# Research Papers — 2026-10 · bundle page 56 of 156 > Full-text markdown of papers #2751–2800 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/56 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/55.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/57.md) ### AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning Authors: Peiqi Jiang, Fan Zhang, Xin Xu, Tianhao Chen, Can Yang Published: 2026-10-11 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.15488v1 Formulaic alpha mining seeks interpretable expressions that rank assets by future returns. The task is challenging because it demands simultaneous processing of unstructured market descriptions, historical data, and quantitative evaluation of candidate factors, yet most existing methods exploit only a subset of these signals. We introduce AlphaPilot, a reinforcement-learning framework that trains multi-turn tool-using LLM agents for adaptive alpha mining. The agent conditions on market descriptions, proposes factor expressions, queries real-data evaluator feedback, and updates a retained factor pool across turns. This design jointly leverages market text, LLM financial knowledge, real data, and evaluation feedback. At inference time, AlphaPilot performs day-by-day search and pool updates to adapt to shifting market regimes. Across three independent runs in out-of-sample rolling backtests on CSI300 and CSI500, AlphaPilot achieves mean total returns of 42.93% and 54.19%, with mean Sharpe ratios of 2.46 and 2.86, respectively. It attains the highest mean total return, Sharpe, and RankIC among the evaluated methods on both universes. --- ### Security in LLM-Assisted Coding: A Systematic Literature Review Authors: Liang Yuan, Maryam Khanian Najafabadi, Mashud Rana, Varvara Vetrova Published: 2026-10-11 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2610.15482v1 Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risks in automated coding, benchmark limitations, and the role of human developers. Findings indicate that models frequently generate insecure code and faulty patches due to training data biases. Additionally, the models themselves are susceptible to direct attacks. Current evaluation methods suffer from data contamination and lack robust security metrics. Consequently, human oversight remains essential. Safer integration of automation will require more security-aware model architectures, stronger security-specific benchmarks, and more effective human-AI collaboration frameworks to mitigate these systemic risks. --- ### SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents Authors: Enhao Huang, Xinye Zhao, Yiming Li, Bingrun Yang, Nanjun Zhou, Chunshu Xia, Hongwei Yao, Zhan Qin Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15481v1 Independently authored skills can impose incompatible requirements, competing preferences, and redundant instructions when jointly loaded by an LLM agent. We propose SkillFusion, an offline compiler that reconciles these interactions into a reusable merged skill. Its central idea is to make composition decisions explicit through typed, scoped constraints linked to their source directives. A type-scope gate selects candidate interactions, while selective fallback revisits pairs potentially missed by structural pruning. A classifier identifies interaction types, and an adversarial verifier re-examines uncertain judgments. The resolver applies conditional routing or explicit priorities to hard conflicts, verified abstraction to soft conflicts, and deduplication to redundant instructions. Source-linked checks guide synthesis and compression, and metadata synthesis supports discovery of the merged skill. The resulting artifact retains associated scripts and resources and can be reused across tasks and executor models. SkillFusion achieves the highest mean Success among evaluated non-oracle methods on all three agent benchmarks and on both transfer benchmarks across three executor models. At the largest tested instruction configurations, it achieves over 2.5 times the Success of unresolved multi-skill loading, highlighting the growing value of reconciliation as composition becomes more demanding. The code will be open-sourced after the review process concludes. --- ### Semantic Saliency from Multi-Modal Large Language Model Scene Understanding Maps Authors: Ziqi Wen, Shravan Murlidaran, Jonathan Skaza, William Wang, Miguel P. Eckstein Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15467v1 Image-computable low-level image saliency has shaped perceptual psychology and computer science, but is limited by its inability to capture human high-level cognitive factors that influence attention and eye movements. Here, we propose a new fully automated method to compute semantic saliency by quantifying each object's contribution to scene comprehension without fitting any parameters to human data: the Automated Scene Understanding Map (AUTO-SUM). AUTO-SUM automatically segments and removes individual objects from a scene, uses multimodal large language models (MLLMs) to describe the original and modified scenes, and measures the semantic similarity between these descriptions using text embeddings. We show that AUTO-SUM can predict which object is most important in a human-measured scene understanding map (H-SUM) estimated using human scene descriptions. We also show that