# Research Papers — 2026-09 · bundle page 115 of 266 > Full-text markdown of papers #5701–5750 of 13298 published in 2026-09, newest first. AI-readable mirrors of the full 13298-paper 2026-09 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-09/page/115 [← Previous bundle](https://aipod.dev/papers/archive/2026-09/page/114.md) [Next bundle →](https://aipod.dev/papers/archive/2026-09/page/116.md) ### GraphSVR: q-Space--Aware Graph-Based Slice-to-Volume Registration for Diffusion MRI Authors: Noga Kertes, Daphna Link Sourani, Alex M. Bronstein, Moti Freiman Published: 2026-09-21 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2609.24732v1 Diffusion-weighted imaging (DWI) remains highly vulnerable to subject motion, particularly in time-efficient protocols and in motion-prone populations. While slice-to-volume registration (SVR) can mitigate inter-slice and inter-stack misalignment, diffusion MRI introduces additional complexity due to diffusion-direction-dependent contrast and the requirement to align dozens of measurements within a common reference frame, effectively yielding a 4D registration problem. Existing approaches rely primarily on sequential modeling or pairwise similarity and often degrade under sparse gradient sampling or severe motion. We introduce GraphSVR, a q-space-aware graph-based framework for 4D SVR registration in DWI. GraphSVR represents slice groups as nodes in an acquisition-structured graph, with edges encoding temporal proximity, spatial slice geometry and diffusion encoding relationships. A graph neural network predicts globally consistent stack-wise rigid motion, optimized in a self-supervised, zero-shot manner using only an anatomical reference image, without requiring paired ground-truth motion. We evaluate GraphSVR using both fully synthetic diffusion simulations and realistic recombination-based simulations from real acquisitions with controllable motion severity and gradient sparsity. Performance is quantified using grid error (mm) and rotation error relative to known ground-truth transforms. Under severe motion, GraphSVR reduces grid error and rotation error by 73% compared to FSL eddy, the standard DWI motion-correction method, with the largest gains observed in sparse-direction regimes. These results demonstrate that explicitly modeling acquisition structure through graph-based reasoning improves robustness and global consistency in 4D DWI motion estimation. Code is available at https://github.com/nogakertes/GraphSVR.git. --- ### ReSTI: A Source-Grounded Audit and Repair of STI-Bench Authors: Pengzhan Sun, Ramanathan Rajaraman, Shiu-Hong Kao, Junbin Xiao, Angela Yao Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24727v1 Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit STI-Bench against the official ScanNet, Waymo, and Omni6DPose sources and find systematic coordinate-system and timestamp errors, under-specified targets and times, and disagreements between keyed options and answer details. We introduce ReSTI, a source-backed revision that reconstructs every recoverable answer under an explicit target, time, coordinate system, physical quantity, and unit. Source reconstruction reveals task-level geometric failures: ScanNet Grounding omits the required alignment between annotation and raw camera coordinate systems, while Orientation measures camera rotation on the wrong plane. ReSTI replaces these labels with explicit, source-consistent geometric definitions and corrects other source-verifiable defects, including Waymo poses evaluated at the wrong timestamp. Across 2,064 legacy questions, ReSTI retains 1,782 questions and records 282 evidence-backed exclusions. ReSTI therefore provides a conservative and source-traceable basis for evaluating precise video spatial--temporal reasoning. Project page: https://github.com/pengzhansun/ReSTI. --- ### A digital-twin framework for forecasting treatment-day imaging with contour uncertainty in adaptive proton radiotherapy Authors: Yizhou Wu, Jie Ding, Justin Roper, Minglei Kang, Yuheng Li, Sibo Tian, David S. Yu, Xiaofeng Yang, Chih-Wei Chang Published: 2026-09-21 Categories: physics.med-ph, cs.AI arXiv: https://arxiv.org/abs/2609.24725v1 Head-and-neck anatomy changes over a six-to-seven-week proton course, and the anatomy of a later week cannot be imaged when the plan is made. We present a digital-twin framework that forecasts a patient's treatment-day anatomy as an ensemble of predicted CTs with propagated contours and quantifies the uncertainty of the forecast contours. The twin is a library of previously treated patients with planning and weekly quality-assurance CTs (QACTs), made patient-specific by a two-step foundation-model deformable registration: a cross-patient field carries each library patient onto the current patient, and a longitudinal field, estimated in the current patient's frame, carries that patient's planning-to-QACT change onto the current patient's own planning CT. A library of 302 observations from 88 patients yields about 300 replicates per patient, each a deformation that occurred in a treated patient. The dispersion of the propagated contours, resolved by outward normal, is six-direction contour uncertainty in millimeters. This is uncertainty in the input to the forecast, which library patient the current patient follows, rather than in model parameters, and it is unchanged when the registration engine is exchanged. On ten patients with clinician contours on two QACTs, the library alone fixes the anisotropic shape of the uncertainty (4.5 to 6.2 mm); the first QACT narrows it by a factor of 3.2 to 3.6 without a contour being drawn; an approved contour improves the center but not the width. The estimate orders directions correctly but is not Gaussian-calibrated. A clinical target volume expansion is worked out as one application. --- ### A Federated Artificial Intelligence Framework for Optimizing Pancreatic Cancer Treatment - Strategy Update Authors: Anne-Christin Hauschild, Amirreza Aleyasin, Nils H. Beyer, Lisa Fricke, Jonas Hügel, Maryam Moradpour, Anh-Tien Nguyen, Youngjun Park, Sophia Rheinländer, Tim Beissbarth, Elisabeth Hessmann, Martin Middeke et al. Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24718v1 While a centralized approach involving patient consent to collect and analyze data centrally would theoretically offer the best data quality and predictive performance, it is not always feasible in practice. Federated Learning (FL) architectures have shown to be a very promising approach to use and access distributed disease related resources within the GDPR boundaries. In a previous case report, we described the preconditions at the participating sites and necessary administrative and process related steps to prepare data, people and infrastructure for improving subtype identification and assessing treatment options in pancreatic cancer. We update this report sharing our experience in tackling the challenges and show preliminary results of the actual federated learning AI pipelines. At the participating sites, we have to identify and annotate the data being accessible after extraction and transformation in a local FL hub - in our case a centrally developed and distributively deployed Docker container. This container comprises the FL scripts generating local models. We apply a newly developed FL algorithm considering all local features, including partial overlapping features specific to the local sites. Theoretically, an annotation in a cancer setting should succeed using the German oncology core data set (oBDS), which is already utilized for mandatory reporting to cancer registries, and can be sustained in the FL setting. The FL algorithms deal robustly with partially overlapping features as we showed with public data sets. Major roadblocks including straightening operational concepts for the infrastructures, ethics approval for such novel architectures and support for every site have been addressed. However, scaling up this approach in the future faces hurdles; while including broader multi-modal data sets should be feasible, large-scale deployment to more sites remains challenging. --- ### Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis Authors: Jiling Zhou, Aisvarya Adeseye, Antti Hakkala, Seppo Virtanen, Jouni Isoaho Published: 2026-09-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2609.24710v1 Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning over complex and heterogeneous data. However, existing prompting approaches typically focus on eliciting reasoning without explicitly considering how intermediate reasoning steps are structurally organized. We introduce Security Reasoning Topology, which models reasoning through three representative structures: Linear, Branching, and Graph. To evaluate their effects, we conduct controlled experiments on three cybersecurity datasets covering MITRE ATT&CK network traffic, cyber threat intelligence (CTI), and CVE vulnerability analysis. We evaluate multiple LLMs, including Llama 2 (7B, 13B, 70B), GPT-5.1, and Mistral Large 3, while keeping task inputs consistent and controlling reasoning structure through system-level prompting. Results show that reasoning topology substantially affects performance: Graph reasoning achieves the highest overall accuracy, improving over few-shot prompting by 9.8-12.2 percentage points across datasets, while Branching provides a strong intermediate solution. The results further show that the effect of reasoning topology remains consistent across model families and scales, highlighting reasoning topology as an important design factor for LLM-based cybersecurity analysis. --- ### "MeBo Leaves a Piece of You Behind": Designing a Relational Voice-Based Memory Companion for Older Adults Authors: Hasibur Rahman, Mahsa Nasri, Manasi Vaidya, Melika Vafafar, Jessie Chin, Smit Desai Published: 2026-09-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.24706v1 Autobiographical remembering supports identity, well-being, and social connection in later life, yet voice-based memory technologies largely rely on isolated prompts. We designed and built MeBo, a fully functional relational voice-based memory companion, through participatory design with 11 older adults. Their accounts shaped four Design Strategies that guided MeBo's interaction design and multi-agent implementation. In a mixed-methods evaluation with 20 older adults, participants found MeBo exceptionally usable (SUS = 87.75), enjoyable, sociable, emotionally responsive, and trustworthy. Participants