# Research Papers — 2026-10 · bundle page 49 of 156 > Full-text markdown of papers #2401–2450 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/49 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/48.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/50.md) ### Federated Coreset Subsampling for Distributed Memory Banks Authors: Jason Witzemann, Daniel Pröll, Sebastian Hegenbart Published: 2026-10-12 Categories: cs.DC, cs.CV arXiv: https://arxiv.org/abs/2610.16425v1 In real-world scenarios, industrial processes can span multiple factories and goods are often produced at multiple sites, leading to a shared yet non-identical distribution of data across locations. To address this, we propose two federated approaches for i) combining existing coresets (Double Subsampling) and ii) creating new coresets (Federated Subsampling) in a distributed anomaly detection setting. In particular, we adapt the memory bank based PatchCore algorithm to a federated setting, resulting in increased cold-start performance, resilience to domain- and sensor-shift, and resilience to unreliable actor participation, a common problem in classical, network based federated learning strategies. --- ### Learning $ω$-Powered Conditional Distributions with Importance-Weighted Flow Matching Authors: Maciej Falkiewicz, Frantzeska Lavda, Jason Ramapuram, Alexandros Kalousis Published: 2026-10-12 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2610.16419v1 Classifier-Free Guidance (CFG) with guidance scale $γ$ is commonly motivated by the $ω$-powered conditional distribution obtained by setting $ω=γ$, but CFG does not, in general, sample from this distribution exactly. We study whether the powered target can instead be learned explicitly. We introduce Importance-Weighted Conditional Flow Matching (IW-CFM), which reweights conditional flow-matching examples using density ratios obtained from frozen conditional and unconditional flow models. With exact normalized weights, the resulting objective has the same gradient as flow matching on the powered target; in practice, we use self-normalized estimation and a regularized empirical approximation for high-dimensional data. On synthetic distributions, IW-CFM recovers analytical powered targets for which numerically matched CFG, $γ=ω$, exhibits a visible mismatch. On ImageNet, an amortized lightweight corrector achieves better alignment than fixed- and matched-guidance CFG with the corresponding weighted and filtered reference distributions. We additionally present an exploratory CLIP analysis of powered-density rankings on real ImageNet data. Aggregate shifts across selected prompt-specific contrasts coexist with heterogeneous classwise responses, including nonmonotonic trajectories. These results provide a practical route for studying and approximating model-defined powered conditional distributions. --- ### Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps Authors: Anton Firc, David Drtil, Martin Perešíni, Milan Šalko, Vojtěch Staněk, Kamil Malinka Published: 2026-10-12 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2610.16417v1 Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can replace that person before the stream reaches the verifier. Passive deepfake detectors generalize poorly to new generators, while interactive challenges are often selected without evidence of which gestures expose current attacks. We evaluate randomized gesture challenges in 108 live sessions with six subjects, 24 impersonated identities, and two face-swap tools, DeepFaceLive and FaceFusion, injected through a virtual camera. The static calibration segment reaches a session-level AUC of 0.878 with a frozen UCF spatial detector, while the mean across the active-gesture windows reaches 0.988. Pose and combined gestures have the highest point estimates, whereas expressions show no clear improvement. Hand occlusion against FaceFusion, configured with an occlusion mask, scores below the static baseline. The end-to-end time required to satisfy the validator also distinguishes attacks from genuine sessions, achieving a session-level AUC of 0.732, although this signal includes synthesis and transport delays. These results show that challenge sets should be tested against current attack configurations and that response time can provide an additional, deployment-specific signal. --- ### Chain Dimension Scaling: Communication-Efficient Loop-Style Scaling for Industrial Short-Video Ranking Authors: Zhimeng Jiang, Yuening Li, Ruixiao Sun, Yuanzhen Lin, Kun Jin, Chuan He, Liang Liu Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16415v1 Industrial recommendation rankers keep scaling in width and depth to billions of parameters, but this increasingly incurs costs in parameter growth, distributed communication overhead, and training inefficiency. We introduce \underline{C}hain \underline{D}imension \underline{S}caling (CDS), a scaling strategy orthogonal to width and depth. CDS repeatedly applies a single feature-interaction block with parameters shared across iterations, so the number of iterations (the chain length) becomes a new scaling dimension that adds no parameters. A lightweight intra-chain residual connection stabilizes optimization and improves quality. CDS enables two regimes. In the \emph{compression regime}, shallow blocks with a longer chain match deeper baselines with fewer parameters and faster training; in the \emph{quality-scaling regime}, increasing chain length under a fixed parameter budget yields consistent offline and online gains, suggesting the chain dimension adds modeling capacity beyond parameter reuse. We evaluate CDS in a large-scale multi-task short-video ranking system in production. In the compression regime, CDS stays within $0.03\%$ of baseline offline quality while reducing trainable parameters by 26.6\% and improving training throughput by 6.4\%, with neutral-to-positive online participation. In the quality-scaling regime, quality improves monotonically with chain length. Wall-clock analysis shows the efficiency gain comes mainly not from reduced FLOPs but from lower cross-device synchronization overhead and reduced optimizer update cost. These results position parameter-shared iterative computation as a practical, communication-efficient scaling axis for industrial ranking systems. --- ### SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data Authors: Valerii Iakovlev, Markus Spanring, Martin Flechl Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16412v1 As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summarizing large log streams into human-readable reports. Further progress requires meaningfully evaluating this function, yet existing benchmarks leave end-to-end summarization from large log streams underexplored due to the prohibitive cost and complexity of collecting real-world data. We introduce SLS-Bench, a benchmark for incident log summarization featuring 90 tasks grounded in real-world incident reports, each with a synthetic log stream and a reference summary. To construct SLS-Bench, we developed a data generation pipeline that converts incident reports into structured incident models, which guide the generation of synthetic logs and reference summaries. This pipeline combines narrative grounding, explicit incident modeling, generator-verifier loops, and statistical comparisons with real-world log streams to produce realistic and controllable observability data. Our evaluation of 14 LLMs on SLS-Bench shows that while frontier models can produce useful summaries, they do so at substantial cost and latency, and open-weight models lag significantly. SLS-Bench provides a framework for systematic evaluation of log analysis agents and a scalable blueprint for future synthetic observability benchmarks. --- ### Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios Authors: Francesco Baldo, Luca Castri, Gloria Beraldo, Nicola Bellotto Published: 2026-10-12 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.16411v1 Deploying robots in human-shared environments requires deciding not only how to navigate, but also when dedicated social signals are worth emitting. Classic observation-based inference can be misleading in such settings: confounding factors may bias the estimated relationship between a signal and the task outcome, leading to incorrect decisions. Causal inference provides a framework for disentangling these relationships by modelling the mechanisms linking observations, actions, and outcomes, and by estimating interventional effects after accounting for confounding paths. We study a human-robot interaction scenario in a corridor and use a causal model to estimate whether a social navigation signal causally improves transit success. We represent the interaction as a causal DAG involving robot action, pedestrian occupancy, available space, task outcome, and a controlled confounder (static obstacles). We compare the interventional estimate with the observational estimate obtained by conditioning only on the robot action, which does not explicitly model interventions. Our results show that accounting for confounding variables can reverse the conclusions drawn from naive observational analysis: the observational estimate wrongly suggests that the social signal is detrimental, whereas the causal estimate shows that it is beneficial. This discrepancy highlights how failing to account for confounding can lead to incorrect conclusions and demonstrates the importance of causal models for context-aware signalling decisions in social robot navigation. --- ### Recovering from Pose-Selection Failures in Repeated Visual Localization Authors: Jaehyun Kim, Wonseok Kang, Tae-Wan Kim Published: 2026-10-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.16409v1 Repetitive structures can give an incorrect pose candidate more inlier support than an accurate one, causing visual localization to select it. History-Guided Pose Reselection (HPR) uses coarse position forecasts from up to five past localization outputs to distinguish well-separated current-query candidates. The best-fitting forecast proposes an alternative; HPR accepts it only if every well-fitting forecast is much closer to it than to the localizer's