AUTO-SUM can predict the object most fixated by human observers during free viewing and scene description tasks better than a low-level saliency model (GBVS, Itti-Koch), a saliency model trained based on human meaning ratings (Meaning Map), and comparable to DeepGaze, which is trained on human fixation data. We contend that AUTO-SUM can be used as a semantic saliency model that complements lower-level saliency models. Code are available at https://github.com/starsky77/AUTO-SUM-Source-Code . --- ### MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection Authors: Hexiang Gu, Saihui Hou, Changlan Liu, Min Ren, Huijia Wu, Hongxun Gu, Zhaofeng He Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15463v1 With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex interactions among visual, textual, and contextual cues, making accurate detection challenging. Recent studies have introduced Retrieval-Augmented Generation (RAG) and external knowledge into harmful meme detection. However, existing methods mainly retrieve similar instances or auxiliary information, limiting their ability to capture reusable harmfulness knowledge and underlying reasoning mechanisms, and thus constraining both detection performance and interpretability. To address these challenges, we propose MemeLogos, a knowledge-driven retrieval-augmented reasoning framework for harmful meme detection. MemeLogos abstracts recurring harmfulness patterns and reasoning structures from diverse harmful cases into reusable knowledge units and organizes them into a dedicated star-shaped knowledge graph. By combining structured knowledge retrieval with an explicit multi-stage reasoning process inspired by cognitive mechanisms, MemeLogos leverages retrieved knowledge to guide harmfulness reasoning, improving both detection reliability and interpretability. Extensive experiments show that MemeLogos consistently outperforms existing harmful meme detection methods while generating more coherent and interpretable reasoning, demonstrating the effectiveness of structured harmfulness knowledge for multimodal content understanding. --- ### Scalable Robust MCTS with Anytime Deterministic Optimality Guarantees Authors: Tomer Massas, Vadim Indelman Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15461v1 MDP planners often rely on nominal transition models that may differ from the true dynamics. Robust MDP planning accounts for this uncertainty through a set of admissible models, but doing so with limited online computation is challenging: the search tree grows exponentially with the horizon and each robust backup requires an additional optimization. Existing online robust methods remain limited in scale and offer at most probabilistic guarantees. We introduce, to the best of our knowledge, the first deterministic anytime guarantees for robust online MDP planning. We restrict computation to the sampled search tree while deterministically bounding the contribution of unsampled trajectories. For any fixed policy, we derive lower and upper bounds on the gap between its projected and true robust values under rectangular and non-rectangular uncertainty sets. Under rectangular uncertainty, we propagate these bounds through the robust Bellman operator to bound the optimal robust value. These bounds are computable from the current sampled tree, hold at every node, tighten as the sampled support expands, and converge to the robust values as full support is recovered. We develop CAR-MCTS, a bound-guided MCTS planner that uses these deterministic bounds to guide exploration, prune provably suboptimal branches, and terminate once the optimal root action is certified. The fixed-policy bounds also yield an anytime policy-evaluation mechanism that certifies the robust value of any policy, independent of how it was obtained. Experiments verify the deterministic bounds, their tightening under support expansion, substantial branch pruning, root-action certification, and convergence to the optimal robust policy. To our knowledge, this is the first scalable robust MCTS framework with anytime deterministic guarantees for both online planning and policy evaluation, without enumerating the full state space. --- ### When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems Authors: Jinhao Zhou, Xiaoyu Zhang, Jiongchi Yu, Fahao Chen, Jun Wu Published: 2026-10-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2610.15459v1 LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protocols, remote tools, and model endpoints exposes communication to message loss, delay, and context expiration. Because agents often exchange open-ended natural language, anomalies can alter task-relevant information while leaving messages processable, allowing semantic errors to propagate through subsequent interactions. Systematic studies of faults in inter-agent communication remain limited. This paper presents a large-scale empirical study of how communication faults manifest, propagate, and affect task outcomes in LLM-MAS. We construct a cross-layer taxonomy linking lower-stack disturbances to application-visible faults and develop a fault-injection and tracing pipeline. Our evaluation covers more than 29,000 executions across 100 tasks, five domains, three workflow topologies, and three model configurations. We find that 20.7% of failures with complete detection records occur