reported higher positive affect and momentary social connection and lower negative affect after the session than before. Participants described how MeBo followed their stories, returned to earlier memories, adapted to their preferences, and made its growing memory visible and controllable. MeBo's relational framing surfaces tensions around what it should remember, who may access memories produced through interaction, and what becomes of them when the user or MeBo is no longer present. --- ### Offline Reinforcement Learning for Distribution-Grid Protection Authors: Julian Oelhaf, Alexander Luce, Christian Bergler, Andreas Maier, Siming Bayer Published: 2026-09-21 Categories: eess.SY, cs.LG arXiv: https://arxiv.org/abs/2609.24703v1 Data-driven protection may complement conventional relays in distribution grids whose operating conditions vary with distributed generation, switching events, and changing short-circuit levels. We study line-selective tripping from static trajectories of a realistically simulated CIGRE medium-voltage network using offline reinforcement learning. A convolutional Q-network receives causal voltage-current phasor and apparent-impedance features, optionally together with raw waveforms, and is trained with conservative Q-learning (CQL). A controlled sensitivity study evaluates two observation windows, reward variants, and three CQL weights under a common split and training protocol; one exploratory post-hoc run additionally increases the discount factor from $γ$=0.95 to 0.99. On 225 held-out episodes, the best per-timestep result is obtained with combined input and CQL weight $α$=0.9, reaching precision 0.9993, recall 0.9496, and F1-score 0.9738. Because dense per-timestep scores do not encode the terminal semantics of relay operation, we also evaluate the first non-wait action in each episode. The default combined-input agent selects the correct line-trip action first in 98.13% of 214 fault episodes, but trips in 72.73% of the 11 non-fault episodes. In the post-hoc run, the corresponding rates are 98.60% and 54.55%, respectively. The results show that dense predictive performance and terminal protection behavior can lead to different model rankings. Offline CQL therefore demonstrates strong faulted-line selection on the simulated fault episodes, while the static trajectories, small non-fault set, and single-seed post-hoc design preclude conclusions about practical relay security or deployment readiness. --- ### Adapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference Authors: Changxu Liu, Zhaogeng Li Published: 2026-09-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2609.24698v1 Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follows a single candidate chain, tree-structured speculation retains multiple branches from shared prefixes; under the same budget, this broader coverage can improve acceptance and efficiency. Adapting it to DeepSeek-V4 is nontrivial: its CSA/HCA online compressed attention concentrates the difficulty on the target-verify side, where branches diverging from a shared prefix compress into different states, breaking cross-branch state consistency. We integrate tree-structured speculative decoding into the DeepSeek-V4-Flash pipeline via branch-aware causal verification, temporary state isolation, and accepted-path state refresh, keeping verification and compressed-state updates consistent across branches. Across budgets D=5 to D=8, batch sizes 1 to 64, and three datasets (GSM8K, MBPP, ShareGPT), tree speculation achieves a higher accepted length than the matched linear configurations in all settings (e.g., at D=8 about 2.83--3.41 versus 2.39--2.84) and improves throughput in nearly all configurations---marginal only at the smallest budget---by up to about 18.5%. More importantly, the gains follow stable, transferable regularities: the relative gain grows with the budget and is most pronounced for less predictable workloads at small-to-medium batch sizes, while beyond a certain budget throughput plateaus and decouples from the still-rising accepted length. These results show that retaining multiple candidate paths under the same budget can effectively improve DeepSeek-V4 decoding efficiency, and offer experience for adapting speculative decoding to future models with compressed, sparse, or structured context representations. --- ### What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization Authors: Niklas Bubeck, Yundi Zhang, Vasiliki Sideri-Lampretsa, Julian McGinnis, Jiancheng Yang, Daniel Rueckert, Jiazhen Pan Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.24691v1 Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the latent codes for image generation to operate on. Thereby, the tokenizer choice bounds every downstream task from reconstruction fidelity and generation quality to the representations available for downstream analysis. Yet, medical imaging pipelines routinely utilize tokenizers from natural imaging on the hypothesis that their behavior carries over. However, this is an assumption never tested in the medical imaging regime, where datasets are orders of magnitude smaller and images exhibit far lower inter-sample variance. We present a systematic evaluation of medical image tokenizers evaluating thirty configurations across ten model families on twelve datasets at three compression factors, spanning reconstruction, generation, latent geometry, downstream classification, and memorization. We find that (1) performance on image reconstruction and generation strongly correlate, unlike prior reports on natural images; (2) modern tokenizers use nearly all of their codebook entries, but still leave most of the latent space unused; (3) training-set memorization is mild and is further suppressed by stronger latent space compression; and (4) discrete quantization can largely preserve downstream classification, with lookup-free schemes being the main exception. --- ### Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion Authors: Mathilde Abrassart, Nicolas Obin, Axel Roebel Published: 2026-09-21 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2609.24688v1 Angular-margin speaker encoders are widely used in voice conversion, yet the geometry of their classifier prototypes remains poorly understood. We analyze ECAPA-TDNN classifier prototypes as points on the unit hypersphere and characterize their organization using rotation-invariant angular statistics together with global and local effective dimensionality measures. Our analysis shows that standard training can induce angular concentration and a substantial reduction in effective dimensionality. To address this, we investigate two geometric regularization strategies (hinged Riesz log-energy and effective-dimension maximization) applied to classifier prototypes to encourage more uniform hyperspherical coverage. The resulting prototype sets exhibit higher effective dimensionality and improved isotropy, with configuration-dependent effects on speaker-recognition performance. When the corresponding ECAPA-TDNN models are used as speaker encoders for Fast-VGAN, the regularized systems also exhibit improved robustness in zero-shot voice conversion, particularly for previously unseen speakers. --- ### Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies Authors: Trung Dao, Sankalp Yamsani, Jaden Park, Joohyung Kim, Yong Jae Lee Published: 2026-09-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.24682v2 Vision-Language-Action (VLA) models map observations to actions with no objective that accounts for how the world responds, so their robustness is bounded primarily by data coverage. World models carry precisely that missing objective and are better grounded for it, yet rolling the future forward costs seconds per decision and rules them out of the control loop. We show the two can be separated. What a world model knows about physical scenes lives in its internal features; generating the future is merely the objective that produced them, so the grounding can be inherited while the generative machinery is left behind. We add one feature-alignment term to ordinary VLA training: a frozen world model is run over the training frames once and cached, and the student learns to agree with that cache. No teacher is loaded during training, the projector is discarded after it, and the deployed policy is identical to the undistilled baseline, running in 32ms and 1.86GB on a consumer RTX5090, so every gain is attributable to the representation rather than to added capacity or test-time compute. A 0.8B student reaches 97.9% on LIBERO, improves from 48.2% to 50.5% on RoboCasa-GR1 humanoid manipulation, and the same objective carries over to real hardware, on both a single-arm and a bimanual platform. The gain survives changes of student scale, backbone, alignment layer, and teacher, indicating a broad representational prior rather than a fragile alignment between two particular networks. Project page: https://thaw-vla.trung-dt.com/. --- ### Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies Authors: Trung Dao, Sankalp Yamsani, Jaden Park, Joohyung Kim, Yong Jae Lee Published: 2026-09-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.24682v1 Vision-Language-Action (VLA) models map observations to actions with no objective that accounts for how the world responds, so their robustness is bounded primarily by data coverage. World models carry precisely that missing objective and are better grounded for it, yet rolling the future forward costs seconds per decision and rules them out of the control loop. We show the two can be separated. What a world model knows about physical scenes lives in its \emph{internal features}; generating the future is merely the objective that produced them, so the grounding can be inherited while the generative machinery is left behind. We add one feature-alignment term to ordinary VLA training: a frozen world model is run over the training frames once and cached, and the student learns to agree with that cache. No teacher is loaded during training, the projector is discarded after it, and the deployed policy is identical to the undistilled baseline, running in $32$~ms and $1.86$~GB on a consumer RTX~5090, so every gain is attributable to the representation rather than to added capacity or test-time compute. A $0.8$B student reaches $97.9\%$ on LIBERO, improves from $48.2\%$ to $50.5\%$ on RoboCasa-GR1 humanoid manipulation, and the same objective carries over to real hardware, on both a single-arm