pose. HPR needs no odometry and returns the selected candidate unchanged, using prediction for selection rather than pose refinement. With one development-set threshold, HPR improves recall within 5 meters and 10 degrees in all 12 main configurations of Hierarchical Localization (HLoc), MASt3R-based pose generation, and JIST-based retrieval, losing successes on fewer than 0.4 percent of queries. On NAVER Gangnam B1, HPR corrects 97 HLoc failures and loses six successes; gains persist within 0.25 meters and 2 degrees on all three HLoc test sets. Median HPR runtime on HLoc candidates is below one millisecond, excluding pose generation. Recovery weakens under less frequent localization. --- ### EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications Authors: David Nukrai, Bar Alon, Nativ Levy, Ido Andrew Atad, Ido Cohen, Itamar Zimerman, Lior Wolf, Eli David, Ilan Naiman Published: 2026-10-12 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.16402v1 Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward fixed specifications. We introduce EvoWeb, a novel benchmark comprising 320 cumulative requests over 32 web applications, grounded in real-world product features and structured by functional dependency graphs. Agents iteratively modify a persistent codebase, while a multimodal web agent tests each intermediate application in a live browser, assessing newly requested functionality, cross-request integration, and previously requested functionality. To characterize reliability throughout development, we integrate trajectory performance across user-tolerance thresholds rather than impose a fixed stopping criterion. Experiments across open- and closed-source frontier models show that EvoWeb reveals clear performance differences between models, with cross-request integration emerging as a key challenge. Further analysis shows that later requests with deeper or more numerous dependencies are solved less accurately, while runtime errors become more frequent over successive requests. EvoWeb provides a testbed for evaluating and improving coding agents in long-horizon, multi-request development. --- ### Recursive Environment Scaling for General Long-Horizon Agents Authors: Lingxiao Jing, Zhengbo Jiao, Yichen Xiang, Bofan Zhu, Lingbei Meng, Yan Ni, Haorui Chen, Ran Ran, Zhirong Shen, Yuheng Yang, Chenhang Cui, Yaosong Du et al. Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16397v1 We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environment Scaling (RES), transforms existing benchmark environments while preserving their objectives and completion requirements. A proposer changes information access, resource relations, and execution dependencies; execution-grounded checks validate the resulting candidate, and accepted changes are inherited across rounds. This produces related environments for paired evaluation and training-trajectory collection. Experiments on 294 initial tasks from three benchmarks show lower task success for all six evaluation models, with decreases of 57.14--77.14 percentage points on Claw-Eval-Live. With equal trajectory counts and identical optimization settings, fine-tuning on RES trajectories outperforms original-trajectory SFT in all nine model--benchmark comparisons by 7.00--14.61 percentage points. Ablations identify recursive inheritance and dependency composition as important contributors to increased difficulty. Together, these results support environment scaling for both agent evaluation and training. --- ### Sampling from Neural Operator Priors to Solve Partial Differential Equations Authors: Andrew Millard, Joshua Murphy, Zheng Zhao Published: 2026-10-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.16396v1 Guided sampling with sparse observations and PDE residuals has recently been combined with neural operator priors to solve partial differential equations in function space, their natural setting. We pair such a prior with pseudo-bootstrap sequential Monte Carlo (pBS SMC), a guided sampling framework that accommodates proposals without tractable densities, and introduce a new proposal by adapting the DPM++ algorithm to the guidance setting. Across five benchmark PDE systems this proposal attains the best error--time trade-off at every step count tested, and wrapping it in pBS gives the lowest error on most inverse-problem settings, with the largest gains when few sampling steps are used. --- ### RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning Authors: Ye Rin Kim, Yongjun Jeong, Seongjun Yun, Hanbum Ko, Soohyun Oh, Sungbin Lim, Sungwoong Kim Published: 2026-10-12 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.16391v1 Multi-step retrosynthesis planning is often considered solved once a route to purchasable starting materials is found, but such a route should also be practical in real-world chemistry. Recent LLM-based planners formulate this process as sequential decision-making over an AND-OR graph, yet typically expand a single molecule per turn and are optimized for solvability alone, leaving alternative routes uncompared across the multiple objectives that determine practicality before the search budget is committed. We introduce RetroPlanner, an LLM-based planner that jointly compares multiple routes to steer the search toward higher synthesizability, as measured by reaction plausibility, round-trip consistency, and starting-material price. RetroPlanner is trained to reason over chemical evidence: structural progress from the target molecule, bond changes and reaction classes, where candidate routes diverge from one another, and how they rank across multiple objectives. Experiments on multi-step retrosynthesis benchmarks demonstrate that RetroPlanner recovers more alternative routes than prior LLM-based planners while improving synthetic route quality and maintaining a high success rate. --- ### QBFF: Deep Quantum Bottleneck for Automatic Speaker Verification Anti-Spoofing Authors: Anton Firc, Nouhaila Innan, Vojtěch Staněk, Kamil Malinka, Martin Perešini, Zbyněk Lička, Walid El Maouaki, Alberto Marchisio, Muhammad Shafique Published: 2026-10-12 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2610.16390v1 A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining executable on real hardware. We investigate deepfake (synthetic) speech detection, a largely unexplored application in this area, where reliable confidence scores are as important as discrimination performance because deployment decisions are made at fixed thresholds and overconfident errors can be costly. We introduce QBFF, which routes a compressed speech representation through a small 8-qubit variational circuit (VQC) used as a drop-in bottleneck, with a matched classical bottleneck as the control. The quantum circuit yields better-calibrated confidence in most matched comparisons, including out-of-distribution evaluation, though the downstream deployment-cost benefit is model-dependent. We then run the same circuit on a real IBM quantum processor. To our knowledge, this is the first anti-spoofing pipeline to run on a QPU; hardware execution demonstrates feasibility, with lower subset EER and $C_{llr}$ but higher mean actDCF than the matched classical reference. Together, these results show that hardware-executable quantum bottlenecks can improve score reliability, with gains that vary by evaluation setting. --- ### Throwing4: Phase-Aware Pose Modeling for Throw-Distance Prediction in Elite Athletics Authors: Bikash Kumar Badatya, Kartike Tiwari, Jyotirmoy Amin, Ravi Hegde Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16383v1 Elite athletics throwing provides a structured biomechanical action sequence together with an objective continuous outcome, namely throw distance, making it a suitable setting for performance-oriented sports analytics. In this work, we investigate whether explicit phase alignment of pose dynamics improves throw-distance prediction under realistic broadcast conditions. To support this study, we curate Throwing4, a dataset of 500 elite throwing clips spanning javelin, discus, hammer, and shot put, with corresponding two-dimensional pose sequences, frame-level phase annotations, and official distance labels. We formulate throw-distance prediction from broadcast-derived pose as a regression problem and compare full-sequence modeling against a phase-conditioned approach that partitions each attempt into four technique stages and fuses phase-specific motion representations. Experiments across multiple graph-based pose encoders show a consistent reduction in prediction error when phase structure is incorporated, indicating that phase-aligned modeling provides a more stable representation than treating the entire motion as an unstructured sequence. These findings suggest that explicit biomechanical phase information is a useful inductive prior for pose-based performance modeling in elite athletics throwing. Beyond score prediction, the dataset and protocol provide a basis for future work on fine-grained technique analysis, interpretable sports analytics, and robust modeling from broadcast video. --- ### PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization Authors: Hang Su, Zequn Liu, Jianghan Chao, Qiuyu Tian, Xuesong Lu, Yingce Xia Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.16372v1 Although users may express different personalization needs across tasks, these task-specific behaviors can reflect shared underlying preference mechanisms. Existing LLM personalization methods often focus on surface-level interactions or undifferentiated histories, overlooking the shared mechanisms underlying these behaviors. We introduce PersonaFactors, a framework that distills reusable and interpretable personalization factors from heterogeneous user interactions. We construct a library of thirteen PersonaFactors by extracting evidence-grounded rationales and clustering recurring patterns across tasks, and develop a dynamic factor-guided generation framework that selects factors relevant to each user's history and current request. Across four personalization benchmarks and four backbone models, Dynamic PersonaFactor achieves the best score on every reported metric. Representation analyses further show