morphology, and recognition of difficult mimics. We present MS-Exam-Gen, a reproducible framework for constructing and auditing a text-based multiple-choice question (MCQ) benchmark for MS-MRI knowledge; it does not evaluate direct MRI image interpretation. MS-Exam-Gen targets source-grounded criteria, protocols, reporting, and differential diagnosis. The framework combines expert-source indexing, exam-oriented topic induction, evidence-grounded MCQ generation, automated quality audits, a same-family consistency screen, and empirical calibration. From a 66-source corpus indexed into 4,289 retrieval chunks, the pipeline produced a locked 3,058-item candidate benchmark spanning 16 topics and 53 subtopics. Evaluation across 12 primary LLM endpoints yielded 36,696 item-level predictions and separated performance over a 42.8-percentage-point accuracy range (89.7% to 46.9%). Across these endpoints, 25.5% of items were missed by at least four. Post-generation audits showed that refreshed construction reduced measurable answer cues, while option-order testing showed that absolute MCQ scores remain position-sensitive. Generated construction labels remain metadata rather than validated psychometric categories. Because expert adjudication and full option-order counterbalancing remain future work, MS-Exam-Gen is not a clinically certified examination. It should be interpreted as an automatically filtered, source-grounded candidate benchmark and reproducible audit workflow for item-level and topic-specific LLM evaluation. --- ### Bayesian Optimization in Sequence-to-Architecture Latent Space for Zero-Shot NAS Authors: Ondrej Tybl, Lukas Neumann Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06167v1 Zero-shot Neural Architecture Search removes the prohibitive cost of traditional NAS, but its search process is typically based on the evolutionary algorithm (EA); lacking an explicit model of the objective, it often resorts to a near-random search through mutation. Bayesian Optimization offers a principled alternative by modeling the objective and aggregating information across iterations, but scales poorly to the high-dimensional, discrete, graph-structured spaces of modern NAS, restricting its use to only small networks. In this paper, we bring Bayesian Optimization to zero-shot NAS for large-scale architectures by learning a latent space via a Variational Autoencoder trained to reconstruct a novel prefix encoding of architectures and propose a proxy scalarization that combines several zero-shot proxies into a single Bayesian Optimization objective. After only 10,000 iterations of the proposed search algorithm (8 hours on a single GPU), our method found a network architecture which under the given model parameter count constraints achieves state-of-the-art results on three separate tasks -- image classification, object detection and semantic segmentation. --- ### Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair Authors: Wenji Bai, Muhammad Waseem, Zeeshan Rasheed, Jaakko Peltonen, Pekka Abrahamsson Published: 2026-10-05 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.06163v1 Localizing where an LLM-based agent first fails to uphold security during a repair can show which stage of its workflow needs an additional safeguard. This is difficult for silent failures, which are patches that pass syntactic and functional checks but still contain a security vulnerability. Because such patches give no observable failure signal, existing failure attribution methods, which rely on observed task failures and labelled failure steps, are less suited to them. We propose Security Awareness Gap Evaluation (SAGE), a trace-based method that combines an assessment of the security reasoning recorded at each turn with the reconstructed code history to identify the earliest turn at which a repair diverges from the task's security intent. We evaluate SAGE on 95 confirmed silent failures drawn from 3,684 repair traces produced by six agent frameworks and six base models on SecurityEval and CVEfixes. SAGE assigned an origin in 93 cases. Most origins were an unaddressed security requirement or an inadequate defence choice, and only five coincided with the code change itself. When the agent introduced the vulnerable code, the origin preceded the write in 14 of 19 cases. Repeated scoring and a second judge reproduced the origin type more consistently than the exact turn, and agreement was lowest for traces that kept only the final file. --- ### Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training Authors: Zhuojing Huang, Luise Pohlmann, Lisa Beinborn Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.06161v1 During language acquisition, bilingual children are regularly exposed to code-switched input and use it as a cognitive scaffold to accelerate vocabulary growth and cross-linguistic syntactic mapping. In contrast, computational bilingual models are conventionally pretrained on interleaved monolingual corpora. While introducing synthetic code-switching during pretraining has become a promising strategy to enhance cross-lingual alignment and downstream performance, the structural and developmental parameters governing