without an immediate failure signal, reaching 76.2% for partial-content faults. Flat maintains 53.0% task success under communication faults, compared with 3.3% and 3.2% for Sequential and Hierarchical, respectively. This advantage primarily arises when an alternative information path preserves the evidence required by downstream agents. We also evaluate execution-side and evidence protection mechanisms and find that they recover different failure cases. Evidence recovery depends on whether trustworthy information remains accessible through an unaffected path. These observations provide empirical insights into communication-fault propagation, workflow resilience, and protection design for LLM-MAS. --- ### Split Conformal Interval Length under Huber Contamination Authors: Xiao Zhang, Bowen Zhang, Lie He Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15458v1 Existing analyses of interval length in split conformal prediction largely focus on clean data. However, how contamination at the training and calibration stages alters interval length relative to the corresponding clean population oracle remains understudied. In this paper, we consider Huber contamination and derive a finite-sample upper bound that holds uniformly over contaminating distributions, with leading terms scaling as $L(δ_1+n_1^{-1/2}) +(n_2^{-1/2}+δ_2)/((1-δ_2)r_0)$, in addition to a clean-sample estimation term. We further establish a minimax lower bound matching the upper-bound rate up to constant factors on a regular asymmetric location submodel. For calibration contamination, we obtain an exact worst-case characterization of the population interval-length deviation. We also extend the upper-bound results to conformalized quantile regression and adaptive residual scores. Experiments on synthetic and real-world datasets provide empirical support for our theoretical findings on training and calibration contamination. --- ### PMB-NN: Physiological-Model-Based Neural Network for Glucose Forecasting in Type 1 Diabetes Authors: Yaowen Zhang, Shuhao Que, Ying Wang Published: 2026-10-11 Categories: physics.med-ph, cs.LG arXiv: https://arxiv.org/abs/2610.15456v2 Accurate, physiologically consistent glucose forecasts could help people with type 1 diabetes respond to impending excursions. We applied our physiological-model-based neural network (PMB--NN) framework to glucose forecasting. A temporal convolutional network (TCN) used 180 min of history, constrained during training by a personalized four-parameter physiological model. The main PMB--NN combined forecast and neural--physiological agreement losses; a three-term variant additionally fitted physiological predictions to measured glucose. Data comprised 6--8 weeks of continuous glucose monitoring, pump, and meal records from 25 AZT1D participants. Person-specific models used chronological 70/10/20 train/validation/test splits and 30-, 60-, and 120-min horizons. Median mean absolute errors were 16.24, 25.00, and 30.20 mg/dL with basal insulin records and 15.38, 24.21, and 31.79 mg/dL before these records became available. In the latter setting, PMB--NN had the lowest median error at 30 and 60 min; it outperformed the physiological model alone in all six settings. In input-increase tests, glucose predictions changed in the expected direction for 85\% of correction boluses and 100\% of carbohydrate rescues, versus 57\% for active insulin and 56\% for active carbohydrates. Most standalone physiological fits showed locally distinguishable parameter effects, with glucose-related coefficients more stable under resampling than insulin- or carbohydrate-related coefficients. The three-term variant improved hyperglycaemia accuracy with basal records, but did not significantly change overall MAE and reduced directional plausibility in three tests. PMB--NN combines personalized forecasting with an explicit physiological model, allowing assessment of predictive accuracy, physiological response behavior, and participant-specific coefficients. --- ### BridgeCodec: Mamba Enhanced Neural Audio Codec with Schrödinger Bridge at Low Bitrate Authors: Zijian Lin, Jing Yang, Jinghao Luo, Zhuo Wang, Fan Fan, Zhiyong Wu Published: 2026-10-11 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2610.15453v1 Neural audio codecs achieve remarkable performance but operate as closed ecosystems with rigidly co-trained encoderdecoder pairs, severely hindering interoperability. To resolve this, we propose BridgeCodec, a versatile framework that decouples these pairs by translating latent representations between mismatched, frozen endpoints. We formulate this cross-codec translation as a Schrödinger Bridge optimal transport problem, enabling robust mapping between disparate distributions without predefined noise priors. To efficiently capture longrange speech temporal dependencies, we integrate a Mambaenhanced U-Net architecture. We validate BridgeCodec on an extreme deployment scenario: mapping a lightweight 8 kHz source encoder directly to a 48 kHz target decoder at an ultralow bitrate of 1 kbps. Experimental results demonstrate that BridgeCodec achieves superior wideband reconstruction and high perceptual quality, successfully bridging heavily bottlenecked, heterogeneous codecs. --- ### EmoTrace-Bench: Diagnosing Emotional Expression in Text-to-Video Generation through Controlled Cues and Intensity