that PersonaFactors and user history induce partially overlapping low-dimensional representations, and that their joint use yields complementary shifts. Taken together, these findings suggest that factor-based and history-based personalization can mutually reinforce each other. --- ### Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs Authors: Eugenie Shi Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.16371v1 Large language models are increasingly deployed in morally and legally sensitive contexts, yet little is known about how they internally represent distinctions between moral reasoning styles. We ask whether a model's differential response to rule-framed and consequence-framed moral questions reflects distinct internal structure or merely surface lexical sensitivity. We construct a 2$\times$2 factorial dataset crossing reasoning style (rule-based vs. consequence-based framing) with judgment polarity (permissive vs. prohibitive), drawn from three established moral reasoning benchmarks and evaluated on a cleanroom test set of novel phrasings that includes conflict pairs where the two framings predict opposite labels. Using linear probing and activation steering, we identify two orthogonal directions in the residual stream: Dir-A tracks reasoning style and Dir-B tracks judgment polarity, each near-blind to the other factor (cross-correlation $|r| < 0.04$). This double dissociation replicates across three instruction-tuned models from different developers at comparable proportional depth, and it is not knife-edged in layer: the directions are recoverable and causally effective throughout an extended band of the network. Dir-A can causally change judgments, and in conflicting scenarios, it selectively corrects errors in rule-based judgments without changing consequence-based judgments, suggesting that it does not simply make the model more likely to accept everything. Generalization beyond the training templates is partial: the direction transfers across benchmark sources, but its advantage over lexical baselines on novel phrasings is modest. We therefore frame the result as moral reasoning style sensitivity, a geometrically dissociable and causally effective structure, rather than internalized normative reasoning. --- ### LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers Authors: Zhixiong Zhao, Zukang Xu, Xing Hu, Lifeng Liu, Guangyu Sun, Dawei Yang Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.16368v1 Looped Language Models (LoopLMs) improve parameter efficiency by recursively reusing shared Transformer modules, yet their repeated computation over evolving recurrent states poses new challenges for low-bit deployment. Existing post-training quantization (PTQ) methods, largely designed for feed-forward Transformers, fail to account for cross-loop activation dynamics, heterogeneous loop sensitivity, and recursive error propagation, leading to substantial performance degradation at low precision. To address these challenges, we propose LoopQuant, a loop-aware PTQ framework for accurate and efficient low-bit quantization of LoopLMs. LoopQuant is built on three core components: 1) Cross-Loop Distribution Canonicalization (CLDC) learns a shared quantization-friendly representation across recurrent states while preserving parameter sharing; 2) Interaction-Aware Loop-wise Precision Allocation (ILPA) allocates activation precision under a fixed bit budget by modeling task-level loop sensitivity and cross-loop interactions; and 3) Loop-Conditioned Task Calibration (LCTC) further aligns quantized inference with the low-bit recursive trajectory through lightweight task-space calibration. Extensive experiments across LoopLM architectures demonstrate that LoopQuant consistently outperforms existing low-bit PTQ methods. On Ouro-2.6B, LoopQuant under W4A4 surpasses all W4A8 baselines in performance, while reducing model memory by 65.3% with only 3.4% additional storage overhead over naive INT4 and achieving a 1.7 times decoding speedup over BF16. These results demonstrate a strong balance among accuracy, compression, and inference efficiency, providing a practical and deployment-friendly solution for low-bit LoopLM inference. The code is available at (https://github.com/Kishon-zzx/LoopQuant). --- ### World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models Authors: Shinseong Kim, Jaeseok Jeong, Jianlong Fu, Youngjung Uh Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16365v1 Video world models must generate physically plausible futures, not just realistic frames. Existing approaches typically use semantic, physical, or predictive information to guide the visual generation stream, leaving a fundamental question: where inside the generator should predictions of scene evolution live? Standard video tokens jointly encode appearance and dynamics, but provide no distinct state for learning and reading predictive dynamics. We answer this question with the Physical Registry: temporally grounded registry slots inside a video DiT that are initialized from an observation-conditioned forecast, co-evolve with video tokens, and receive future-representation supervision, making predictive dynamics an explicit, readable state of the generator. In a controlled comparison of predictive-state interfaces on Physics-IQ Verified, Physical Registry improves vanilla fine-tuning by 9.9/8.7 points on I2V/V2V, the largest gain among the interfaces we compare. Across all Cosmos and WAN backbones, Physical Registry improves Physics-IQ Verified scores. With only 0.45% additional parameters, it enables Cosmos 3 Nano 16B to surpass the published I2V score of Cosmos 3 Super 64B (43.56 vs. 42.7). On WorldModelBench, it also improves physical adherence and the total score for all four evaluated backbones. Because the registry becomes candidate-specific while remaining readable, the Physical Registry Selector (PRS) ranks emerging futures by how far their intermediate registry readouts depart from the shared forecast before full denoising is complete. Across four backbones, this selection improves I2V scores by 5.6-15.9% without completed-video external scoring. Together, these results support a broader principle: dynamics prediction should live as an explicit model state that co-evolves with the video representation. Project page: https://grainsack.github.io/physical-registry/ --- ### From Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing Imagery Authors: Zhongyu Pang Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16364v1 Speech-driven visual grounding in remote sensing (RSVG) removes the typing bottleneck of text-based interaction and is intended to preserve prosodic intent, enabling hands-free target acquisition in time-critical missions. The direct-audio paradigm, mapping raw speech straight to a bounding box and bypassing automatic speech recognition (ASR), was recently adopted by RSTalker, but what such grounders actually learn about language remains unmeasured. SemEcho grafts a frozen Whisper speech pathway onto a VLTVG grounding host so that speech and text share one decoder, making the paired text, free by construction since speech corpora in this task are synthesized from DIOR-RSVG expressions, a training-time teacher and a fair, same-host text upper bound. On this instrument we dissect three semantic injection channels (feature-mimicry distillation, word-level CTC supervision, and two-stage ASR pretraining) with linear semantic probes, and release Audio-DIOR-R (80,973 training clips; 10 timbres x K=3; Qwen3-TTS synthesis with online sox noise lambda in (0, 0.4)) and Audio-DIOR-Comp, a re-split holding out 17 attribute-category combinations under a 2x2 acoustic-semantic protocol. Our anatomy yields four findings. (i) Whether direct alignment beats a domain-trained ASR cascade is decided by recognizer quality: against a weak in-domain cascade (CTC 0.53) direct wins by 9.0 Acc@0.5 points with transcription errors concentrated on spatial-relation words, but a strong in-domain cascade (CTC 0.029) reaches the text upper bound (80.8 vs. 81.0) and beats even the strongest direct model by 8.8 points; the anti-ASR premise holds only against weak recognizers. --- ### HexaBee-4B: Six-Language Translation with Multilingual Answering and Bidirectional Supervision Authors: Iman Barati, Mohammadmostafa Rostamkhani, Mohammad Badzohreh Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.16361v1 Multilingual translation requires a model to preserve meaning while producing text in a requested language. We present HexaBee-4B, a translator adapted from Gemma 3 4B IT through three stages: Wikipedia continued pretraining, joint multilingual answering and answer-text translation, and bidirectional translation specialization. The intermediate stage connects two tasks through shared multilingual answers: answering a question in the requested language and translating an answer into that language. It comprises 19.46 million answering records, including 5.76 million cross-language question-answer pairs, and 10.70 million answer-text translations. The final stage uses 658,274 forward and reverse synthetic translation examples. On 36,572 synthetic test examples spanning all 30 directions among Arabic, Chinese, English, Hebrew, Persian, and Spanish, HexaBee-4B achieves direction-macro chrF++ of 73.75, compared with 57.11 for Gemma 3 4B IT and 66.83 for Gemma 3 12B IT. BLEU, TER, COMET, and a matched model-judged subset support the same overall ranking. These results demonstrate improved translation across the six-language set, with chrF++ gains in every evaluated direction over both baselines. --- ### VideoSlate: Stateful Commit Control for Temporally Grounded Agentic Video Reasoning Authors: Shuo Zheng, Yuanjie Dang, Peng Chen, Jianjun Xiang, Ronghua Liang, Mohammed Bennamoun, Qiuhong Ke Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16357v1 Agentic video reasoning systems gather and assess video evidence across stages, selecting relevant spans as visual evidence for answering questions. New candidates and observations prompt reassessment of the current span, but revisions can correct localization errors or discard useful evidence already present in the adopted span. Systems