and a bimanual platform. The gain survives changes of student scale, backbone, alignment layer, and teacher, indicating a broad representational prior rather than a fragile alignment between two particular networks. Project page: https://thaw-vla.trung-dt.com/. --- ### Guaranteed Low-Rank Tensor Recovery from Modewise Measurements via Normalized Block-Weighted Riemannian Gradient Descent Authors: Yushi Zhou, Feng Zhang Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24679v1 We consider the recovery of low-multilinear-rank tensors from linear measurements and propose an adaptive block-weighted modewise Riemannian gradient descent method. The method combines memory-efficient modewise measurements with a normalized adaptive weighting strategy for the core and factor components of the Riemannian gradient. The weighting improves convergence without increasing the multilinear-rank bound of the search direction or the size of the reduced core used for retraction. Under the tensor restricted isometry property and a suitable initialization, we establish local linear convergence and derive sampling guarantees for sub-Gaussian and subsampled orthogonal with random sign (SORS) measurements. Numerical experiments on synthetic low-Tucker-rank tensors show that the proposed method reduces iteration counts and computational time while maintaining reliable recovery performance, especially near the recovery threshold and for structured SORS measurements. --- ### Muon Can Outperform Dedicated Continual Learning Methods Authors: Sebastian George Sincari, Bogdan Alexandru Gheorghe, Antonio Barbalau Published: 2026-09-21 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2609.24678v1 Continual learning with Low-Rank Adapters (LoRA) typically mitigates forgetting by penalizing the overlap between a new update and the accumulated past weights, which discourages certain update directions without controlling how an update distributes its energy over the ones that remain. We ask whether that restriction has to be task-aware, or whether a generic one supplied by the optimizer is enough. We train a plain incremental LoRA (IncLoRA) with Muon, which orthogonalizes each update, and compare it against O-LoRA and ELLA over five seeds and three task orders on the Standard CL Benchmark and three seeds on TRACE. IncLoRA+Muon reaches the accuracy band of the dedicated methods on Standard CL and improves on every AdamW configuration on TRACE. One update-constraining mechanism is enough, whether it comes from the loss or from the optimizer; on Standard CL a second one does not help, and for the most restrictive method it costs 8.4 points of accuracy and the plasticity to fit each task. What separates the two optimizers is not the size of the update, which under Muon is 0.91 to 2.06 times that under AdamW, but how it is distributed. AdamW confines it to between 1.4 and 1.8 effective singular directions, Muon spreads it over 7.0, and the two do not overlap in any tracked run. Part of the advantage usually attributed to dedicated CL methods may therefore be explained by the geometry of the optimizer's updates. --- ### TimeLitmus: A Diagnostic Benchmark for Cross-Modal Understanding and Explanation Faithfulness in Event-Conditioned Time-Series Prediction Authors: Jie Gong, Maowei Jiang, Zhiwei Liu, Yankai Chen, Guojun Xiong, Xue Liu, Min Peng, Qianqian Xie, Sophia Ananiadou Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.24677v1 Large language models (LLMs) are increasingly used to make predictions from numerical time-series histories and textual events. Yet accuracy alone cannot reveal whether correct answers reflect effective integration of the two inputs or instead arise from event polarity, unimodal priors, or superficial cues. Likewise, plausible explanations may rationalize predictions without faithfully reflecting the evidence that drives model behavior. We introduce TimeLitmus, a diagnostic benchmark for cross-modal understanding and explanation faithfulness in event-conditioned time-series prediction. TimeLitmus contains 4,856 evaluation records across Finance and Traffic, combining natural prediction with controlled counterfactual and contrastive interventions, explanation-targeted faithfulness tests, and systematic shortcut controls. Across ten representative LLMs, standard prediction accuracy substantially overstates reliable cross-modal understanding: Hard Paired Contrast (HPC) pair correctness peaks at only 19.2% in Finance and 11.7% in Traffic, and all ten models show lower-than-expected consistency on Finance series-side controls. Models often recognize scenario relations explicitly yet fail to apply them during independent prediction. Explanation faithfulness shows a similar gap: in Traffic, most models cite the manipulated temporal factor in over 90% of cases, while behavioral support remains below 22%. Human annotators outperform LLMs on matched controlled and hard-pair diagnostics, confirming that these distinctions are recoverable from the inputs. Natural-only adaptation yields selective gains in evidence selection and input sensitivity, but not consistent gains in controlled or hard-pair behavior. The benchmark, evaluation suite, and supervised adaptation data will be released publicly. --- ### Trust in Edge-Enabled IoT Security: Features, Challenges and Research Directions Authors: Esin Ece Aydın, Şerif Bahtiyar, Gürkan Gür Published: 2026-09-21 Categories: cs.CR, cs.AI, cs.CY, cs.ET, cs.NI arXiv: https://arxiv.org/abs/2609.24669v1 Providing autonomous intelligence, pervasive connectivity and usability to human life and industry has led to the emergence of the Internet of Things (IoT). To support time-sensitive and resource-constrained applications, IoT systems nowadays increasingly rely on edge computing. This brings computation and decision-making closer to end devices. In edge-enabled IoT architecture, latency and communication overhead are reduced, but interactions among a larger and more diverse set of devices, edge nodes, services, and data sources are introduced as well. In such environments, security and privacy mechanisms provide the foundation for protection, while trust management can assess the reliability of interacting entities and adapting secure decisions. In this paper, we systematically review the current state of trust management in edge-enabled IoT. To this end, we propose a comprehensive taxonomy that maps physical, network, and application architectural IoT layers against the consumer, commercial, industrial, and infrastructure IoT domains. We further investigate state-of-art research based on their trust design, how trust integrated into secure IoT operations, the attacks that effect trust management process. Based on these findings, we identify key gaps in current research and outline future directions for context-aware and adaptive trust management in edge-enabled IoT. --- ### Ev-YOLO: Uncertainty-Aware Object Detection via a Unified Evidential Formulation Authors: Simon Barbarit-Gaboriau, Hind Laghmara, Rémi Boutteau, Samia Ainouz Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24668v1 Reliable uncertainty estimation is essential for deploying object detectors in autonomous systems operating in uncertain environments. Evidential Deep Learning (EDL) provides a principled framework for uncertainty-aware classification by representing network outputs as evidence and interpreting predictions through subjective logic. However, existing evidential object detectors typically combine evidential classification with regression uncertainty models that do not share the same theoretical foundation. In this work, we propose an evidential version of YOLOv8 in which both classification and bounding-box regression are formulated within a common evidential framework. Our approach exploits YOLOv8's distribution-based bounding-box representation, allowing the evidential formulation to be applied not only to classification but also to localisation. As a result, both tasks produce belief, uncertainty, and probability estimates that can be interpreted within the Dempster--Shafer framework. Experiments on KITTI, MUSES, and nuScenes show that the resulting detector remains broadly competitive with standard YOLOv8 in terms of detection accuracy while providing a localisation uncertainty that effectively discriminates between correct and erroneous detections. Moreover, this uncertainty becomes increasingly discriminative under domain shift. --- ### Beyond Endpoint Performance: Process-Level Evaluation of Self-Evolving Agents Authors: Hongqiang Lin, Chao Liu, Xiaofan Bai, Xuan Jin, Yuhong Li, Nenggan Zheng, Xipeng Cao Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.24663v1 Self-evolving agents convert interaction feedback into persistent artifacts, such as memories or skills, which in turn guide subsequent decisions. As these artifacts are iteratively updated throughout an experience stream, the capabilities they support may evolve. Consequently, endpoint performance alone offers an incomplete view of self-evolution. Process-level evaluation is therefore essential to identify when a target capability emerges and whether later updates strengthen, preserve, or weaken it. Motivated by this, we propose \textsc{EvoPathBench}, a benchmark that tracks individual capabilities during artifact-level self-evolution. EvoPathBench fixes the base model, tools, freezes evolving artifacts at successive checkpoints, and evaluates the target capability on held-out episodes. This benchmark evaluates agent self-evolution using public trading data and calibrated trajectories. It tests three capabilities: generalization to unseen tasks, retention after unrelated learning, and rule adaptation to new evidence. Experimental results show that gains on similar unseen tasks often weaken under distribution shift, retention losses are concentrated in a minority of evolution paths, and no method achieves reliable rule adaptation. Moreover, while self-evolution enables agents to generate candidate artifacts with substantial held-out gains, the selected updates consistently fall short of realizing this potential. Together, these findings establish capability-level process evaluation as a foundation for analyzing self-evolution, identifying candidate evaluation and selection as key targets for improvement. --- ### DUMA-Bench: A Dual-Control Multi-Agent Benchmark for Evaluating LLM Agent Security Authors: Ivan Aleksandrov, German Kochnev, Sabrina Sadiekh, Yaroslav Rogoza Published: 