Authors: Yeheng Wang, Liudan Shi, Yi Zheng, Jingke Li, Shiyuan Liu, Xin Tao, Yuanxing Zhang, Guoyu Sun Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15452v1 Text-to-video (T2V) models are increasingly used to generate videos with targeted emotional expressions, yet existing evaluation methods mainly rely on holistic video-text alignment and provide limited insight into whether failures arise from target-emotion expression, intensity control, or specific affective cues. We introduce EmoTrace-Bench, a fine-grained diagnostic benchmark that controls emotion intensity and selected affective cues in prompts and evaluates generated videos at multiple levels. EmoTrace-Bench contains 448 controlled prompts covering eight emotions, two intensity levels, and diverse cue conditions. Using 12 T2V models, we generate 5,376 videos and evaluate target-emotion presence, perceived intensity, and ten audiovisual dimensions of emotional expression with an automated evaluator calibrated and validated against human annotations on a subset of the data. Results reveal substantial differences across models and prompt designs. Prompts that explicitly describe a character's emotional reaction are followed more reliably than prompts that describe only events or scenes, whereas adding more affective cues or using more explicit cinematic audiovisual language does not consistently improve emotional generation. These results illustrate how aggregate alignment scores may overlook localized differences in target-emotion expression, intensity control, and cue realization. EmoTrace-Bench provides a traceable and interpretable framework for diagnosing emotional video generation without modifying existing generation pipelines, and we release the prompts and the automated evaluation rules. --- ### CoFlu-Brain: An fMRI Connectivity Foundation Model with Cofluctuation-Based Pretraining Authors: Ziteng Sui, Junfeng Xia, Wenhao Ye, Mo Wang, Quanying Liu Published: 2026-10-11 Categories: cs.NE arXiv: https://arxiv.org/abs/2610.15450v1 Functional magnetic resonance imaging (fMRI) commonly characterizes large-scale brain organization through functional connectivity (FC). However, an observed FC matrix is not a fixed brain graph but a statistical estimate determined by the finite BOLD frames used to compute it. Conventional FC-based approaches typically represent each scan with a single Pearson-correlation matrix, leaving frame-resolved variations in regional interactions unexploited. To address this limitation, we introduce CoFlu-Brain, which organizes framewise cofluctuation observations into multiple retained and dropped views, each summarized as an FC matrix. The model learns connectivity structure reproducible across retained views and predicts the representations of the corresponding dropped views, while adopting SIGReg from LeJEPA to prevent representation collapse. We pretrained CoFlu-Brain on 13,444 subjects from eight dataset groups and evaluated its representations via frozen-encoder linear probing on seven classification and two age-prediction tasks across seven datasets. CoFlu-Brain showed strong transfer across demographic, developmental, and clinical prediction tasks, outperforming the evaluated released models on most tasks. Random frame partitioning improved aggregate transfer, while the complete objective achieved the strongest overall performance. Code is available. --- ### Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play Authors: Yisong Xiao, Benlei Cui, Haiwen Hong, Shiji Zhao, Zonghao Ying, Yaoyuan Zhang, Longtao Huang, Aishan Liu, Hui Xue, Ting Ma, Xianglong Liu Published: 2026-10-11 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.15449v2 Despite significant advances in language understanding, Large Language Models (LLMs) can still miss meaning hidden in plain sight, failing to identify harmful intent in expressions readily understood by humans. Malicious users exploit this gap by strategically disguising harmful content to evade automated moderation, posing a serious threat to online platform safety. The vulnerability reflects a fundamental cognitive asymmetry between human readers, who integrate contextual, phonetic, and visual cues to decipher the intent behind deliberate obfuscation, and text-based LLMs, which rely primarily on token sequences and have limited exposure to evolving evasions. To bridge this asymmetry, we propose PASP (Perception-Aware Adversarial Self-Play), which combines multi-perceptual views with adversarial self-play to improve understanding of harmful intent as evasions evolve. Specifically, PASP constructs textual, phonetic, and visual views of each input, preserving its original context while exposing pronunciation and glyph cues obscured in token space. During adversarial self-play, an attacker uses defender feedback to generate intent-preserving evasions, while the defender is trained using an intent-invariance reward to understand harmful intent across changing surface forms. Extensive experiments show that PASP reduces adaptive attack success rates by up to 73.71% and 74.49% on ChineseHarm-Bench and EvoHarmBench, respectively, preserves model capabilities with minimal degradation, and effectively interprets real-world evasive expressions in e-commerce. --- ### Rethinking Supervision in Document Unwarping: A Self-consistent Flow-free Approach Authors: Shaokai Liu, Hao Feng, Wengang Zhou Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15445v1 In recent years, the proliferation of smartphones has led to an upsurge in the digitization of document files via these portable devices. However, images captured by smartphones often suffer from distortions, thereby negatively affecting digital preservation and downstream applications. To address this issue, we introduce DRNet, a novel deep network for document image rectification. Our approach is based on three key designs. Firstly, we exploit the intrinsic geometric consistency inherent in document images to guide the learning process of distortion rectification. Secondly, we design a coarse-to-fine rectification network to leverage the representations derived from the distorted document image, thereby enhancing the rectification result. Thirdly, we propose a unique perspective for supervising the learning of rectification networks, where undistorted document images are employed for supervision, which is free of warping mesh as ground truth in existing methods. Technically, both low-level pixel alignment and high-level semantic alignment jointly contribute to the learning of the mapping relationship between deformed document images and distortion-free ones. We evaluate our method on the challenging DocUNet Benchmark dataset, where it sets a series of state-of-the-art records, demonstrating the superiority of our approach compared to existing learning-based solutions. Additionally, we conduct a comprehensive series of ablation experiments to further validate the effectiveness and merits of our method. --- ### Harnessing SPAD Noise: Test-Time Gated Attention for Indoor Depth Estimation Authors: Yiquan Gao Published: 2026-10-11 Categories: cs.CV, cs.LG, cs.RO, eess.SP arXiv: https://arxiv.org/abs/2610.15431v1 Monocular depth estimation (MDE) has emerged as a cost-effective alternative to hardware-dependent 3D sensing modalities, yet predicting precise metric depth remains a persistent challenge due to intrinsic scale ambiguity, edge bleeding, and limited zero-shot generalization in unseen environments. Recent multi-modal approaches incorporate 1D/3D Single-Photon Avalanche Diode (SPAD) data to resolve these ambiguities, but they mainly treat SPAD noise as a harmful artifact required for denoising or leave the noise ignored. In this paper, we present an essentially different insight: native SPAD noise is an informative prior that implicitly encodes deterministic environmental characteristics. Driven by this paradigm shift, we introduce a novel, lightweight Test-Time Gated Attention framework by Harnessing SPAD Noise, therefore dubbed HSN. Tailored for indoor scenarios, HSN leverages the synergistic combination of 1D SPAD histograms and Gate Adapters (GAs). Through three complementary optimization phases, it generates channel-wise gated attention vectors to dynamically adjust encoder feature maps at inference time, effectively resolving ambiguous scale and boundary challenges without the heavy computational overhead or dense 3D modalities that other TTA methods suffer from. Extensive experiments on challenging real-world indoor benchmarks show that HSN achieves state-of-the-art metric depth accuracy in in-domain settings, while exhibiting even greater potential under zero-shot generalization to unfamiliar environments. Furthermore, interpretability analysis reveals that the proposed gated attention mechanism adaptively shifts attention toward deeper semantic layers under intensifying SPAD noise. Code will be made publicly available. --- ### World Modeling through Spectral Alignment Authors: Holger Molin, William Peng, Marco Bagatella, Randall Balestriero Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15429v2 How do we tell a world model what information to preserve? We study this question through the lens of spectral representation learning. We introduce SpecWM, a JEPA framework that explicitly specifies desired relationships between observations through a target similarity kernel and trains the encoder to reproduce those relationships in its embedding geometry. Different kernels provide different supervision, ranging from physical state information to a fully self-supervised temporal kernel requiring only the ordering of observations within trajectories. We characterize the global optima of the objective, establish conditions for linear recoverability and invariance to nuisance information, and connect temporal-kernel similarity to the behavioral successor measure under an idealized setting. Empirically, the choice of kernel strongly controls which physical quantities are recoverable from the representation. More importantly, temporal spectral alignment improves CEM planning success over LeWorldModel from 52% to 68% on OGBench Cube, 49% to 77% on OGBench Scene, and 29% to 51% on CALVIN. These results suggest that explicitly specifying representation geometry provides a simple way to steer what latent world models preserve for control. --- ### Pessimistic Latent Task-aware Optimization for Robust Offline Meta-Reinforcement Learning Authors: Chang-Hoon Jeong, Kisung Shin, Hanwool Sul, Byoung-Tak Zhang Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15428v1 Context-based offline meta-reinforcement learning (COMRL) has advanced almost entirely through better task representations, which