the success remain poorly understood. In this work, we investigate the efficiency of training with synthetic code-switched data across two typologically distinct language pairs by controlling two key variables: the structural location of code-switches and the dynamic switching rate across training stages. Our results show that training with code-switched data improves cross-lingual alignment for typologically close languages. --- ### TIGER: Time-Series Classification with In-Context-Learning Gated Ensemble of Representations Authors: Johann Faouzi Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06156v1 A representation family is a distinct way of extracting features from time series. Ensemble algorithms that combine several representation families remain the most accurate approach to time series classification. Current state-of-the-art ensembles, most notably HIVE-COTE~2.0, pair a bespoke classification algorithm with each representation family and combine their predictions using a fixed, non-adaptive rule. We present TIGER (Time-series classification with In-context-learning Gated Ensemble of Representations), which instead applies the same small portfolio of three general-purpose classifiers (Ridge, Extra Trees, and Naive Bayes) to four representations from four distinct families, stacking the resulting twelve base learners' predictions into a meta-feature matrix. The final prediction is produced by an adaptive meta-classification rule that chooses, independently for each data set, between a weighted hard majority vote and TabICLv2, a pretrained tabular foundation model used in-context as a meta-classifier, based on the mean number of training samples available per class. On a 142-data-set benchmark drawn from the UCR time series classification archive, TIGER obtains the best mean accuracy, balanced accuracy, and F1-score among six compared algorithms, including HIVE-COTE~2.0, and significantly outperforms each of the other five individually. TIGER's adaptive rule also meaningfully outperforms either of its two constituent meta-classification methods used alone, and its single hyperparameter, tuned using only a twenty-data-set development subset, is shown to generalize to the full evaluation benchmark. We further characterize TIGER's design through an extensive set of ablation experiments and report the design alternatives that we investigated and ultimately discarded. --- ### Reinforcement Learning-Based Optimization of Workload-Aware Power Delivery Networks Authors: Oran Hayes, Maria Pantazi-Kypraiou, Athanasios Tziouvaras, George Stamoulis, Anuj Pathania, Shreejith Shanker, George Floros Published: 2026-10-05 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2610.06148v1 Power Delivery Networks (PDNs) are critical components of modern VLSI chips, providing stable voltage levels while satisfying electromigration (EM) and IR-drop constraints. Conventional PDN design methodologies typically rely on worst-case assumptions, often resulting in over-provisioned networks and inefficient use of resources. This paper presents a reinforcement learning-based framework for the optimization of workload-aware PDNs. The proposed methodology first generates workload-aware PDNs using architectural power traces obtained from system-level simulations. These power traces are mapped to spatial power density distributions, enabling adaptive allocation of PDN resources according to local current demand. A reinforcement learning agent then performs wire-width optimization to minimize PDN area while maintaining EM and voltage integrity constraints. Electrical and reliability metrics are obtained using SPICE-based circuit analysis and EM lifetime estimation. Experimental evaluation is performed on a dataset of workload-aware PDNs generated from 4-, 8-, and 16-core multiprocessor floorplans using PARSEC and SPLASH-2 benchmark workloads. Furthermore, the proposed Deep Q-Network (DQN)-based optimizer reduces the average normalized PDN area by 47\% while satisfying all EM and IR-drop constraints. Compared to simulated annealing, the proposed approach achieves comparable optimization quality while providing approximately 26$\times$ faster optimization. --- ### Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts Authors: Seungmin Oh, Seunghun Kang, Jongbin Ryu Published: 2026-10-05 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2610.06147v1 Vision-language models (VLMs) achieve strong zero-shot transferability but remain vulnerable to target-domain shifts at inference time. Test-time adaptation (TTA) offers a practical remedy, yet most existing VLM-TTA methods follow a prediction-side adaptation paradigm. They use test samples to adjust logits, prototypes, caches, priors, or feature statistics, often incurring additional computational overhead. In this paper, we take a different perspective and reframe VLM-TTA as candidate verification rather than prediction adjustment. We propose Test-Time Correction (TTC), a hypothesis-based correction framework guided by a simple principle: hypothesize, reconstruct, correct. Given a test feature and its top-k candidate labels, TTC treats each candidate label as a hypothesis, reconstructs