2026-09-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2609.24662v1 LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume passive users and static control, ignoring the interactive dynamics that shape real agent behavior. We introduce \textbf{DUMA-Bench}, a benchmark and evaluation protocol for measuring agent security under \emph{dual-control} interaction, where both the agent and the user can influence the shared environment state. DUMA-Bench extends $τ^2$-bench ~\cite{barres2025tau} with adversarial environments covering eight vulnerability classes, including RAG poisoning, cross-agent manipulation, and unsafe output handling. We evaluate \textbf{14 models from five model families} (OpenAI, Anthropic, DeepSeek, Qwen, and Z.ai) across eight domains and multiple user-behavior regimes. Across our experiments, introducing dual-control interaction increases the attack success rate from \textbf{26.9\%} to \textbf{41.1\%}. These results show that agent security is not solely a property of the model but emerges from the interaction between the model, the user, and the environment. DUMA-Bench provides a missing evaluation layer for studying security in realistic agent deployments. --- ### Touch2Robot: Robot Touch in the Human Demonstration Loop Authors: Shengcheng Luo, Xiaoyang Cheng, Hong Ying, Xiaoying Zhou, Jiaming Jiang, Haoran Guo, Wanlin Li, Ziyuan Jiao, Chenxi Xiao Published: 2026-09-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.24660v2 Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot hand. Collecting demonstrations directly on the target robot avoids this mismatch but substantially increases the cost of data collection. To address this trade-off, we present Touch2Robot, a framework that lets humans collect demonstrations while seeing how the target robot hand would contact the object. We capture human hand motion, tactile-glove measurements, and object motion during human manipulation. These recordings guide object-specific RL policies to reproduce the demonstrated object motion while favoring contacts consistent with the recorded human touch. We distill the learned behaviors into a unified real-time retargeter that maps incoming human observations and object geometry to robot hand configurations. During collection, the predicted robot configuration is synchronized with the tracked object pose in simulation to reconstruct robot-object contacts, which are visualized to help the demonstrator adapt subsequent interactions to the target hand. Across four real-world tasks, Touch2Robot improves average real-robot replay completion from 37.9% to 72.1% over visual-only feedback, while reducing the collection time per replay-successful demonstration from 58.6s to 18.2s. Reconstructed target-hand contacts achieve 44.2% F1 against real-robot tactile measurements, and policies trained on Touch2Robot demonstrations improve downstream Diffusion Policy performance by 29.1 percentage points over visual-only feedback. These results show that bringing robot touch into the human demonstration loop improves both the quality and efficiency of scalable dexterous data collection. Project webpage: https://Touch2Robot.github.io/. --- ### Touch2Robot: Robot Touch in the Human Demonstration Loop Authors: Shengcheng Luo, Xiaoyang Cheng, Hong Ying, Xiaoying Zhou, Jiaming Jiang, Haoran Guo, Wanlin Li, Ziyuan Jiao, Chenxi Xiao Published: 2026-09-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.24660v1 Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot hand. Collecting demonstrations directly on the target robot avoids this mismatch, but substantially increases the cost of data collection. To address this trade-off, we present \textbf{Touch2Robot}, a framework that lets humans collect demonstrations while seeing how the target robot hand would contact the object. We capture human hand motion, tactile-glove measurements, and object motion during human manipulation. These recordings guide object-specific RL policies to reproduce the demonstrated object motion while favoring contacts consistent with the recorded human touch. We distill the learned behaviors into a unified real-time retargeter that maps incoming human observations and object geometry to robot hand configurations. During collection, the predicted robot configuration is synchronized with the tracked object pose in simulation to reconstruct robot-object contacts, which are visualized to help the demonstrator adapt subsequent interactions to the target hand. Across four real-world tasks, Touch2Robot improves average real-robot replay completion from 37.9\% to 72.1\% over visual-only feedback, while reducing the collection time per replay-successful demonstration from 58.6~s to 18.2~s. Reconstructed target-hand contacts achieve 44.2\% F1 against real-robot tactile measurements, and policies trained on Touch2Robot demonstrations improve downstream Diffusion Policy performance by 29.1 percentage points over visual-only feedback. These results show that bringing robot touch into the human demonstration loop improves both the quality and efficiency of scalable dexterous data collection. \textit{Project webpage: \href{https://Touch2Robot.github.io/}{https://Touch2Robot.github.io/}.} --- ### Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models Authors: Xiaoqiang Wang, Mengyang Xiong, Jun Dai, Bang Liu Published: 2026-09-21 Categories: quant-ph, cs.CL arXiv: https://arxiv.org/abs/2609.24657v1 Language models can be adapted by changing the computations applied to individual tokens. Quantum circuits offer one such approach, but evaluating wider circuits inside a large model can be computationally demanding. Here we introduce HyperQ, which adds token-conditioned quantum residual branches to a frozen masked-diffusion language model. A quantum residual branch is a module in each transformer block that reads a token's hidden state, emits the coordinates of that token's circuit, executes it, and adds the measured values back through a residual connection. The backbone remains frozen, and only the added branches are trained. Within each branch, a lightweight circuit hypernetwork emits token-specific rotation angles, coupling strengths, and measurement axes in a shared sparse circuit structure. The required expectation values have an exact classical expression whose evaluation cost grows linearly with the qubit count, enabling circuits from 16 to 64 qubits to be trained within a 1.1-billion-parameter backbone. Across downstream benchmarks, increasing circuit width raises the average score from 47.65 to 54.30. At 64 qubits, HyperQ exceeds the backbone and its low-rank-adapted counterpart by 4.71 and 3.67 points, respectively. HyperQ is fine-tuned on 20,000 prompt-response pairs, compared with 200,000 for the classical baselines. These findings support token-conditioned circuit emission as a tractable architectural approach to quantum-augmented language modelling. --- ### Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement Authors: Qing Yao, Lijian Gao, Qirong Mao Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24651v1 Diffusion and flow models, as promising generative paradigms for speech enhancement, face a training--inference mismatch: training uses analytical path states, whereas inference recursively evaluates models on self-generated rollout states along discretized sampling trajectories. This mismatch causes prediction and discretization errors to accumulate. To address it, we introduce Corrective Forcing (CoF), a post-training paradigm that forces diffusion and flow models to learn from self-generated rollouts and correct their predictions. CoF corrects clean-speech predictions on rollout states toward the ground truth under dynamic sampling schedules, exposing the model to varying inference conditions. It further regularizes local evolution using locally corrected counterfactual transitions as references for factual transitions. By expressing model outputs through a shared clean-speech prediction parameterization, CoF applies the same post-training objective across diffusion and flow formulations. Experiments with SB-VE and OT-CFM demonstrate improvements in perceptual quality and reconstruction fidelity, together with robust performance across different numbers of sampling steps. --- ### Assessing Readability with LLMs: The Role of Reasoning and Few-Shot Prompting Authors: Raphaël Thieffry, Matej Martinc Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.24650v1 Readability assessment is essential for tailoring texts to intended audiences across educational, healthcare, and information retrieval domains. However, traditional readability formulas struggle to generalize across genres and languages, while supervised machine learning models rely on scarce, domain-specific annotated corpora, limiting their applicability--particularly for less-resourced languages. Large Language Models (LLMs) offer a highly scalable, multilingual alternative that requires no task-specific training, yet the impact of advanced prompting strategies on their performance remains underexplored. In this paper, we conduct a systematic benchmark of diverse open-source LLMs for multilingual readability assessment, focusing on the prediction of discrete readability levels required by educational frameworks. In addition to English, we evaluate our approach on a less-resourced language, Slovenian, to establish whether LLMs remain effective in low-resource settings. Specifically, we investigate the influence of explicit reasoning, demonstrating that Chain-of-Thought (CoT) prompting and reasoning-oriented models yield significant improvements over direct answering. Furthermore, our exploration of few-shot in-context learning reveals that providing just one labelled example per category (1-shot) substantially enhances prediction quality compared to zero-shot settings, with additional examples offering diminishing returns. By comprehensively comparing these approaches against traditional unsupervised metrics and state-of-the-art supervised baselines, we establish the viability of out-of-the-box LLMs as robust, cross-lingual readability assessors. --- ### iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs Authors: Ahmed Khaled Khamis, Xiaotong Ji, Hassan Jaber, Rasul Tutunov, Matthieu Zimmer, Jun Wang, Haitham Bou-Ammar Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24646v2 On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full demonstration-conditioned teacher. This fixes teacher influence at the full-teacher endpoint, providing