therefore need to connect evidence organization across stages with temporal state control, allowing accumulated information to jointly inform revision assessment while explicit adoption decisions govern how assessment outcomes affect downstream visual evidence. We introduce VideoSlate, a stateful commit-control framework built around shared evidence. A typed evidence blackboard links candidate spans, provenance, construction, and verifier observations, enabling an incumbent-relative certifier to assess revision support from the candidate, current span, and related proposals. Based on certification, the controller authorizes a revision or retains the current span, separating evidence accumulation from state updates and recording each decision and its evidence on the blackboard. Extensive evaluations across video grounding and grounded question-answering benchmarks show that VideoSlate can improve temporal localization through selective revision. --- ### naspaclust: A hybridisation of spatial fuzzy clustering with nature-inspired optimisation Authors: Bahrul Ilmi Nasution, Rezzy Eko Caraka, Robert Kurniawan Published: 2026-10-12 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2610.16356v1 We present an overview of R package called \texttt{naspaclust}, a tool for spatial fuzzy clustering improvement by hybridising the Fuzzy Geographically Weighted Clustering (FGWC) with nature-inspired optimisation algorithms. There are seven optimisation algorithms in general, namely Artificial Bee Colony, Flower Pollination Algorithm, Gravitational Search Algorithm, Harris-Hawk Optimisation, Intelligent Firefly Algorithm, Particle Swarm Optimisation, and Teaching-Learning Based optimisation. The optimisation algorithms available do not only use the basic algorithms, but also the modified version of several parts such as randomisation terms and updating rules. Furthermore, we also provide additional options by providing more distance metrics options based on the \texttt{ rdist} package. This study showed the implementation of the \texttt{naspaclust} package in various cases, as well as comparing the performance of the algorithms in the scope of basic algorithms. The \texttt{naspaclust} package allows to improve the performance of fuzzy clustering, mainly in spatial context. --- ### Self-Distillation with Verbal Regularization Authors: Jiazheng Li, Yawei Li, Junru Lu, Zhenyi Shen, Di Yin, Lin Gui, Xing Sun, David Rügamer, Xinpeng Wang, Yulan He Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.16354v1 On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student. The teacher is conditioned on privileged information (PI), such as verified solutions. The student, which does not observe PI, learns from the teacher's next-token distributions along its own sampled responses. However, PI can bias supervision toward shortcut reasoning with limited verification or reconsideration, accompanied by a sharp drop in the entropy of the output distribution. To address this challenge, we introduce self-distillation with verbal regularization (VRSD), which uses system prompts to regulate how the teacher uses PI, thereby encouraging rethinking and exploration to counteract premature commitment. Theoretically, we model prompting as attenuating the influence of PI on the teacher distribution and derive conditions for entropy preservation. Across three models and four tasks, VRSD improves Pass@1 over OPSD in 11 of 12 model-task settings, by 3.9 percentage points on average, while generally maintaining higher token entropy. --- ### A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes Authors: LoonSage Team, Bowei Song, Caiwei Zhao, Chuwen Liu, Dechuang Gu, Dong Fang, Feiyu Xie, Huaiyu Li, Hui Zhang, Jian Tian, Jian Wang, Jie Zhao et al. Published: 2026-10-12 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.16352v1 Reinforcement learning (RL) has emerged as a critical phase in the post-training pipeline of large language models (LLMs). As the frontier of LLM capabilities shifts from static reasoning to agentic tasks--characterized by external tool invocation, multi-turn interactions, and long-horizon decision-making--existing mainstream RL frameworks have grown increasingly unwieldy, raising the overhead of adoption, usage, and debugging. To address these challenges, we present LoongSage, an agent-native, fully asynchronous RL framework with a lightweight core of roughly 14K lines of code. Built upon Megatron for distributed training and SGLang for high-throughput inference, LoongSage centralizes orchestration within a single controller process and encapsulates all GPU-resident components as Ray actors. It introduces AgentFlow, a unified execution paradigm that orchestrates both white-box and black-box agents. For asynchronous execution, it integrates sliding-window strategies that bound trajectory staleness, and employs TransferMesh, a topology-aware synchronization mechanism that routes weights after each step over the fastest transport available to each receiver. Beyond agentic RL, LoongSage incorporates a memory-efficient Teacher Manager that decouples the scaling of teacher models from GPU memory constraints, natively supporting Multi-Teacher On-Policy Distillation. Extensive evaluations across four complete training runs, spanning complex reinforcement learning and multi-teacher distillation, demonstrate that task rewards improve steadily while the train-inference gap is kept under continuous control, and the fully asynchronous pipeline removes synchronous idle bubbles, sustaining hardware utilization. --- ### RIFT: Token Influence Follows the Path of Least Resistance Authors: Tingan Jin, Shuhang Dong, Haosong Li Published: 2026-10-12 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.16349v1 Which context tokens drive a language model's answer? Graph-based tools such as attention rollout and attention flow answer this from a single forward pass, yet their faithfulness in decoder-only models is rarely tested against interventions. We view the layers of a decoder as a causal network whose conductances are attention weights, and read a token's influence on the answer from the resistance between them. We propose RIFT (Resistance-based Information Flow in Transformers), which scores a token by the series resistance of its path of least resistance to the answer, found exactly by a classic shortest-path dynamic program. On synthetic in-context retrieval tasks and extractive question answering over Wikipedia paragraphs, RIFT predicts the effect of replacing a token with a Spearman correlation of 0.52-0.68; predicting a single replacement, it reaches 77-96% of the agreement between two different random replacements. It needs no gradients and no extra forward passes, scoring every token of a prompt in 0.9-3.4 ms on one CPU thread, whereas the replacement experiment needs a forward pass per token. On 576 held-out prompts from four models of two families (Qwen3 and Llama 3.2), it outperforms token distance, attention rollout and attention flow in every pre-specified comparison, by 0.23 to 0.88 in mean Spearman correlation, and it is the best or tied-best of all attention-based scores we test. Aggregates that add up all routes (attention flow, effective resistance and rollout) instead mostly encode token position: as a simple proposition shows, early tokens have many more parallel routes to the answer. --- ### DWI Connectome-based Sex Classification in Young using Supervised Variational Autoencoder Authors: Aditya Kothapalli, Aaryan Gera, Sathvik Reddy, Ninad Aithal, Debanjali Bhattacharya, Neelam Sinha Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.16348v1 During adolescence, significant changes in brain development are influenced by hormonal changes that impact both the body and the brain. This study presents sex classification in 787 young adults having age range of 15-25 years using Diffusion-weighted (DWI) structural connectome, focusing on 82 Desikan-Killiany atlas ROIs. A supervised variational autoencoder (SVAE) is used to extract latent space features from DWI connectome data. Although several studies explored differences in brain structure and function between sexes, the main contribution of this study lies in incorporating SVAE to learn a compact, regularized latent representation for the task of sex classification. Initial exploratory data analysis shows that these features can capture the differences in sex-specific latent space patterns. Subsequently, the learned latent space SVAE features are fed to different ML models for sex classification. Among the considered ML classifiers, the multi-layer perceptron yields the highest accuracy of 80% in classifying sex. This demonstrates the effectiveness of SVAE in learning compact, informative representations from DWI connectome for sex classification. The present work highlights the potential of using DWI brain connectomics and deep learning to differentiate sex, paving the way for future research on diverse populations that may include transgender individuals, to better understand sex-related variations in brain structure. --- ### Rescuing Points Trapped Inside Incorrect Decision Regions: A target for Evaluating and Improving Forward-Forward Learning Authors: Alireza Rahmansetayesh, Amirhossein Yousefiramandi, Maxwell Spiridonov, Sumit Raut, Kent Ziti, Pierre Baldi Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.16347v1 Forward-Forward learning replaces end-to-end backpropagation with local, layer-wise training objectives. Its variants are evaluated primarily by classification accuracy, often measured with linear probes trained on their representations. We show that this evaluation can over-credit the learning method: a linear probe on the representations of an untrained convolutional neural network already reaches accuracy well above chance. Moreover, a single accuracy value does not reveal which datapoints become correctly classified after training and which remain misclassified. To examine what learning contributes beyond the random, untrained baseline, we present an analysis methodology built on the Boundary Proximity Index (BPI), a multiclass margin normalized by a class-centroid reference. We apply our analysis