separate task identity from artifacts of the behavior policy so that the latent reflects the task alone. The implicit expectation has been that a clean representation will transfer to out-of-support (parameter-extrapolation) tasks. On such a task, however, the encoder produces a latent outside the training support, where the policy has never been trained. We address this gap with Pessimistic Latent Task-aware Optimization (PLATO), which exposes the policy to off-support latents during training. PLATO assumes a mild manifold hypothesis: task latents lie on a low-dimensional manifold, and out-of-support tasks lie farther from the training centroid. It exploits this geometry by perturbing inferred latents outward from the centroid to synthesize counterfactual tasks. A learned decoder ensemble then rolls out short trajectories at each perturbed latent, and the policy is updated on the imagined transitions under a pessimism weight that down-weights steps on which the ensemble disagrees. We prove that the perturbation leaves the training support by a controllable margin and that the out-of-support generalization gap is bounded by the same perturbation reach, and we give explicit conditions, verified empirically, under which the epistemic disagreement at the perturbed latent stays bounded away from zero. On eight MuJoCo continuous-control benchmarks, PLATO consistently improves out-of-support returns over strong COMRL baselines while remaining competitive on in-distribution tasks. Our code is available at https://github.com/deephoony/plato. --- ### Riemannian Graph Tokenizer for Structural Knowledge Transfer Authors: Qimin Zhou, Haibo Liu, Yujie Wang, Li Sun, Chuan Shi Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15427v1 Foundation models are at the forefront of artificial intelligence. A tokenizer, converting the raw input into discrete representations that the model can understand, plays an important role to the success of foundation models. Unlike the text tokenizer that is well studied in large language models, graph tokenizer is still at its early stage, facing the challenges of tackling the non-Euclidean structures and capturing the structural semantics. How to design a graph tokenizer for structural knowledge transfer? To this end, we propose a Riemannian Graph Tokenizer (RGT) that bridges the structural knowledge and quantized representations to support cross-domain structural knowledge transfer. The connection is established by Riemannian geometry. Specifically, we first define the geometric vocabulary (trees, cycles and sequences), which captures fundamental structural patterns and reflects the intrinsic geometry of graph. Second, we construct a Riemannian quantizer with Riemannian Straight-Through Estimator to tokenise graph structures across multiple domains into discrete tokens. To ensure consistency and transferability across diverse geometric spaces, RGT further incorporates a geometry-aligned decoder that projects manifold-specific tokens into a unified tangent space. The theoretical analysis and geometric interpretations are provided to support the effectiveness of our proposed method. Extensive experiments across diverse datasets demonstrate that RGT significantly enhances structural knowledge transferability across graph domains. --- ### SpecFit: Not All Draft Tokens Cost the Same in Offloaded MoE Inference Authors: Hongliang Cao, Xiuyu Li, Siqi Wang, Ziming Wang, Jingmin Zhu, Hailong Yang Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15417v1 Mixture-of-experts (MoE) models activate only a few experts per token, but when their expert weights are offloaded to host memory, host-to-device (H2D) expert transfers enter the critical path of decoding. Speculative decoding verifies several draft tokens in one forward pass, yet in an MoE model each verified token activates its own experts, so a larger draft tree transfers more experts. Because of this H2D cost, speculative decoding commits several tokens per verification cycle yet is sometimes even slower than autoregressive decoding. Based on this observation, we propose SpecFit, which chooses the verified draft subtree to maximize predicted throughput rather than acceptance length. SpecFit estimates the expected number of committed tokens from draft path probabilities and predicts cycle time from the node count and the per-layer union of the experts the subtree activates; this union is a monotone submodular coverage function, so each node pays only for the experts it adds. An exact search over ancestor-closed subtrees returns the subtree with the highest predicted throughput; run after each draft level, the same search also decides when to stop drafting, and the unmodified target verifies the result. On CNN/DailyMail summarization and a GSM8K subset with Qwen3-30B-A3B, SpecFit decodes 21.6% and 7.0% faster than EAGLE-3 with the same expert cache and 1.97x and 1.72x as fast as vanilla EAGLE-3. Code is available at https://github.com/Chlience/SpecFit. --- ### Sensitivity or Criterion? Measuring and Moving When Language Models Act Authors: Sixun Dong, Yebowen Hu, Ming Yin, Yiran Chen, Fei Liu, Chen Chen Published: 2026-10-11 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15415v1 Before an agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from reluctance to act. Signal-detection theory separates sensitivity