no control over how much demonstration information should be transferred at each prediction state. We introduce Information-Proximal SDFT (iSDFT), which instead treats the teacher as a budgeted source of information. At each token, iSDFT selects the distribution closest to the current student that satisfies a prescribed teacher-information constraint, yielding a closed-form exponential target with a locally determined tilt. To control cumulative drift, we further anchor the student to its frozen base policy. Across four heterogeneous LLM backbones and two specialisation tasks, iSDFT improves vanilla SDFT in 7 of 8 model-task settings and matches it in the remaining one. It also provides tighter retention on the original SDFT benchmark suite, with 73% of evaluations remaining within 0.5 points of the base model versus 52% for the strongest baseline, while achieving the largest mean improvement on all ten additional mathematics, coding, and competition-mathematics benchmarks. These results show that controlling how much and when teacher information is introduced improves specialisation while preserving broader capability. --- ### Annie, Are You Okay? How Style- and Context-Based Personalization Shape AI-Assisted Decision-Making Authors: Hasibur Rahman, Benjamin R. Cowan, Smit Desai Published: 2026-09-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2609.24644v1 As people turn to generative AI for financial advice, these systems can personalize how they communicate and what they say. Whether these forms of personalization shape decisions differently remains unclear. We conducted a preregistered 2 x 2 between-subjects factorial experiment (N=240): participants ranked three comparably viable stocks, discussed them with an AI, and reranked them. Participants perceived both forms of personalization, but only context-based personalization reliably changed ranking behavior: it increased reconsideration and moved rankings toward the AI's assigned recommendation. Participants felt more influenced without judging the AI as more correct, trustworthy, intelligent, likeable, or high-quality. Those initially farther from its recommendation moved more toward it while judging its advice less correct; exploratory analyses suggest greater susceptibility among lower-expertise participants. These findings show how personalized AI can steer decisions among defensible options with only a minimal evaluative trace, raising concerns for the design and governance of personalized decision support. --- ### Written as a Record, Read as an Address: What a Forward Pass Leaves in an Operation's KV Cache Authors: Lingfeng Wu, Behzad Shomali Published: 2026-09-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2609.24635v1 When a language model reads an operation such as "Swap the contents of Box F and Box B", its forward pass writes keys and values for those tokens into the KV cache. Prior work on entity tracking establishes what models use: bindings are resolved at query time rather than stored as explicit latent state. We ask what they write at the operation span and how it is accessed. We split a forward pass into a frozen writer and a reader: the writer's cache is recomputed without gradients, while the reader sees only the instruction and operation tokens, with all state descriptions hidden, and is trained in isolation. Anything the reader recovers was therefore already present in the unmodified cache. On a synthetic boxes task, a base reader recovers $\leq 0.06$ of queried bindings against $0.75$--$1.00$ after training, and recoverability tracks the operation's read/write footprint. We find two modes of access. Across Llama-3.1-8B and Mistral-7B, operation-span transplants causally redirect which visible state is read even when the two worlds hold identical values, revealing a routing record. Isolation training preserves routing and adds direct access to the payload, the value the operation read, from the single operand-name token in a narrow mid-depth band (layers 12--15 of 32 in Llama-3.1-8B, 14--17 in Mistral-7B) --- the same site that holds the routing record. The same recipe extends to further operations, ToMi and GSM8K, but is bounded by training coverage and costs open-book accuracy. Operation tokens thus leave localized, causally recoverable records that support both routing and direct payload access, though the model that writes them reads mainly the address they carry and not the value. --- ### High-resolution Nitrogen Dioxide Maps Reveal Exposure Limit Breaches across Europe Authors: Linus Scheibenreif, Konrad Schindler Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24634v1 Nitrogen dioxide (NO2) is a common air pollutant, released into the atmosphere through the incomplete burning of fossil fuels, and associated with respiratory and cardiovascular diseases in humans. Ambient NO2 concentrations are regulated through air-quality limits assessed with a sparse network of fixed monitors. The revised EU Ambient Air Quality Directive (2024/2881) introduces a daily NO2 limit to be met from 2030. At present, neither the regulatory monitoring network nor existing coarse, annual-mean models can resolve NO2 concentrations at the spatio-temporal resolutions necessary to assess compliance. Here we map NO2 across Europe at hourly and 10m resolution with a machine-learning model that combines ground monitors with satellite, reanalysis, land-use, traffic and emission data and returns a calibrated predictive distribution at every location. Validated against held-out regulatory monitors and independent citizen-science campaigns, the maps resolve high-resolution spatiotemporal NO2 gradients for 110 metropolitan areas in Europe. We reconstruct the daily compliance statistic across those regions and find limit breaches in 91 EU air quality zones deemed compliant by the regulatory monitoring network, covering a population of approximately 135M. Beyond air quality zones and monitor locations, an estimated 9-9.4% (20M) of the population in mapped regions lives in areas where the daily NO2 limit is breached. The high-resolution maps offer a route to population-scale assessment of compliance with the 2030 limits. --- ### From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking Authors: Zhengbao Yao, Yuanfu Luo, Kehan Xue Published: 2026-09-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2609.24631v2 Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints, nonconvexity compromises solver robustness and can cause failures. Large language models (LLMs) exhibit strong semantic reasoning capabilities, but directly generating dense trajectories makes it difficult to guarantee physical feasibility. We introduce SE-LLM-OCP, a unified framework in which LLMs make high-level discrete maneuver decisions, while an optimal-control module enforces low-level vehicle dynamics and collision constraints. Online, the LLM proposes sparse maneuver plans, decomposing the parking task into a sequence of short-horizon trajectory-optimization problems. A low-level solver then sequentially solves optimal-control problems. If the solver fails, the LLM aggregates failure evidence from the solver and validation stages to guide replanning. Offline, SE-LLM-OCP automatically evolves a structured decision-making knowledge base from scratch, driven by accumulated online failures. We validate our proposed framework in simulation on a car-like vehicle model and on a differential-drive robot. Our experimental results show that SE-LLM-OCP enables safer autonomous parking in narrow scenarios and demonstrates transfer of the same maneuver representation to a different kinematic platform. --- ### Augmented Hypothesis Testing with Persona-Based LLM Simulations Authors: Ziyad Benomar, Aymen Al Marjani, Paul Missault, Saab Mansour Published: 2026-09-21 Categories: cs.LG, cs.AI, stat.AP arXiv: https://arxiv.org/abs/2609.24629v1 A/B testing requires large sample sizes, long timelines, and significant costs. When auxiliary predictions of experimental outcomes are available from machine learning models, uncertain prediction quality precludes replacing human experiments entirely, yet these predictions may still contain useful signal. We propose a principled framework for learning-augmented hypothesis testing that leverages predictions of unknown quality to reduce sample sizes while maintaining statistical validity. Predictions naturally vary in granularity, from coarse aggregate signals to fine-grained individual-level estimates, and our framework addresses both ends of this spectrum: (1) for population-level directional predictions, where only a binary signal on the treatment effect sign is available, we use an asymmetric test and prove consistency and robustness bounds within the learning-augmented algorithms paradigm; (2) for individual-level predictions, we introduce Generalized PPI++ (GPPI), extending Prediction-Powered Inference to handle nonlinear prediction errors through higher-dimensional transformations. Both methods benefit from accurate predictions while remaining robust to inaccurate or adversarial ones. We validate our framework using persona-based LLM simulations, where AI agents equipped with user personas predict individual behavior, as a natural prediction source spanning both granularity levels. Experiments on four real-world datasets demonstrate that our methods, combined with persona-based predictions, substantially reduce experimental costs while preserving rigorous statistical validity. --- ### FedMust: Semi-supervised Multi-task Student-Teacher Federated Learning for Multi-organ CT Segmentation Authors: Ashkan Moradi, Bendik Skarre Abrahamsen, Mattijs Elschot Published: 2026-09-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2609.24627v1 Multi-organ segmentation using deep learning requires large amounts of annotated patient data; however, institutions often lack sufficiently large and diverse annotated datasets. Privacy constraints further prevent institutions from sharing patient data to overcome this limitation. Moreover, due to the labor-intensive nature of annotation and the scarcity of diverse expertise, institutions typically have labels for only a small portion of their local data, leaving the larger unlabeled portion unused. In this work, we propose a flexible semi-supervised federated multi-task student-teacher framework that leverages federated learning (FL) to improve multi-organ segmentation using both labeled and unlabeled data across participating sites. At each communication