to seven Forward-Forward variants and related layer-local methods and find that initially misclassified points near the probe's decision boundary generally have higher rescue rates than those farther inside incorrect decision regions. Rescue rates vary substantially across methods, with some correcting a substantial fraction of these deeply embedded points. Together, these analyses offer a way to evaluate representation learning beyond accuracy and identify the rescue of points far inside incorrect decision regions as a target for improving local learning methods. --- ### ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting Authors: Yuchen Jiao, Miao Zhang, Yuxuan Liu, Chengxi Li Published: 2026-10-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.16345v1 Recent advances in instruction-driven time series forecasting highlight a fundamental tension: systems must simultaneously master natural-language instruction following and precise numerical prediction. Current approaches often force a compromise. Large language models (LLMs) can interpret unstructured requests but may be inaccurate when asked to produce forecast values directly, whereas time series foundation models (TSFMs) provide numerical forecasts but typically require structured inputs specifying the target series, context window, and horizon. We present ChronoScribe, which applies semantic-numerical specialization to this workflow. A LoRA-adapted LLM proposes an execution path and context length; deterministic rules resolve the executable configuration. On the specialist path, a frozen TSFM produces quantile trajectories for the task-specified horizon. Deterministic trajectory summaries condition the response, while the LLM neither generates nor revises predicted values. We evaluate a Qwen3.5-9B--Chronos-2 implementation across 23 evaluation dimensions and 30 public datasets against eleven proprietary direct LLMs and three open TSFMs. ChronoScribe has the lowest error on sMAPE, MASE, WAPE, RMSE, and MAE among all evaluated systems, including fixed-context controls. Across these metrics, even the lowest direct-LLM error remains 2.0--2.7 times the corresponding ChronoScribe error. At the system level, ChronoScribe achieves a Task-Level Score (TLS) of 65.5, 10.6 points above the strongest direct-LLM baseline. The results support ChronoScribe's division of labor, in which the LLM handles interpretation, configuration, and communication while the TSFM handles numerical forecasting. --- ### Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate Authors: Seungdong Yoa, Ye Seul Sim, Suhee Yoon, Sanghyu Yoon, Dongmin Kim, Soonyoung Lee, Bumsoo Kim, Junhyun Lee Published: 2026-10-12 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.16343v1 Multi-agent debate has shown promise for improving the reasoning of large language models, yet recent theory suggests its benefits are highly regime-dependent. While interaction can amplify informative signals under corrective conditions, symmetric debate dynamics are neutral in expectation, often making majority voting preferable. We reconcile these views by arguing that debate is effective only when invoked at the right time and with appropriate structure. Based on this insight, we propose LASE: Leader-Adaptive Structured Engagement, a leader-centric multi-agent debate framework that selectively engages interaction only in non-neutral regimes. LASE introduces an asymmetric leader-supporter architecture that enables directed information flow and selective signal amplification, while defaulting to simple aggregation otherwise. Experiments across diverse reasoning benchmarks show that LASE achieves multi-agent-level performance with near single-agent token cost, substantially improving efficiency over static debate and voting baselines. --- ### SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation Authors: Kaisi Guan, Ying Ba, Wenjing Wang, Xihua Wang, Chen Li, Jing Lyu, Ruihau Song Published: 2026-10-12 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2610.16338v1 Recent years have witnessed rapid progress in joint audio--visual generation. However, audio--visual synchronization remains a challenge, as generated speech and sound often temporally misalign with visual events. A key bottleneck is the lack of human-annotated data, reliable evaluation benchmarks, and synchronization-aware evaluation models for generated audio--visual outputs. To address these limitations, we conduct a comprehensive study spanning data, benchmarking, and reward modeling. We first introduce SyncReward-Data-80K, a dataset containing 80K professional synchronization ratings for clips from eight audio--visual generators. A taxonomy-guided construction pipeline covers four sound-event families: Speech, Onset, Instrument, and Ambient. We further construct \textbf{SyncReward-Bench}, a held-out benchmark of 1K clips, each independently rated by multiple professionals. Using this benchmark, we systematically evaluate specialized synchronization metrics and omni-modal models, revealing their substantial misalignment with human judgments. Finally, we develop SyncReward, a reward model that combines semantic--temporal contrastive pretraining on real clips with human supervision on generated clips. As an evaluation metric, SyncReward achieves the strongest agreement with human ratings among the evaluated methods. As a reward, it improves synchronization through inference-time best-of-$N$ selection and reinforcement learning based post-training. We will release the data, benchmark, model, and code at https://github.com/WeChatCV/SyncReward. --- ### WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention Authors: Mijeong Kim, Kyujin Lim, Bohyung Han Published: 2026-10-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.16337v1 Rotary Positional Embedding (RoPE) is widely used to encode relative positions in Transformers. In multi-view settings, however, patch coordinates are defined independently in each image: the same 3D point can therefore have different coordinates across views, making them insufficient for establishing cross-view correspondences. We introduce WorldRoPE, a probabilistic world-centric RoPE for multi-view attention. At each layer, WorldRoPE back-projects each patch token into a set of volumetric Gaussian primitives in a shared world frame. These primitives represent multiple plausible 3D supports for a token, jointly capturing alternative depth hypotheses, depth uncertainty, and the finite spatial extent of its patch frustum. When a key token's support is projected into a query view, it induces a distribution over where that key may appear in the query image. WorldRoPE integrates the rotary operator over this distribution in closed form, combining rotations at the projected primitive centers according to their mixture weights with covariance-dependent attenuation. This makes attention less sensitive to uncertain key locations in the query view, without rasterizing or warping token features. The formulation reduces to deterministic RoPE when the support collapses to a point. Across layers, the predicted geometry guides cross-view attention, while the updated features refine the geometry used at the next layer. Experiments on novel view synthesis, depth estimation, and 3D geometry reconstruction demonstrate the effectiveness of WorldRoPE for multi-view Transformers. --- ### TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents Authors: Yutong Zhi, Jie Zhang, Xiuqi Lu, Jiayuan Xu, Jing Shao Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16333v1 As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the context that produced them. Yet as results persist across caches, recovery mechanisms, and shared runtime state, this association can break, causing a real and unmodified result to be consumed in an incompatible execution context and lead the agent to an unsafe action. We characterize this failure as tool-result misbinding. To systematically study this failure, we introduce ReplayBench, a benchmark that uses controlled tool-result replay to evaluate misbinding across 19 representative agent scenarios, 4 failure properties, and 3 replay mechanisms. Across eight LLMs, three agent frameworks, and diverse stateful workflows, we find widespread replay-induced failures, with a mean Final-State Error Rate of 0.649 under cross-task replay. Stage-wise analysis localizes these failures to model-side action generation. Further analyses show that replay susceptibility varies with task similarity, shows little dependence on object similarity, and remains high under result staleness and implicit environment changes. These findings motivate runtime validity mechanisms that eliminate final-state errors in our evaluated settings while preserving legitimate recovery. The results call for explicit contextual binding in tool-using agent runtimes. Our work is public at https://github.com/Phitooo/Replaybench. --- ### BAT3R: Robust Online 3D Reconstruction with Bayesian Adaptive State Updates Authors: Lijian Li, Yuanpeng He, Yudian Zheng, Chung-ju Huang, Linyu Li, Dongming Jin, Wenpin Jiao, Zhi Jin, Chi-Man Pun Published: 2026-10-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.16330v1 Feed-forward transformer models have driven remarkable progress in 3D vision,yet their quadratic complexity renders them impractical for long video sequences. Streaming 3D reconstruction addresses this bottleneck by processing frames sequen?tially with constant memory. However, existing recurrent architectures inevitably suffer from progressive degradation over long sequences, as they fail to account for the intrinsic reliability of observations and the accumulated confidence of the historical state, leading to severe error accumulation. To address these issues, we introduce BAT3R, a training-free Bayesian adaptation framework comprising two synergistic modules: State Innovation Gating (SIG) and Bayesian-guided Adaptive State Updating (BASU). SIG acts as a distributional regularizer that anchors state evolution to its geometric initialization, effectively arresting representational drift during long-term inference. Building on this, BASU reformulates state update as a recursive Bayesian inference