the feature within the corresponding latent subspace stored in a memory bank, and measures the resulting divergence shift. This shift quantifies how much the candidate subspace and its relations to other candidates change after the hypothetical insertion of the test feature. A correct candidate hypothesis induces only a small shift, whereas an incorrect one perturbs the subspace more strongly. TTC therefore corrects the prediction by selecting the candidate with the minimum aggregated divergence shift. This training-free candidate-verification mechanism avoids iterative optimization and provides a favorable accuracy-efficiency trade-off. Across five TTA settings and 15 benchmark datasets, including zero-shot classification, domain generalization, few-shot classification, base-to-novel generalization, and cross-dataset evaluation, TTC consistently improves accuracy over state-of-the-art VLM-TTA methods while achieving up to 2x speedup, over 3x lower CPU memory usage, and up to 1.4x lower GPU memory usage than the lowest-memory training-free baseline. --- ### Impact of Data Augmentation on Confidence Calibration in Melanoma Classification Authors: Morgan May, Simon Caton, Pierpaolo Dondio Published: 2026-10-05 Categories: cs.AI, cs.CV, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2610.06146v1 Accurately quantifying the predictive uncertainty or improving model calibration plays an important role in medical image classification, in particular in melanoma diagnosis, where accurate uncertainty quantification can have significant implications for patient care. One of the methods for calibration improvement is data augmentation. In addition, data augmentation as a method for synthetically increasing the size of the dataset has been proven to improve the performance of models trained on imbalanced datasets. However, the impact of data augmentation, as a transformation of a part of the original data, on calibration of models trained on imbalanced datasets, in particular in melanoma classification is under-explored. We train neural networks on SIIM-ISIC 2020 melanoma classification dataset under two conditions: with and without data augmentation, and compare the differences in AUC and expected calibration error (ECE) in both scenarios. Our results shows improvements in uncertainty calibration using different augmentation methods. --- ### On Impact of Loss Function on the Performance of Neural Networks in Melanoma Diagnosis Authors: Morgan May, Pierpaolo Dondio, Simon Caton Published: 2026-10-05 Categories: cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.06139v1 Melanoma is the deadliest type of skin cancer, whose early diagnosis is crucial for patients' survival. Image classification using deep learning models has shown promising results for melanoma diagnosis. However, the performance of these models on the melanoma datasets such as SIIM-ISIC melanoma classification dataset is a challenge due to the class imbalance. One of the methods to deal with this challenge is using loss function modifications. In this work, we have investigated the effect of different loss functions on the performance of deep neural networks. We trained these networks using focal loss, logit-adjusted softmax cross-entropy (CE) loss, and weighted softmax CE loss, and we report different metrics for evaluating performance and uncertainty calibration. Our results suggest that focal loss delivers a good combination of performance in terms of AUC and uncertainty calibration in terms of expected calibration error (ECE) simultaneously. --- ### Co-Optimizing Graph Sparsification and Approximate Computing for Energy-Efficient FPGA-Based GCN Inference Authors: Nathaniel Kaye Mellor, Shreejith Shanker, George Floros Published: 2026-10-05 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2610.06138v1 Graph Convolutional Networks (GCNs) have emerged as a powerful framework for learning from graph-structured data, yet their deployment on resource-constrained edge platforms remains challenging due to the computational and memory demands of sparse graph aggregation. This work presents an FPGA-based GCN accelerator that combines DSpar graph sparsification, 8-bit quantization, and approximate multipliers on the AMD Kria KV260. Evaluated on Cora, LastFM Asia, and Amazon Photo, the design explores the interaction between sparsification and approximation across graphs with widely varying densities. Results show that the effectiveness of approximate arithmetic is governed by accumulation depth within GCN computations. Approximate multipliers are most effective when applied to sparse aggregation operations, while graph sparsification further improves their viability by reducing aggregation depth. The combined approach achieves up to 9.88$\times$ speedup while maintaining 86.6\% classification accuracy on Amazon Photo, and 1.52$\times$ speedup with 77.0\% accuracy on Cora, with total power consumption below 1 W. These results demonstrate that graph sparsification and approximate computing are complementary techniques whose co-optimization enables efficient low-power GCN inference on edge FPGA platforms. --- ### AnchorGen: Anchored