round, the proposed framework initiates local training, where clients with labels for the same task form a federation to produce an aggregated teacher model. The resulting teachers generate task-specific features for all data at each client. Subsequently, all clients form a second federation to train a multi-task student model with a shared encoder and task-specific decoders that replicate the teacher-generated features across all segmentation tasks. The aggregated student model is then used to update the local teachers and initiate the next training round. Extensive experiments demonstrated the effectiveness of the proposed method compared with local and federated single-organ models, yielding an average performance gain of 13 percent across clients. The experiments also demonstrated the impact of multi-task learning and unlabeled data and the applicability of the framework in relaxing labeled-data requirements for client participation. The code is available at https://github.com/AshknMrd/FedMust. --- ### Relationally Grounded Latent World Models for Autonomous Driving Authors: Fabian Schmidt, Markus Enzweiler, Abhinav Valada Published: 2026-09-21 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2609.24626v1 Latent world models learn predictive representations for autonomous driving, but the relational semantics these states preserve often remain implicit. We investigate whether traffic scene graphs can serve as privileged semantic supervision for latent world representations. Building on LAW, we construct actor-centric scene graphs from nuScenes 3D annotations, encode their serialized relational structure using a frozen text embedding model, and align the visual latent representations with this semantic target during training. We remove the supervision branch at inference, so it requires neither scene graphs nor 3D annotations and adds no test-time computation. On nuScenes, our method reduces average trajectory L2 error from 0.661 to 0.622 (5.9%) and collision rate from 0.456 to 0.217 (52.4%) relative to our retrained LAW baseline. It also outperforms an unstructured caption-style semantic target, supporting the benefit of explicit relational structure for latent world-model representation learning. --- ### Custom Named Entity Recognition and Topic Classification for Global Health Publications Authors: Genis Skura, Antoine Geissbühler, Jean-Luc Falcone Published: 2026-09-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2609.24625v1 How should natural language processing models be selected and adapted for global health literature in environments where annotated data and computational resources are limited? This thesis investigates these challenges through experiments on semantic tag discovery, named entity recognition (NER), and multi-label topic classification. First, skip-gram word2vec models trained on progressively larger specialized corpora are compared with BioWordVec to assess how corpus size and domain context influence tag discovery. Vocabulary coverage and qualitative evaluation indicate that broader coverage does not necessarily yield more useful domain-specific associations. The analysis then turns to entity extraction, comparing convolutional spaCy models with a RoBERTa-based transformer on 1,000 annotated sentences. Under a lenient scoring protocol, the transformer achieves 0.80 micro-F1 versus 0.65-0.69 for convolutional models, but takes 82 seconds rather than 5-6 seconds. This trade-off motivates fine-tuning convolutional models and integrating a disease recognizer that achieves 81.33% test F1 on the NCBI Disease Corpus. Combined with PDF preprocessing, entity filtering, and MeSH enrichment, the resulting pipeline supports document-level indexing. To complement entity extraction with thematic annotation, MiniLM-based few-shot classification is compared with BART-MNLI zero-shot inference across 50 topics and 1,000 handcrafted test sentences. BART-MNLI achieves 95.2% single-label accuracy versus 59%; reported multi-label accuracies are 88% and 32% under partly manual assessment. However, its higher inference cost limits practical integration. The results show where domain specialization and lightweight adaptation offer practical value, and where transformer accuracy justifies higher inference costs, providing an empirical basis for building knowledge systems under resource constraints. --- ### Learning tactile perception from high-bandwidth single-point sensing Authors: Joseph Rigal, Emmanuel Virot, Caroline Pascal Published: 2026-09-21 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2609.24621v2 Tactile sensing is increasingly being incorporated into learning-based robotic manipulation, yet many existing approaches rely on spatially distributed sensors. Here we introduce {SpectRobot}, a framework that transforms single-point tactile signals into compact time-frequency spectrograms. These spectrograms encode high-bandwidth tactile histories as fixed-size image-like representations. They can be processed by standard vision encoders and integrated into learning pipelines originally developed for vision, while preserving temporal and frequency information unavailable to conventional cameras. Rather than increasing spatial density through arrays of tactile elements, SpectRobot exploits the rich dynamics contained in sparse, high-bandwidth single-point measurements. In our implementation, the sensors are mounted away from the contact surface while remaining mechanically coupled to it, reducing direct exposure to wear and potentially improving robustness in harsh environments and for long-term deployment on dexterous robots. Our experiments demonstrate that: (1) a robot can exploit single-point vibration signals to solve a visually occluded manipulation task; (2) temporal history strongly influences policy performance, while sensing bandwidth controls the spectral information available, with measurements extending to 100~kHz; and (3) the same representation can be used across different tactile sensing technologies mediated by acceleration, force, or strain. We further show that capabilities previously associated with research-grade instrumentation can be accessed using readily available, off-the-shelf hardware. We believe that broader access to high-bandwidth tactile sensing could facilitate the integration of contact dynamics into embodied learning systems and, for some tasks, offer an alternative or complement to increasing the spatial density of tactile sensing. --- ### Ascent: An Agentic System over the Model Context Protocol for Real-World Clinical Data Analysis Authors: Angelo Ziletti, Leonardo D'Ambrosi, Melanie Tuchardt, Tim Kondziella Published: 2026-09-21 Categories: cs.AI, cs.IR arXiv: https://arxiv.org/abs/2609.24620v1 Answering epidemiological questions from real-world clinical data requires medical coding, schema-aware SQL, and validation of implicit choices about populations, denominators, and time. We present Ascent, an agentic system that exposes medical coding, question answering, and cohort analysis through a shared Model Context Protocol tool surface for standardized and native schemas. We introduce EpiTrap, a dataset testing whether systems avoid recognized pharmacoepidemiological errors, and compare a fixed pipeline with agents across models and orchestrators. With capable models, agents improve accuracy over the fixed pipeline by an average of 27 and 20 percentage points on native and standardized schemas, respectively. These gains require more tool calls and longer runtimes. Experience from real projects highlights the system's value for feasibility assessment, diagnostic iteration, and expert-guided analysis. --- ### Video-based Surgical Skill Assessment Using Dynamics-and-Uncertainty-Aware Tree-based Gaussian Process Classifier Authors: Arefeh Rezaei, Mohammad Javad Ahmadi, Amir Molaei, Hamid D. Taghirad Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24619v1 The proposed pipeline integrates a representation-flow convolutional neural network with a dynamics- and uncertainty-aware tree-based Gaussian Process classifier. In this framework, latent motion dynamics are exploited both as discriminative representations and as a source of input uncertainty, enhancing robustness against temporal variations and abnormal motion transitions. Compared with conventional deep learning approaches, the proposed strategy requires less training data and offers improved computational efficiency. To further improve classification performance, we introduce novel semantic-aware compound kernels that effectively capture semantic, flow, and dynamic information embedded in surgical video features. In addition, uncertainty-aware kernels are developed to strengthen the robustness and practical applicability of the compound kernel framework. The proposed method is evaluated on two benchmark datasets, namely the JIGSAWS and the Cataract-LMM (Capsulorhexis) datasets. Experimental results demonstrate strong performance across both datasets, including the LOSO and LOUO evaluation protocols on JIGSAWS, including the subject-independent LOUO protocol on JIGSAWS, on which the framework attains a mean accuracy of \ph{96.9}\%; results under the within-subject LOSO protocol are reported for comparability with prior work, achieving competitive accuracy while substantially reducing computational cost. Overall, the proposed pipeline provides an efficient and accurate framework for video-based surgical skill assessment. --- ### UK-PRBENCH: A Paragraph-Level Precedent Retrieval Benchmark for United Kingdom Case Law Authors: Damith Premasiri, Tharindu Ranasinghe Published: 2026-09-21 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2609.24613v1 Prior case retrieval (PCR) aims to identify precedent cases relevant to a given query case. Existing PCR benchmarks and methods predominantly operate at the document level, treating entire judgments as the unit of relevance. This formulation is suboptimal for legal practitioners, as judgments address multiple legal issues and only a small subset of paragraphs is relevant to a particular query. Addressing this gap, we introduce UK-PRBench, a benchmark for paragraph-level precedent retrieval in UK case law, constructed from judgments obtained from the UK National Archives and covering a broad range of UK courts and tribunals. Furthermore, we evaluate state-of-the-art retrieval models and establish baseline results. Our experiments show that paragraph-level precedent retrieval remains challenging for current