from criterion, but criteria estimated from authored binary labels depend on each benchmark's example mix. We introduce FlipAct, a diagnostic of tool use in physical states. A rule over annotated tool properties computes each answer and a graded evidence score, fixing the Yes/No boundary at zero across models. Questions form 2-by-2 quads that hold required knowledge fixed while the state flips. The slope of the fitted Yes-rate curve measures sensitivity; its crossing at one half measures criterion. Across 44 open models, sensitivity rises with size within a family, and its ranking agrees with three of four external when-to-act benchmarks. Models respond to evidence sign rather than magnitude, accepting actions that leave the state no better about as often as helpful ones. When Yes means act, most models are conservative across rephrasings; in some, this partly reflects a preference for No. Criterion is not determined by size. Activation steering shifts criterion with weights fixed; distillation from a model's own steered copy puts the shift into its weights without a significant sensitivity change. The distilled shift transfers to six external benchmarks, including two without Yes/No answers, while criterion-free AUC is preserved on the five benchmarks where it is available. Accuracy improves where models start conservative and declines or remains within error where they start permissive. Project page: https://sixundong.com/projects/flipact --- ### OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation Authors: Hebaixu Wang, Jing Zhang, Haonan Guo, Di Wang, Jiayi Ma, Bo Du Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15414v1 Multimodal remote sensing image generation emerges as a promising paradigm for recovering complete and complementary observations from heterogeneous and partially observed remote sensing data. However, existing methods predominantly depend on sensor-specific fine-tuning of natural image generation models, limiting unified multimodal generation capacity due to the absence of shared representations and robust conditioning mechanisms. To address these challenges, we propose OmniRSI, a unified multimodal remote sensing image generation model. Specifically, we develop a remote sensing-specific variational autoencoder that captures multimodal priors and promotes a locally smooth latent space for unified representation and robust reconstruction across diverse observed data. Building upon that, we fully adapt Stable Diffusion 3.5 with a ControlNet branch to support unified multimodal generation and translation conditioned on textual and visual cues. Besides, we devise a training-free cyclic latent alignment mechanism that iteratively enriches incomplete visual conditions with generated multimodal information, progressively improving guidance reliability while preserving observed measurements. We also construct RSI-MM, a large-scale dataset comprising 11.5M multi-resolution images with text annotations and partially paired data for training and evaluation. Extensive experiments verify that OmniRSI achieves superior performance in multimodal reconstruction, generation and translation. --- ### From Candidate Tokens to Final Outcomes: Decoding Relative Long-Horizon Candidate Value from Reasoning Model Representations Authors: Yixin Yang, Yue Wang, Fandong Meng, Zhifang Sui Published: 2026-10-11 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.15412v1 Large reasoning models generate reasoning trajectories token by token. At a given prefix, multiple next-token candidates may be plausible, yet shape subsequent reasoning and differ in their chances of leading to the correct answer. Whether these differences are reflected in internal representations remains unclear. To study this question, we define relative long-horizon candidate value to quantify within-prefix differences and construct the Reasoning Candidate-Token Value (RCTV) dataset, pairing mathematical reasoning prefixes with plausible next-token candidates and their empirical long-horizon candidate values. Using RCTV, we examine hidden states, multilayer perceptron outputs, and attention outputs at candidate positions with sparse linear probes. Experimental results provide evidence that relative long-horizon candidate value is linearly decodable from these representations at multiple layers. Candidate-value probes can also outperform probability- and embedding-based baselines. Furthermore, a controlled online intervention experiment shows that using the decoded signals to guide token selection during generation can improve the chances of eventual success. Our findings provide evidence that internal representations encode information about relative long-horizon candidate value, offering insights into how local candidate-level representations relate to long-horizon reasoning outcomes. --- ### CoverSynth: Coverage-Guided Generation of Retrieval Evaluation Sets Authors: Anahita Sharma, Apaar Shanker, Rishav Chakravarti, Sneha Srinivasan, Vijay Kalmath, Dylan Wilbur, Yuan Li, Sara Bolouki, Yuan Xue Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15409v1 Enterprise agents need retrieval evaluation sets that expose domain-specific failures and guide developers towards efficient deployment tradeoffs. Neither expert-human-authored sets nor current synthetic generation methods provide a methodology for