Optimization for Customizable Generative 3D Design Authors: Hantao Zhang, Oliver Heinimann, Jieke Wu, Yingxuan You, Emilien Seiler, Pascal Fua Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06135v1 Engineering design often starts from a 2D sketch that fixes style and proportions, yet the subsequent 3D shape optimization relies on learned generative priors to keep the geometry valid. However, these priors are agnostic to the sketch: while they admit a valid design by correcting a drifted proposal back to its training distribution, they often correct it towards the high-density region, ignoring the specified design. We introduce \emph{AnchorGen}, a rectified-flow framework trained unconditionally on the concatenated shape and sketch latents of paired data. The learned manifold represents the joint distribution of shape-sketch pairs, so constraining the sketch component restricts the iterate to the sub-manifold of shapes consistent with a target style. Since training employs no conditioning signal, the constraint is imposed at inference: gradient descent optimizes the shape latent to minimize a differentiable drag surrogate, while constraining the sketch latent to remain close to the target sketch via a token-wise cosine penalty. A single model thereby supports design-preserving optimization, dimensionally explicit design edits, and sketch-only synthesis. --- ### Machine learning for journal entry testing: A type-aware evaluation of anomaly detectors under a review budget Authors: Jan Gronewald, Michel Scherer, Nijat Mehdiyev Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06133v1 Journal entry anomaly detectors are commonly evaluated on the full population with ROC-AUC, precision and recall, ignoring the review budget and which anomaly types are found. We propose a type-aware evaluation combining per-type recall, fair-share type recall (FSR), which caps each type's credit at its budget share, type coverage and first-hit rank. We evaluate nine unsupervised detectors, a supervised reference and feedback-driven Deep Semi-Supervised Anomaly Detection (DeepSAD) on four real client ledgers with injected typed anomalies and a public synthetic ledger. On the largest client ledger, principal component analysis (PCA), an autoencoder (AE) and a variational autoencoder (VAE) each place on average 98 anomalies among the first 100 postings, but at least 95.8 belong to one type. FSR instead favours a nearest-neighbour (kNN) detector and changes the top-ranked detector on three of four client ledgers. Representation also matters: one-hot encoding exposes unseen accounts, whereas frequency encoding leaves unseen contra accounts largely undetected. On the public ledger, the Histogram-Based Outlier Score (HBOS) and Empirical Cumulative Distribution-Based Outlier Detection (ECOD) reach all eight markings within 1,386 entries, whereas kNN, the hit leader at 1,000 entries, first reaches cross-linked clearing at rank 4,641, and the supervised row-level reference misses this marking within 1,000 entries. There, the adaptive DeepSAD review protocol raises mean hits per 100 reviews from 40.0 to 68.3 but type coverage only from 2.7 to 3.0. These findings show that high hit rates can conceal systematic blind spots and suggest that feedback can reinforce existing detection patterns without broadening anomaly coverage. --- ### Integrating Survival-Based Aging Models with Data-Driven RUL Prognostics Authors: Abhishek Srinivasan, Juan Carlos Andresen, Sepideh Pashami, Anders Holst Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06128v1 Predictive maintenance requires reliable remaining useful life (RUL) estimation. Existing methods mainly follow two paradigms: wear-based aging models that capture cumulative degradation and sensor-driven data models that reflect instantaneous health conditions, each providing only partial information. In this work, we propose a probabilistic fusion framework that integrates wear-based and sensor-based prognostic components through failure probability distributions. Based on explicit structural assumptions linking wear, latent health, sensor observations, and failure, we derive a principled combination rule that enables uncertainty-aware integration with adaptive weighting of the components. Experimentally, we assess this combination rule by learning the wear-based component using a parametric survival model and the sensor-based component using a 1D convolutional neural network (1D-CNN) with a post-hoc uncertainty model. Evaluation on multiple N-CMAPSS datasets demonstrates that the fused model improves point accuracy, preserves the C-index, and produces narrower yet well-calibrated prediction intervals compared to either component alone. The results highlight the complementary roles of wear-based survival model and sensor-based deep learning model, and show that their probabilistic integration provides a structured pathway toward more robust and consistent prognostics over the life-time. --- ### Benchmarking Jailbreak Guardrails for Embodied Agents Authors: Xunguang Wang, Qingyue Wang, Yuguang Zhou, Zongjie Li, Wenxuan Wang, Shuai Wang Published: 2026-10-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.06122v1 