retrieval approaches, highlighting substantial room for improvement. UK-PRBench provides a standardised benchmark for evaluating fine-grained precedent retrieval and advancing retrieval systems for the UK legal domain. --- ### Beyond Uniform Subspaces: Spectrum-Aware and Depth-Adaptive Fusion for Multi-Task Model Merging Authors: Ruxi Gu, Zilei Wang, Wei Wang Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24612v1 Model merging aims to consolidate multiple task-specific models without access to extra training process. However, existing subspace-based methods largely rely on a uniform treatment of task updates, overlooking their intrinsic spectral and depth-wise heterogeneity. We identify two key deviations from this assumption: different tasks require different subspace capacity and exhibit different tolerance to spectral transformation, while subspace projection introduces depth-dependent distortion. Based on these observations, we propose SADA-Merging, a spectrum-aware and depth-adaptive framework for data-free model merging. SADA-Merging allocates task-specific subspace capacity according to spectral complexity, adapts spectral preservation according to task-wise plasticity, and applies depth-dependent anchoring to compensate for projection-induced distortion. This enables the fusion process to adapt to both the intrinsic geometry of each task and its sensitivity across network depth. SADA-Merging operates directly on task updates and is applicable to both full fine-tuning and LoRA settings. Extensive experiments demonstrate consistent improvements over existing data-free merging methods across different task scales and adaptation settings. --- ### GraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting Authors: Eloi Campagne, Yvenn Amara-Ouali, Yannig Goude, Argyris Kalogeratos Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24609v1 Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) provide a natural way to represent these relations. Building a complete GNN forecasting experiment is nonetheless laborious, because graph construction, model selection, training, aggregation, and interpretation sit in incompatible tools. We present GraphToolbox, an open-source Python framework that unifies these stages in one configurationdriven pipeline built on PyTorch Geometric. It offers data-driven graph construction, an adapter that instantiates and trains 51 of the 65 PyTorch Geometric convolutions together with the recurrent cells of PyTorch Geometric Temporal, online expert aggregation, forecasting interpretability, and significance testing on cached forecasts. We evaluate the pipeline in two case studies. On French regional load, the 48 convolutions included in the complete forecasting sweep fall in a band from 1.14% to 1.60% error, online aggregation lowers this to 0.98%, and the graph models improve on classical additive and boosting baselines. On net-load, direct graph models are less accurate than a classical additive model, while forecasting each physical component separately improves them without closing that gap. Both comparisons use the same experimental interface, illustrating the role of GraphToolbox in systematic architectural evaluation. --- ### Applications of Neural Cellular Automata: State of the Art, Challenges and Opportunities Authors: Nick Lemke, Niklas Ihm, John Kalkhof, Mirko Konstantin, Henry J. Krumb, Daniel M. Lang, Ehsan Pajouheshagar, Ario Sadafi, Arjan Kuijper, Karim Lekadir, Marco Lorenzi, Carsten Marr et al. Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24595v1 Neural Cellular Automata (NCAs) are a new type of neural network architecture which enable accurate and robust inference at extremely small model sizes. Recently, NCAs have advanced to become interesting low-resource alternatives to convolution- and attention-based architectures for various tasks such as image analysis, synthetic image generation, and simulation. The rapid development and increased research interest necessitate a comprehensive review of the emerging technology. This review provides an overview of the fundamentals of NCAs, applications to medical imaging, as well as insights into the state of the art. We analyze recent modifications to the originally proposed NCA architecture with respect to their efficiency and accuracy. Furthermore, we review practical applications in real-world scenarios with a focus on medical image analysis, segmentation, classification, registration, depth estimation, and image synthesis. Finally, we identify several advantages of NCAs, research gaps, and conclude with an analysis of future opportunities for NCAs in medical applications in confined settings or areas that have particular demands for robustness or efficient data processing. --- ### Taking a Second Look: Correcting Sea Ice Forecasts with Sparse Observations Authors: Tianshuo Zhang, Xianglei Xing, Aowen Yang, Jia Gao, Wenzhe Zhai, Shanshan Liu, Chengtao Cai Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24591v2 Sea ice forecasts are issued several days ahead, allowing errors to accumulate while new, often sparse sea ice concentration (SIC) observations become available. We find that fixed-propagation errors concentrate near structured, high-gradient ice edges, whereas homogeneous interiors require limited propagation, suggesting that propagation distance should be state dependent. We therefore introduce ECHO (Evidence-guided Correction with Heterogeneous prOpagation), where ECHO-Scale adapts propagation distance while preserving correction geometry, and ECHO-Delta learns a bounded residual around fixed propagation. Across all 96 standard evaluation settings spanning diverse priors, observation times, sparsity levels, geometries, and noise conditions, both outperform fixed propagation. ECHO-Delta achieves the best average accuracy, while ECHO-Scale is more robust to geometry shifts. Code is available at https://github.com/yingtian22/TAKING-A-SECOND-LOOK. --- ### Overlay\_dx - Automating forecasting evaluation Authors: Long Ngo, Mohammed Amine Chamli, Jonathan Rivalan, Thomas Jaillon Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24586v1 Traditional evaluation metrics provides numerical values but often lack comprehensibility, hindering effective differentiation of model performances. Our work addresses this challenge by introducing overlay\_dx, a novel evaluation metric measuring the performance of time series prediction models. Overlay\_dx is a visual metric that represents the percentage of predictions falling within a confidence interval around actual values. Additionally, once evaluation results are plotted, overlay\_dx computes the area under the overlay curve, providing a quantitative measure of alignment between predicted and actual values across different thresholds and predictions. Through extensive experiments, we demonstrate that our approach offers a unified evaluation framework that combines both visual and numerical assessments, enabling improved model comparison and providing valuable insights for further research and optimization efforts in time series prediction. --- ### Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction Authors: Fabian Spaeh, Jingxing Fang, Shandian Zhe, Bin Shen Published: 2026-09-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2609.24579v1 Event logs arise in a wide range of real-world processes, capturing not only event activities and timestamps but also multi-modal contextual information. Existing event-sequence models, including many temporal point process approaches, primarily model event activities and timestamps while overlooking heterogeneous context, such as numerical measurements, categorical attributes, textual descriptions, and metadata associated with individual events and entire traces. In this paper, we propose Universal Multi-Modal Traceformer (UMT), a unified framework for incorporating heterogeneous process context into next-event prediction. Built on a Transformer backbone, UMT introduces a universal feature encoder that maps diverse feature types into a shared representation space and handles contextual information at both the event and trace levels. UMT further develops a per-event Perceiver module that dynamically weights contextual features and adaptively integrates them into event-token representations. To accommodate the heavy-tailed and potentially multi-modal distribution of inter-arrival times, UMT represents each interval at multiple temporal scales and jointly predicts the corresponding scale-specific quantities. Experiments on 13 real-world event logs show that UMT improves both next-event activity and time prediction over existing approaches. --- ### What do VLM-Based Vision-Language Navigation Models Rely on: Interpreting and Steering Policy Behavior Authors: Débora Oliveira Makowski, Samiran Gode, Abhijeet Nayak, Marco Hutter, Cordelia Schmid, Lukas Rosenberger Schmid, Wolfram Burgard Published: 2026-09-21 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2609.24576v1 Modern Vision-Language Navigation (VLN) models rely mostly on pre-trained large Vision-Language Models (VLMs) to predict navigation actions. While this fusion of language instructions and visual observations allows multimodal reasoning, it obscures how information is routed across modalities or what mechanisms drive navigation decisions. Thus, it remains unclear whether VLN models ground their predictions in relevant semantic cues or can track task progress. In this work, we study the interpretability and steerability of VLN models. We use intervention-based metrics that measure how visual observations, instructions, and visual memory causally influence navigation decisions. Our results show that these navigation policies are sensitive to all input modalities and do not depend on a single one. We further show that these agents encode navigation progress and retain semantic structure from their VLM backbones, enabling concept-level steering through internal activations. Finally, we extract activation vectors for abstract behaviors to transfer them zero-shot to out-of-distribution real-world scenarios, improving performance without additional fine-tuning. --- ### Evaluating Decision Models for Text Annotation in Computational Social Science Authors: Hazem Ibrahim, Yasir Zaki Published: 2026-09-21 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2609.24574v2 Computational social science increasingly relies on large language models for text annotation, and the validity of published findings now