process within a Kalman filtering framework. By jointly modeling the temporal reliability of observations via information-theoretic gain and spatial relevance via cross-attention maps, BASU achieves an asymmetric spatio-temporal state fusion: well-consolidated historical regions are protected from redundant updates, while genuinely novel scene content is aggressively incor?porated. Extensive experiments on standard benchmarks (7-Scenes, TUM, ScanNet, KITTI, etc.) demonstrate that BAT3R consistently outperforms state-of-the-art online 3D reconstruction methods, with the most significant gains observed on long sequences and complex scenes. --- ### Explicitly Aligned Multi-View Breast Cancer Risk Prediction from Variable-Length Screening Histories Authors: Solveig Thrun, Zijun Sun, Suaiba A. Salahuddin, Kristoffer Wickstrøm, Elisabeth Wetzer, Stine Hansen, Robert Jenssen, Michael Kampffmeyer Published: 2026-10-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.16329v1 Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benefit from both temporal breast tissue changes across longitudinal examinations and complementary anatomical information from craniocaudal (CC) and mediolateral oblique (MLO) views. Leveraging longitudinal information requires identifying corresponding tissue regions across examinations, yet most approaches rely on implicit feature alignment without explicitly enforcing spatial consistency. Recent work has demonstrated the benefits of explicit temporal alignment; however, existing methods model each view independently, preventing them from exploiting complementary CC and MLO information. Furthermore, explicit approaches have been limited to a single prior examination. To fill these gaps, we propose (github.com/sot176/FlexLMV-Net), a breast-wise longitudinal multi-view framework that jointly models CC and MLO views across screening examinations while accommodating a variable number of prior examinations. FlexLMV-Net explicitly aligns longitudinal feature maps and integrates complementary views through cross-view temporal fusion and a dual-stream attention block. Evaluated on EMBED and CSAW-CC, FlexLMV-Net consistently outperforms existing approaches across breast density, cancer subtypes, and demographic subgroups, highlighting the benefits of explicit longitudinal alignment, multi-view modeling, and flexible use of available screening history. We further introduce (github.com/sot176/BCRBench), an open-source benchmark that unifies state-of-the-art single- and multi-timepoint breast cancer risk prediction models under standardized preprocessing, training, inference, and evaluation protocols, enabling fair and reproducible comparison of existing methods. --- ### Probabilistic Simulation of Gas-Liquid Interfaces with Coupled Flow Matching on Spherical Harmonics Authors: Kiet Bennema ten Brinke, Rachna Ramesh, Douwe Orij, Ivo Roghair, Vlado Menkovski Published: 2026-10-12 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2610.16327v1 Bubbly flows involve strongly coupled bubble motion, deformation, and hydrodynamic interactions, making high-fidelity simulation computationally expensive. We propose a neural surrogate that jointly predicts bubble trajectories and interface deformation in a compact, shared representation, replacing costly mesh-resolved simulation with fast generative inference. Because two-phase flow dynamics is nonlinear and chaotic, we treat forecasting as a conditional generative problem rather than deterministic regression, predicting entire future windows in a single pass. We train and evaluate the surrogate on BubbleSH, a Front-Tracking dataset of rising deformable bubble swarms, assessing performance using trajectory, shape, and distributional metrics over kinematic, morphological, and interaction-based properties. The surrogate reproduces key flow statistics while running several orders of magnitude faster than the underlying DNS solver. --- ### When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models Authors: Shuhul Razdan, R Balamurugan Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16325v1 When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target-centered, scaled conceptor complement by removing its fitted covariance filter while preserving the same target-specific center and gain. At the original aperture $α=.05$ and gain $β=2$, all 21 fitted maps across three models and seven targets expand every direction at the generation intervention layers. The matrix correction is $0.093\%$--$7.815\%$ of the matched-control displacement on held-out extraction activations. In 480 paired comparisons within a 1,920-response study, retaining the matrix changes many individual texts but does not establish a consistent additional target-suppression benefit on the four-target panel. A geometric aperture sweep shows that the operating regime changes with the filter setting. Separately, an invertible soft filter preserves what an unrestricted affine readout can recover, whereas dedicated erasure methods reduce prediction by newly fitted probes. Together, the results show why a whole-intervention comparison cannot by itself attribute generated behavior to the fitted matrix: analyze the complete transformation, hold shared components fixed, and test its output consequences directly. --- ### Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis Authors: Hangil Park, Seungheon Kim, Tae-Kyun Kim Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16324v1 Training-free language-based video anomaly detection (VAD) uses frozen vision--language models (VLMs) and large language models (LLMs) to localize abnormal events without task-specific model-weight optimization. Existing approaches increasingly exploit broader temporal and semantic context, yet generic context does not necessarily foreground abnormal events or specify how video-level semantics should modify local anomaly scores. We introduce a training-free semantic feedback framework that uses VAD-guided active observation for video anomaly understanding (VAU) and returns the resulting anomaly-focused description to refine temporal detection. Starting from an upstream anomaly-score curve, we adapt reasoning-based iterative frame selection: high-score regions seed the observations, and anomaly scores together with VLM relevance assessments guide subsequent temporal exploration. A frozen video-language model generates a single open-ended anomaly description from the selected frames. The description is returned through two complementary feedback levels: video-level feedback determines whether the score distribution should be suppressed, preserved, or sharpened, with selective visual rechecking, while local feedback retrieves event-related windows and promotes scores only after target-local visual verification. All model weights remain frozen, and feedback is applied once without regenerating the description. On the HIVAU video-summary evaluations of UCF-Crime and XD-Violence, VAD-guided observation improves GPT-rated reasonability, detail, and consistency over the matched CLIP-guided variant. For VAD, semantic feedback improves the re-evaluated upstream detector from 84.36% to 86.25% AUC on UCF-Crime and from 68.07% to 72.58% AP on XD-Violence, where the final AUC is 91.74%. --- ### BehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction Authors: Tobias Schneider, Danial Fahrner, Soren Antebi, Daniel Uedelhoven, Lennard Bodden, Sandra Halscheidt, Rafet Sifa Published: 2026-10-12 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2610.16322v1 Discovering behavioral patterns in open-ended games is challenging due to the lack of clear objectives or ground-truth annotations. In this work, we extend a next-token prediction Transformer with the deep clustering algorithm DCSS to learn meaningful representations with well-separated clusters. In a controlled Minecraft session with 26 players, the method discovers 23 distinct behavioral patterns that generalize across the studied players, further refining structures present in self-supervised representations into clearly separable clusters. We group the clusters into seven interpretable categories covering stationary, roaming, travel, mining, base work, logging, and farming behavior. --- ### Building age estimation based on widely available multi-source1 geospatial data Authors: Jialu Sui, Hongsheng Zhang, Rui Liu, Jing Ling, Ruisheng Wang, Hao Wu, Gang Chen Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16320v1 Building age is fundamental for urban infrastructure safety, operation, and planning, as it directly affects structural safety, and sustainable development. Existing methods mostly rely on detailed building information such as street view, function, or materials, which are harder to obtain than geospatial data like satellite imagery and Digital Surface Models (DSMs). However, existing methods based on those geospatial data mainly rely on optical imagery and local texture features, limiting their ability to capture structural information and distinguish buildings from different periods. Moreover, the inherent temporal ordering among building age categories is often overlooked. To address these limitations, we propose the first deep-learning framework for multi-building age estimation using widely available multi-source geospatial data, including remote sensing data and their derived products, as well as building footprint information that estimates age at both pixel and instance levels within a unified pipeline. Specifically, a large pretrained backbone with fine-tuning adapters extracts representative features, and raster-derived and property-derived fusion modules support pixel-wise and instance-wise predictions. Pixel-level estimation employs a pyramid decoder with Cosine-guided Mixture-of-Experts (CMoE) to fuse multi-source raster data across scales, capturing fine-grained building age differences, while instance-level prediction uses attention pooling and Property-Conditional Adaptive Instance Normalization (PCAdaIN) to extract instance-level representations and integrate property attributes. A Temporal Ordinal Constraint Loss (TOCL) enforces the sequential ordering of predicted ages. We also construct a