Embodied agents powered by large language models and vision-language models are increasingly deployed in physical environments, but jailbreak attacks can induce these agents to perform physically harmful actions. A growing number of guardrail methods have been proposed to intercept dangerous behavior before it is executed, yet existing safety benchmarks evaluate the embodied models themselves, leaving it unclear how well these guardrails actually defend an embodied agent in practice. We present the first systematic evaluation of jailbreak guardrails for embodied agents. To compare guardrails under identical conditions, we build a pluggable evaluation framework that treats the embodied agent as a fixed backend and each guardrail as a module that can intervene at the perception, planning, or control stage. We subject six representative guardrails to template-based and automated jailbreak attacks as well as safe instructions, and assess them at the system level along three dimensions: defense effectiveness, measured by the bypass rate and the hazard success rate in the simulator; usability, measured by the false-positive rate and the task completion rate on safe instructions; and efficiency, measured by the latency overhead added at runtime. Experiments on guardrails that span different intervention stages, decision mechanisms, and input modalities reveal a clear trade-off among the three dimensions, and show that no single guardrail dominates in all settings. We further analyze how intervention stage, decision mechanism, and input modality shape safety outcomes, and we offer practical guidance for selecting and designing guardrails for embodied agents. --- ### Mind the Drift: Diagonal Linear Networks Under Large Learning Rates Authors: Aniket Sanyal, Tom Jacobs, Rebekka Burkholz Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06120v1 Large learning rates can qualitatively change the trajectory of neural network training, often pushing optimization into regimes far from classical gradient-flow behavior. The Edge of Stability (EoS) offers a valuable lens on the dynamics such learning rates induce. We study corresponding dynamics in diagonal linear networks, where we uncover a competition between two distinct implicit biases that jointly determine the sparsity of the recovered solution in regression settings. Complementary to the Gain, which captures the average discretization error accumulated by Gradient Descent relative to Gradient Flow, we derive a closely associated but overlooked quantity: the Drift. Under large learning rates, it describes an imbalance between different discretization errors and represents a systematic shift in the optimization trajectory. While the Gain grows monotonically in certain regimes, and can bias towards denser, flatter interpolators, the impact of the Drift depends on its alignment with potential solutions, which can either counteract or reinforce the effect of the Gain. Consequently, its behavior drives model selection, particularly during early training epochs. To validate our theoretical insights, we introduce an intervention that actively steers the Gain to recover sharper, sparser solutions. Thus, our analysis reveals that large learning rates do not universally hinder the recovery of sparse solutions. On the contrary, they can be harnessed to control the implicit bias of training. --- ### ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training Authors: Yuanshi Liu, Boyuan Jiang, Liang Hou, Xin Tao, Pengfei Wan, Zhouchen Lin, Cong Fang Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06116v1 Modern LLM optimizers such as Muon often produce weight matrices with higher effective rank than Adam, yet further spectral control has delivered only modest gains. We identify a tension behind this result: concentrated spectra can suppress gradient directions in coupled weight matrices and slow optimization, while constraints maintained throughout training can limit task-specific adaptation and raise the attainable loss floor. We introduce ORCA (Orthogonal Regularization, Cooled After), a minimal optimizer intervention that applies strong but temporary soft orthogonality regularization early in training, then removes it. This allows the weights to benefit from a broader spectrum early on and adapt freely afterward. Across LLaMA, Qwen3, and fine-grained mixture-of-experts models ranging from 130M to 8B parameters, ORCA achieves lower final validation loss than Muon. Its loss reduction relative to Muon matches or exceeds Muon's reduction relative to Adam. Ablations support the early-shaping, later-release design. Further, ORCA requires no architectural changes and adds minimal overhead. --- ### Flash-OPD: Fast On-Policy Distillation Authors: Wei Chen, Junle Chen, Yitong Yang, Zhaoyang Xu, Jiaxin Lin, Yuxuan Liang, Xiaofang Zhou, Kai Wang, Rui Chen Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06105v1 On-policy distillation (OPD) provides dense teacher supervision on student-generated trajectories, but generating and evaluating long rollouts incurs substantial training cost. Existing acceleration methods reduce this cost through open-loop rollout