rests on the labels generated by such models. Decision models, a new model class built for categorical question answering, answer typed questions with a choice, a probability distribution over the label set, and a confidence score rather than free text, at a small fraction of frontier inference prices. Whether their answers are accurate, and whether that stated confidence can be trusted on social science constructs, are unknown. Here, we mirror the evaluation of Ziems et al. (2024) on 18 computational social science classification tasks (7,977 items), comparing the first commercial decision model and two open-weight counterparts against 19 frontier and open-weight language models under the same zero-shot protocol, and extending the decision-model comparison to eleven open-weight systems released in the week after it. The decision model trails the per-task best LLM on 14 of 15 evaluation tasks, with a median deficit of 11.6 macro-F1 points, at a median 44 times lower measured cost. Its confidence is better calibrated than the verbalized confidence of 16 of the 19 LLMs, yet three frontier models show lower median calibration error (0.157 against 0.066). While items above 0.9 confidence are typically labeled accurately (median accuracy 0.815), on one task, empathy in peer-support dialogues, the model reports high confidence while performing near chance. Nonetheless, our results suggest that decision models are useful as a first step in the annotation pipeline: routing low-confidence items to an LLM matches or exceeds the LLM alone at a quarter to half of its cost. --- ### Poisson Exchange Beyond Submodularity: Effective Approximation Algorithms for Offline and Online Subset Selection over Matroids Authors: Shi Fu, Youming Qiao, Dacheng Tao, Zongqi Wan, Qixin Zhang Published: 2026-09-21 Categories: cs.DS, cs.LG, math.OC arXiv: https://arxiv.org/abs/2609.24569v2 Over the past decade, a growing body of research has shown that $γ$-weak submodularity broadly arises in numerous subset selection tasks, including feature selection, neural network pruning, and video summarization. Despite its prevalence, maximizing a $γ$-weakly submodular function subject to a general matroid constraint remains challenging. To date, the only known approximation guarantee is the conservative $(1+1/γ)^{-2}$ factor established by \citet{chen2018weakly}. To improve upon this result, this paper proposes a novel algorithm called \MGPE, which repeatedly performs maximum-gain local exchanges through careful control of a non-homogeneous Poisson clock, and proves that this \MGPE\ can attain an approximation ratio arbitrarily close to $ρ_γ=1-\left(γ/(2-γ)\right)^{ \frac{γ^2}{2(1-γ)} }$. In sharp contrast to the previous guarantee, our obtained factor $ρ_γ$ not only strictly improves upon $(1+1/γ)^{-2}$ for every $γ\in(0,1)$, but also can asymptotically approach the optimal $(1-1/e)$-approximation for submodular maximization as $γ\to1$. Furthermore, we surprisingly find that when the matroid constraint reduces to a cardinality or the objective satisfies the stronger notion of $α$-weak DR-submodularity, \MGPE\ can automatically recover the tight approximation ratios of $1-e^{-γ}$ and $1-e^{-α}$, respectively. Here, $α\in(0,1)$ denotes the DR ratio. --- ### What Survives on Real Drawings: Active Sampling, Connectome Wiring, and Matched Baselines in Architectural Document Vision Authors: Dmitry Kuklev Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24565v2 A connectome-constrained model of the fly visual system, optimized for motion and then frozen, can be driven over architectural drawings by prescribed motion and used as a texture representation. We compare it with information-matched baselines that see the same 721 photoreceptor samples. On clean synthetic data the frozen model transfers but loses to task training: 0.857 area-weighted accuracy in one-shot hatch matching versus 0.959 for a 5,888-parameter CNN, and 0.619 IoU in wall segmentation versus 0.905 for a matched network. Under scan noise and thickened strokes, the trained networks lose up to 0.188 accuracy while the frozen pipeline loses 0.030. On fourteen production sheets, opened once, a 1,876-parameter fly model reaches 0.505 average precision versus 0.415 for a network two hundred times larger. A preregistered held-out split confirms the clean-data ordering: 0.835 for the circuit, 0.894 for receptors only, and 0.971-0.980 for trained CNNs. Rewiring the connectome while preserving degrees or type pairs and transmitter signs costs 0.271-0.356 accuracy across three seeds, so the exact wiring is load-bearing. Yet the intact circuit does not beat its moving retina, and T4/T5 silencing leaves both tasks intact. Longer observations reverse the circuit-receptor ordering once the stimulus spans a period, but not through T4/T5. Thus active sampling and exact structure matter, while clean-data practical performance remains dominated by task-trained networks and the useful transfer margin is largely retinal. --- ### HyperCLIP++: Fine-tuning CLIP forOpen-vocabulary Semantic Segmentation in Hyperbolic Space Authors: Zelin Peng, Zhengqin Xu, Changsong Wen, Yu Huang, Yaoming Wang, Xiaokang Yang, Wei Shen Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24564v1 CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encoder is known to preserve its generalization capability, recent studies show that fine-tuning both CLIP's text and image encoders jointly significantly enhances segmentation performance, especially for classes from open sets. In this work, we explain this phenomenon from the perspective of hierarchy alignment, since during fine-tuning, the hierarchical level of image embeddings shifts from image-level to pixel-level. We achieve this by leveraging hyperbolic space, which naturally encodes hierarchical structures. Our key observation is that, during fine-tuning, the hyperbolic radius of CLIP's text embeddings decreases, facilitating better alignment with the pixel-level granularity of visual data. Building on this, we propose HyperCLIP++, a novel and parameter-efficient adaptation strategy. HyperCLIP++ directly adjusts the hyperbolic radius of CLIP's embeddings via scaling transformations to achieve a hierarchy alignment to the target task, i.e., segmentation. To ensure this hierarchy alignment is effected consistently across both modalities and preserves their cross-modal alignment during training, HyperCLIP++ integrates a Dual Cross-Relation Communication (DCRC) module that synchronizes these adjustments between the vision and text pathways. Our experiments show that HyperCLIP++ achieves state-of-the-art performance across three benchmarks while fine-tuning only approximately 5% of CLIP's total parameters. More importantly, we observe that after adjustment, CLIP's text embeddings exhibit a relatively fixed hyperbolic radius across datasets, suggesting that the hierarchical level required for this segmentation task might be quantified using the hyperbolic radius. --- ### Evaluating Transformation Models for pCLE Mosaic Registration Authors: Ahmed Aboelela, Johannes Barcsay, Jana Friedhof, Miguel Gonçalves, Alexander Hann, Katharina Breininger Published: 2026-09-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2609.24560v1 Confocal Laser Endomicroscopy (CLE) provides real-time, cellular-resolution optical biopsy but has a narrow field of view, which image mosaicing can extend to provide anatomical context. Because of line-by-line acquisition, probe motion, and probe-tissue interaction, frame alignment generally requires a non-linear transformation whose accuracy is difficult to quantify: flexible transformation models can fit intensity features and noise, so appearance-based metrics such as Normalized Cross-Correlation (NCC) can improve without a genuine gain in geometric accuracy. We therefore establish a dataset of 132 frame pairs across fourteen pCLE sequences from 4 patients with manually annotated landmark correspondences, so that Target Registration Error (TRE) can serve as a geometrically grounded complement to NCC. We assess the effect of progressively increasing the transformation model's degrees of freedom, from translation to Thin Plate Spline (TPS), and of six feature-matching backends spanning classical (Shi-Tomasi, Lucas-Kanade) and learned (SuperPoint, SuperGlue, LightGlue, LoFTR, RoMa) approaches. Translation and rigid models prove insufficient under tissue deformation, while TPS with random sampling achieves the strongest landmark-derived alignment of the evaluated configurations; among the learned matchers, used without fine-tuning, only RoMa offers a robust, if modest, advantage over other methods. At the sequence level, pairwise registration quality proved an unreliable predictor of final mosaic quality, so mosaic quality must be evaluated directly rather than inferred from pairwise metrics. --- ### $t_0$: A Time-Series Foundation Model for Forecasting with Context Authors: Lucas Meyer, Claudio Sole, Huikan Xiang, Nicolas Li, Lucas Franceschino, Arnau Quera-Bofarull, Maarten P. Scholl, Joachim Fainberg, Geoffrey Négiar Published: 2026-09-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2609.24559v1 We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-alpha}$ and $\texttt{t0-beta}$, respectively 102M and 256M parameters. Both condition their forecasts on target history, past covariates, and known-future covariates, without task-specific retraining. Their transformer layers alternate attention along time and across variates. They produce probabilistic forecasts through quantile predictions. Pretraining combines curated public data with synthetic generator families constructed to contain covariate-to-target dependencies. On GIFT-Eval, $\texttt{t0-alpha}$ reaches an aggregate CRPS of 0.4941, and $\texttt{t0-beta}$ a CRPS of 0.4738 and a MASE of 0.6865, third on both and within 4.0% of the best zero-shot TSFM. On fev-bench they score 42.2 and 46.7 in skill, the latter third again and 2.0 points behind the leader. We analyze $\texttt{t0-alpha}$ in depth. Known-future covariates raise its skill by 6.3 percentage points across 30 tasks. The report also examines its calibration, its rollout strategy on long horizons, and its robustness to missing data. On the Victoria electricity-demand benchmark, $\texttt{t0-beta}$ is among the most accurate models with a context of nearly a year. In an independent Macrocosm evaluation of hourly ERCOT prices over 29 months, both cut the MAE of the lagged-price baseline by 38%. ---