building age benchmark for Hong Kong to enable comprehensive evaluation. The source code and datasets are available at https://github.com/littlebeen/RS-buildingAge.git. --- ### HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks Authors: Zijian Cai, Haowei Liu, Kailai Chen, Lin Peng, Cong Wan, Ziqi Zhang, Chunfeng Yuan, Bing Li, Weiming Hu, Haiyang Xu Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16319v1 Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluated separately. To bridge this gap, we introduce HyWe, a framework that unifies both capabilities within one model and trajectory. Its two modes use dedicated prompts and tool sets to sustain sub-goal execution; explicit switching selects the needed capability, and shared history lets each mode build on the other's findings. To provide demonstrations of these behaviors, we develop HyWeCollector, a fully automatic pipeline that uses task prototypes, four switching patterns, and multi-agent synthesis to produce verified hybrid trajectories. We train HyWe-35B on these demonstrations to unify efficient information gathering and browser interaction in a single 35B web agent. To evaluate hybrid task completion, we introduce HyWeBench: 100 human-written tasks on websites distinct from training, with human-written sub-goal checklists and an outcome-based evaluation pipeline. Hybrid training enables HyWe-35B to achieve 47.0% success on this benchmark, improving on the untrained base model by 19.0 percentage points and outperforming existing search-based and operation-based agents. Even before training, the same base model solves 28.0% of tasks with HyWe, versus 11.0% with all tools under one prompt. Beyond hybrid tasks, HyWe-35B achieves 59.0% and 88.3% success on Online-Mind2Web and WebVoyager, outperforming existing open-source baselines and cutting action cost per successful task by 48.3% and 51.9% compared with Fara-7B. --- ### Strong yet Controllable LLM Abstention without Learning to Abstain Authors: Junwei Zhang, Yifei Wang, Wanli Yang, Hexiang Tan, Rui Tang, Xin Chen, Jingang Wang, Du Su, Fei Sun Published: 2026-10-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.16318v1 Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong. Abstention can be implemented outside the model (selective answering) using a confidence threshold that controls the answer rate (coverage), or learned inside it (abstention training), which can perform better but fixes coverage once trained. To compare the two, we match their coverage and decompose risk (error rate) into answering ability and distinguishing ability, i.e., how well the model answers and how accurately it abstains, respectively. The decomposition shows that abstention training performs better mainly by answering better: with strong confidence estimators, the two have nearly equal distinguishing ability. This motivates Train for Accuracy, then Post-hoc Select (TAPS), a modular approach that keeps coverage controllable, needs only standard post-training and an off-the-shelf confidence estimator, and benefits from advances in either component. Across three LLMs and three factual QA benchmarks, TAPS with a probing-based confidence estimator attains 1.5--9.4 percentage points lower mean risk than three representative abstention training methods at matched coverage. Within TAPS, accuracy training often weakens the model's own confidence signals, yet refitting the estimator largely preserves distinguishing ability. Together, these results establish TAPS as a strong yet controllable baseline and raise the bar for future abstention training: sacrificing control over coverage should yield gains beyond what can be achieved by optimizing answering and abstaining separately. --- ### ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning Authors: Yike Wu, Keyan Chen, Qixiong Wang, Xi Xiang, Maofei Que, Xiaolong Jiang, Xiaoqin Zhang, Ling Shao, Shijian Lu Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16315v1 Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate computation may duplicate resolved work, introduce noisy evidence, and perturb correct predictions. We propose that such computation should be residual: allocate additional computation only to requirements unresolved by the base model and, after a localized failure, recompute only the affected states. We instantiate this formulation in ReTAC, a training-free multiagent framework for video spatial reasoning. ReTAC organizes supplementary computation around unresolved requirements. It plans ordered steps to acquire missing spatial evidence and combines the observations with compatible native evidence for reasoning. In addition, it uses stage-aligned verification to localize failures to planning, perception, or reasoning. Dependency-based recovery recomputes only affected states while reusing unaffected ones. Extensive experiments show that ReTAC achieves the highest overall score among the compared methods across three mainstream MLLMs and two widely adopted benchmarks. Further analyses show that gains from additional computation depend not only on how much is used, but also on where it is allocated and which valid intermediate states are preserved. --- ### Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment Authors: Haoming Yang, Ke Ma, Yangbangyan Jiang, Ligong Zhang, Xiaojun Jia, Longtao Huang, Yingfei Sun, Qianqian Xu, Qingming Huang Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16312v1 Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We identify a distinct challenge: ensuring the safety of the \emph{multi-step reasoning process} itself, where locally coherent steps may still lead to globally harmful outcomes. To explore this vulnerability, we propose PDRA (Paradox-driven Reasoning-based Attack), a novel attack method that programs a harmful reasoning trajectory. PDRA first constructs a paradoxical narrative core by pairing a malicious actor (e.g., a terrorist) with a benign task (e.g., writing a safety bulletin). It then embeds this core into a structured analytical framework that forces the model through a mandatory three-stage analysis -- surface purpose, latent intent, and operational reconstruction -- guiding it to produce detailed harmful content while maintaining narrative coherence. Mechanistically, we show PDRA steers the model's internal representations away from refusal-related patterns, suppressing safety-triggering lexicons while activating planning-oriented terms. Empirically, PDRA achieves state-of-the-art attack success rates across diverse LLMs with high efficiency. \textcolor{red}{\textbf{Warning:} This paper may contain sensitive content.} --- ### ATTCK-R: Knowledge-Aware Long-Horizon Jailbreaking for Protected LLMs Authors: Md Mushfiqur Rahman, Tobias Rohde, Rahul Tripathi, Khalil Elkhalil, Kevin Lybarger Published: 2026-10-12 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2610.16305v1 As large language models are deployed behind increasingly sophisticated safety mechanisms, evaluating their robustness under realistic adversarial conditions becomes increasingly difficult and critical. Existing jailbreaking evaluations often rely on static prompts, limited interaction horizons, or lightly protected systems, failing to reflect protected deployment settings with prompt-based safety protections. We show that the introduction of a prompt-based safety protection reduces the average attack success rate of a strong multi-turn baseline from 0.896 to 0.608 (32.1\% relative), demonstrating that unprotected evaluations substantially overestimate real-world vulnerabilities. We propose Adaptive Traceback and Tactic Curation for Knowledge-based Red-teaming (ATTCK-R), a planning-driven multi-turn red teaming framework designed for protected black-box systems. ATTCK-R models jailbreaking as a long-horizon trajectory optimization problem using a structured belief state, introduces optimization-based tactic curation to abstract reusable strategies from prior successes and failures, and employs informed traceback to resume attacks from strategically meaningful states rather than restarting. Evaluated across 9 widely used LLMs configured with a single prompt-based safety protection layer, ATTCK-R consistently outperforms strong recent multi-turn jailbreaking frameworks. Ablation results confirm that long-horizon planning and tactic curation improve attack effectiveness, while adaptive traceback improves efficiency through structured recovery from conversational failure. --- ### RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models Authors: Yaoyang Liu, Dongyu Yan, Yihua Du, Shengju Qian, Zeke Xie, Xin Wang, Ying-Cong Chen, Long Chen Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16302v1 Video-based interactive world models aim to enable real-time, user-controllable environments. Yet most existing systems are trained and rolled out at a fixed temporal rate, limiting both runtime-rate adaptation and physical-horizon coverage -- a limitation we term temporal-rate coupling. Specifically, when runtime generation throughput differs from the learned temporal rate, the generated world evolves unintentionally more slowly or quickly. Moreover, using a single temporal rate imposes an inherent trade-off between temporal granularity and physical horizon: higher rates capture finer motion but cover a shorter duration under a fixed context window. To address both limitations, we introduce Rate-Adaptive Rollout (RAR), a framework that enables interactive world models to roll out at controllable temporal rates. At its core, Stride-RoPE aligns latent frames sampled at different rates on a shared physical-time coordinate, enabling consistent multi-rate rollout, unseen-rate generalization, and online rate switching without discarding history. Meanwhile, RAR uses multi-stride video sampling to enable joint learning of fine-grained dynamics and long-horizon evolution. Across action- and camera-controlled environments, RAR achieves temporally consistent multi-rate rollout and online rate switching while preserving high-rate generation quality and extending physical horizons under matched training budgets. RAR also transfers to pretrained world models while preserving perceptual