schedules or closed-loop horizon adaptation. However, supervision compatibility can vary substantially across trajectories, making a single rollout horizon difficult to match their heterogeneous reliable lengths: an overly short horizon may truncate useful supervision, while an overly long one wastes computation beyond reliable regions. Our key insight is that the trajectory-specific reliability boundary need not be predicted before generation. By viewing reliability as the first-passage of accumulated low teacher--student compatibility events, the boundary is inherently unknown before sampling, yet whether it has been reached can be determined exactly from the observed prefix. Building on this insight, we propose *Flash-OPD*, which shifts from rollout-horizon control to adaptive trajectory-level boundary verification. *Flash-OPD* interleaves cached generation with teacher verification and independently stops each trajectory according to its observed compatibility events. To reduce verification overhead, the recent event rate is used only to schedule the next verification point, while the actual stopping decision always relies on the exact cumulative count. This separation prevents estimation errors from causing premature termination while enabling efficient verification during generation. Extensive experiments across diverse datasets and teacher--student settings show that *Flash-OPD* achieves $2.2\times$--$7.5\times$ speedups over standard OPD while maintaining or improving accuracy. --- ### Benchmarking CLIP for Zero-Shot Face and Periocular Gender Estimation Authors: Fernando Alonso-Fernandez, Kevin Hernandez-Diaz, Jose Maria Buades, Josef Bigun Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06102v1 We investigate CLIP for zero-shot gender estimation from full-face and periocular images. Three CLIP backbones are evaluated on 11,299 frontal images from Adience using image-text similarity with male/female prompts, achieving 95.54% full-face accuracy without task-specific training. For periocular, zero-shot predictions are strongly biased towards males, primarily due to a misaligned decision boundary. Threshold alignment substantially reduces this bias, reaching 85.29% accuracy. Linear SVMs trained on CLIP features provide only marginal gains, with a best periocular accuracy of 86.17%, approximately 2.8% above previous Adience results in the literature. Nevertheless, the gap with full-face performance confirms the greater difficulty of periocular gender estimation --- ### From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation Authors: Quanyu Long, Xiao Chen, Jianda Chen, Haozhen Zhang, Qisheng Hu, Jianzhu Bao, Wenya Wang Published: 2026-10-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.06100v1 Realistic environment replicas are increasingly valuable for training and evaluating LLM agents, yet the original systems may be inaccessible or impractical to reproduce. We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation. We instantiate this paradigm with Trace2Env, a learning-free framework for settings where the original system is unavailable but historical interaction traces remain accessible. Trace2Env reconstructs these traces into a reusable environment worldbook containing environment schemas, grounded evidence, and induced behavioral knowledge. At runtime, the world model agent actively consults the worldbook together with persistent episodic state to infer each action's observation and lasting state effects. Across nine environments, Trace2Env improves both next-observation fidelity and long-horizon interaction consistency over conventional prompt-based LWMs. In multi-turn interaction, task agent actions generated against Trace2Env remain valid more often when replayed in the real environment, indicating that its simulated dynamics better preserve the consequences of earlier actions across successive turns. These results establish agentic language world modeling as an alternative direction for building realistic environment replicas without reconstructing the original executable system. --- ### On the Geometry of Multimodal Saturation: Riemannian VICReg Authors: Nessim Ben Abbes, Duc Han Le, Sabri Mtibaa, Van-Tam Nguyen Published: 2026-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.06096v1 In self-supervised learning, a third modality should improve, or at least preserve, performance. Across nine image-text-tabular datasets, we show that it instead harms performance: the trimodal model underperforms its own best bimodal subset in 55.6% of paired runs under VICReg. The same failure occurs in 51.1% of paired runs under SimSiam. We call this failure multimodal saturation. We propose that the failure lies in the alignment geometry. Riemannian VICReg (R-VICReg) generalizes classical VICReg: it aligns views by squared geodesic distance on learnable negative-curvature product factors and recovers VICReg exactly as curvature vanishes. Over the same 45 paired runs, R-VICReg raises the probability that the third modality helps from 44.4% to 64.4%, with gains concentrated where VICReg saturates. --- ### Transmission Factors for Lossy Compression of PDE Training Data: Measuring What Reaches a Trained Operator Authors: Huy Hoang Le Published: 2026-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.06095v3 Operator-learning benchmarks ship as full-precision arrays, and they have grown to terabyte scale. A curator who wants to distribute one has to decide how coarsely to store it. That decision is usually made by fixing a tolerance on the reconstruction error of the stored field. We show that this quantity is measured in the wrong place. It compares the stored field with the original, before any model is trained. What the curator is buying is the accuracy of a model trained on the compressed copy, and the two can disagree: two PDEBench families stored to identical field error differ threefold downstream. A solution operator smooths, so only part of the codec error ever reaches the model's output. That part can be measured. Push a compressed field through a model already trained at full precision, and compare its output against the output on the clean field. The measurement costs forward passes and no training on compressed data. It spans more than two orders of magnitude across six PDE families, and it orders downstream cost where field error does not, inverting 12 of 104 cross-dataset comparisons against field error's 36. Read as a budget, the same curve nominates a storage rate for each dataset. A back-check against trained models finds those rates wrong in both directions by up to a factor of two in stored bits. --- ### Anatomy-preserving unpaired cone-beam CT refinement for image-guided radiotherapy using pseudo-label guided diffusion Authors: Qi Lai, Yutong He Published: 2026-10-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.06094v1 Cone-beam computed tomography (CBCT) is widely used in image-guided radiotherapy, but scatter, beam hardening, noise, truncation, and other artifacts limit image quality and CT number accuracy. Paired CBCT and CT data are difficult to obtain clinically because of motion, anatomical changes, and acquisition mismatch. We present RefineCBCT, an unpaired CBCT refinement framework that uses pseudo-label guidance and short-step diffusion to reduce artifacts while preserving patient-specific anatomy. RefineCBCT was trained and evaluated on unpaired CBCT and planning CT data from public LUNG TCIA and PELVIC TCIA datasets and compared with representative GAN and diffusion based methods. On LUNG TCIA, it achieved the best results across all metrics, with MAE 19.411, RMSE 62.758, PSNR 30.845 dB, and SSIM 0.931. On PELVIC TCIA, it achieved the best MAE, PSNR, and SSIM, with values of 14.905, 36.671 dB, and 0.876. The refined images showed fewer streaking and shading artifacts, clearer anatomical boundaries, and improved soft tissue uniformity, with line profile and ROI analyses showing closer agreement with planning CT. These results suggest that RefineCBCT provides efficient and effective CBCT refinement under clinically realistic unpaired training conditions and may support more reliable CBCT use in image-guided radiotherapy workflows. Code is publicly available on GitHub, and the evaluated datasets are available from The Cancer Imaging Archive. --- ### Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII Authors: Alexandru Nazare, Agnese Profico, Nicolò Vania, Elena Di Croce, Daria Caramanica, Davide Venditti, Elena Sofia Ruzzetti, Giancarlo A. Xompero, Fabio Massimo Zanzotto Published: 2026-10-05 Categories: cs.CL, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2610.06093v1 The robustness of Personally Identifiable Information (PII) protection in Large Language Models (LLMs) is a critical concern, yet the risks associated with cross-lingual data extraction remain under-explored. This study evaluates the vulnerability of English-centric and multilingual models to Training Data Extraction (TDE) attacks when prompted in non-English languages. We construct a multi-domain PII dataset comprising social media handles, email addresses, and phone numbers and translate the attack contexts into Italian, Spanish, French, and German. Our results show that TDE attacks against both English-centric and multilingual models transfer to different languages: the attacks are successful on translated prompts, even though only the original English prompt might have been included in the pre-training data. A web-presence check on a sample of the translations confirms that they are not available online. The share of English leaks recovered in other languages grows with the multilingual capability of the model, and it drops sharply when the original wording is lost, even without a change of language. This suggests that native multilingual pre-training facilitates the emergence of latent cross-linguistic bridges that simplify the retrieval of personally identifiable information (PII). We analyze the activations of multilingual large language models (LLMs) and find that different translations of the same prompt are bridged in similar representations, with the strongest alignment in the middle layers. Our results highlight a fundamental security gap in modern LLMs, necessitating more robust, language-agnostic sanitization strategies for future model alignment. ---