quality. --- ### FON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention Authors: Helong Hu, Hongdan Pan, Shuiqing Hu Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16301v1 Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position signals bound to the training length. Existing attention-free alternatives all optimize the single function of generation. We propose FON (Fusion-Organ Network), which differentiates one weight stack into a drafting organ (multi-tap learnable delays + content-adaptive recursion; causal, O(S) training, O(1) decode state, no sequence-level quadratic attention) and a revision organ that re-processes the written prefix through multi-scale ripple kernels injected via weak gates, never generating. At 30M parameters, iso-parameter and iso-token budget, FON reaches perplexity 131.03 on WikiText-103, beating Transformer (197.73) and Mamba2 (152.53); the advantage persists under all depth-aligned baselines and at the 70M tier (-20.8%). At 8x length extrapolation FON degrades by ~8-9% without positional-encoding engineering, between ALiBi and RoPE. The revision channel provides a structural pathway for in-domain infilling that causal architectures lack in principle (+19% over on-demand coupling), at a perplexity cost indistinguishable within measurement precision. We report all costs and boundaries: impaired long-range retrieval, synthetic-task disadvantages, weaker out-of-domain code infilling than a same-recipe Transformer, and a 6.5-12.3x wall-clock gap. --- ### Learning Temporal Evidence Selection for Video Anomaly Understanding Authors: Hangil Park, Seungheon Kim, Tae-Kyun Kim Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16299v1 Video anomaly understanding (VAU) aims to generate language-level interpretations of anomalous events in long videos, requiring visual evidence that supports explanation beyond anomaly detection alone. Existing VAU pipelines commonly rely on anomaly-centric or predefined temporal sampling strategies, which efficiently emphasize suspicious moments but overlook contextual cues, object interactions, and temporally distributed evidence needed for reasoning. Motivated by recent progress in learnable temporal selection for long-video question answering, we revisit VAU temporal sampling as a downstream-aligned evidence selection problem. We introduce the semantic-conditioned Temporal Sampling Q-Former that learns to select temporal visual evidence through the VAU generation objective. Since generic VAU prompts provide weak video-specific guidance, we condition the sampler on CLIP-embedded object tags automatically extracted from the input video. These tags are used only for temporal evidence selection and are not appended to the LLM generation prompt, separating sampler conditioning from prompt augmentation. The proposed sampler operates in visual-token space, computes soft temporal selection weights from frame-level representations, and merges duplicated selections before response generation. Experiments on HIVAU-70K show that our model achieves the best performance among the compared fine-tuned models, while ablations demonstrate that learnable temporal sampling improves over fixed anomaly-focused sampling and that CLIP-embedded object-tag conditioning further improves over generic-prompt conditioning. Our results suggest that temporal sampling in VAU should be aligned with explanation-oriented evidence utility rather than anomaly saliency alone. --- ### Memory-Efficient Integer-Only Training of Deep Neural Networks Authors: Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Manuel Roveri Published: 2026-10-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.16298v1 Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision benchmarks retain floating-point in at least one stage, typically the weight update or optimizer state. We present a training algorithm that scales to modern deep neural networks, in which every tensor (weights, gradients, and activations) is stored as INT8, and every operation (forward pass, backward pass, weight update, optimizer update) is performed in integer arithmetic. Specifically, tensors are stored as signed integer mantissas paired with explicit power-of-two exponents, on which integer-only operations are performed using five custom composable building blocks (products, sums, divide-by-constant, nonlinear functions, and weight updates). This allows complete implementation of trainable integer layers, including convolutions, batch and layer normalization, softmax, and GELU. A per-group velocity mechanism with independent exponent tracking preserves gradient precision across neurons and channels with diverse magnitudes. As every tensor fits in INT8, training memory is roughly 4x smaller than the FP32 baseline. We validate our training algorithm on CNNs (ResNet-18/34/50/101, MobileNetV2) and Vision Transformers (ViT-Ti / B), demonstrating for the first time that training neural networks with INT8 tensors and integer arithmetic can achieve competitive accuracy on CIFAR-10, CIFAR-100 and ImageNet at a reduced memory budget. --- ### SLDBench v2: Active Scaling Law Discovery Authors: Lingbei Meng, Rui Huang, Zhirong Shen, Jinxin Liu, Lingxiao Jing, Haorui Chen, Yaosong Du, Haowei Lin Published: 2026-10-12 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.16297v1 Scaling laws predict large-model performance from small experiments, but finding a reliable law itself requires costly experiments. SLDBench tests whether language-model agents can discover scaling laws when all experimental results are given upfront. We introduce SLDBench v2 with two extensions. First, we expand the corpus from 8 to 127 scenarios spanning language-model pretraining, downstream performance, and vision-language transfer, and select 30 challenging scenarios on which a reference power-law fit reaches $R^2 \le 0.8$; they represent at least $1.09 \times 10^{23}$ FLOPs of source-reported training compute. Second, we introduce active scaling law discovery: an agent chooses which experiments to run, pays each one's recorded cost (e.g., training FLOPs), and revises its law as outcomes arrive, and is scored on the same hidden extrapolation targets as in the passive setting. Across 8 frontier agent systems, median $R^2$ drops from 0.72-0.75 (passive) to 0.24-0.57 (active), and prediction error rises 1.5-4.7 times, depending on the system. Agents favor cheap experiments, spending 8-44% of the full-pool cost on average; low-cost acquisition can yield strong predictions, but cheap purchases also leave experimental conditions needed for extrapolation unobserved. Experimental planning thus remains a key open challenge for agents that assist model development in the prevailing AI-for-AI study. --- ### ClothAtlas: Joint Garment Identification and State Estimation under Self-Occlusion Authors: Jens Lundell, Alberta Longhini, Lei Shu, Hemal Arora, Evan Robert, Carlota Parés-Morlans, Marcel Büsching, Mårten Björkman, Jeannette Bohg Published: 2026-10-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.16293v1 Garment manipulation requires inferring both garment identity and complete configuration from partial, self-occluded observations. This creates a chicken-and-egg problem: completing a partial observation requires a garment-specific deformation prior, while identifying the garment requires a configuration that explains the observation. We introduce ClothAtlas, which jointly identifies garments and estimates their complete configurations from partial point clouds and a library of canonical meshes. A shared graph-conditioned flow-matching model samples configurations for each candidate mesh and ranks candidates by observation fit. The model accommodates different mesh shapes, vertex counts, and connectivities, allowing new garments to be added from canonical meshes alone without retraining. On held-out DexGarmentLab garments, ClothAtlas ranks the correct mesh first among 221 candidates for all 22 test garments from a single flat observation. From a single self-occluded observation, it identifies 15/22 garments, compared with 8/22 for a deterministic graph estimator. Persistent vertex identities support grasp-target localization on real garments, reducing mean error from 15.4 to 6.4 cm overall and from 17.0 to 8.3 cm on occluded targets compared with dense descriptor matching. Project page: https://clothatlas.github.io/ --- ### 3D Gaussian Splatting for Fine-grained Urban Scene Reconstruction via Semantic-guided Density Control and Loss Design Authors: Yueling Liao, San Jiang, Xing Zhang, Zhongwen Hu Published: 2026-10-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.16292v1 3D Gaussian Splatting (3DGS) has been becoming a promising 3D reconstruction technique because of its advantage of high-fidelity rendering effect with high efficiency. However, it still suffers from coarse density control and semantically blind loss functions when reconstructing the fine-grained structures in complex urban scenes. Thus, this study proposes SG-GS, a semantic-guided 3DGS method for fine-grained structure reconstruction. It takes the semantic segmentation deduced by the Segment Anything Model (SAM) as a constraint and systematically integrates it into both Gaussian density control and loss function design. On the one hand, a semantic-constrained adaptive density control mechanism is constructed, which dynamically allocates gradient thresholds to different semantic regions of the scene and introduces an additional boundary-enhanced densification strategy, so that new Gaussians are directed to structurally critical regions. On the other hand, a multi-feature guided loss function is designed, and fine-grained supervision signals are gradually introduced through a phased progressive training strategy, alleviating the artifacts caused by the lack of semantic constraints in the basic loss. Experiments on three datasets show that the proposed method consistently improves reconstruction accuracy. Compared with the original 3DGS, the PSNR increases by approximately 2.7% to 5.2%, while artifacts on linear structures and boundary blurring are effectively mitigated. The method can serve the fine-grained 3D reconstruction of urban scenes. ---