achieving the necessary coverage, reliability, efficiency, and discriminability required for such decision-making. Simultaneously, the field does not have an assessment framework for determining when an evaluation set has satisfied these properties. We introduce an evaluation set assessment framework for these criteria and CoverSynth -- a generator specifically designed to satisfy these criteria without incurring the high cost of human expert labeling. Starting from an unannotated corpus, CoverSynth targets coverage across retrieval demands and system capabilities. Deterministic checks locate evidence quotes in their sources, while model-based checks assess semantic validity to guarantee reliable ground truth. Across five public enterprise-style corpora, our method provides informative variation in difficulty, revealing unseen failure modes such as an inability of agents to handle underspecified or ambiguous requests. On the RepLiQA corpus, 91\% of human-generated queries can be answered by all members on a panel of 12 retrieval systems, compared to only 12\% of CoverSynth-generated queries. Finally, in a repeated TechQA/RepLiQA study, 12 of 12 within-harness model contrasts have positive nominal 95\% intervals on generated sets, compared with 4 of 12 on human sets. CoverSynth makes coverage and evidence quality explicit construction objectives, producing corpus-grounded evaluations that reveal retrieval headroom and differences between agent configurations. --- ### State Representation Shapes Long-Horizon Agent Learning and Transfer: An Empirical Study Authors: Dong Nie, Rui Lan, Yixin Nie, Lingzi Hong Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15407v1 An end-to-end success rate alone cannot distinguish failure to learn an action from failure to apply it as task state changes. We study this distinction in deterministic tool workflows that provide the current artifact state and candidate action recipes. Using 1.7B, 8B, and 27B Qwen models, we compare supervised learning across workflow horizons and cross the state representation used for training with the one used at evaluation. Horizon-matched supervision yields high completion, but an H4-trained 1.7B model transfers poorly to longer workflows under full-state observations. In an H16 crossover, compact-trained 1.7B adapters complete 50/50 held-out tasks in compact view and 0/50 in full view for each of three paired training seeds; full-trained outcomes vary across seeds. A separate 8B adapter pair shows a similar asymmetry. The view dependence also appears in paired-choice tasks where both candidate calls are executable and the correct choice depends on table contents; here, the compact mask does not consult the target action. An explicit relevance cue improves full-view execution but does not close the gap for the tested checkpoint. In a separate 27B ScienceWorld study, compact-state training improves local accuracy under both views, indicating that the transfer pattern depends on the task and observation construction. Together, these experiments identify representation-sensitive transfer as a bottleneck in the controlled workflows, without isolating content reduction from other changes to the observation. --- ### A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning Authors: Hao Li, Wenping Yin, Fabian Deuser, Jia Jia, Ziqi Liu, Levente Juhász, Fan Zhang, Filip Biljecki Published: 2026-10-11 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2610.15403v1 Crowdsourced disaster imagery provides timely, ground-level observations when conventional disaster mapping is delayed or incomplete, yet its geographic value depends on where observations are produced, how they are interpreted, and whether they can be reliably located as actionable Geospatial Intelligence (GEOINT). Using more than a decade of PhotoMappers, a crowdsourced disaster-mapping initiative, this study examines the changing geography of disaster information and asks how emerging GeoAI models compare with human geographic interpretation. We combine longitudinal spatial analysis with cross-view geolocalization using street view imagery (SVI) and remote sensing imagery (RSI), and evaluate vision-language models (VLMs) reasoning through 30 indicators spanning geographic cues and reasoning evidence. The results reveal a geographically and temporally uneven archive shaped by changing disaster types, Community Lifelines, and operational priorities. Integrating VGI, SVI, and RSI with Sinkhorn re-ranking achieves 40.90% R@1, 61.10% R@5, and 69.45% R@10, while yearly R@1 varies markedly from 25.00% to 65.07%. Geographic reasoning is similarly uneven: Qwen3.6-27B achieves an overall agreement of 67% compared with 51% for InternVL3-8B, with both models showing greater difficulty with localized and place-specific evidence than broad spatial configurations. We argue that the value of GeoAI lies less in replacing volunteered geographic interpretation than in complementing it, scaling candidate retrieval while retaining human judgment for ambiguous and consequential cases. This provides a pathway toward more human-centered and responsible GeoAI for disaster mapping. All data and code are openly available at https://github.com/bobleegogogo/PhotoMappers-VLM. --- ### Harnessing VLM in Embodied RL: From Reward Regressor to Success Detector via Exploration-Augmented Key-Observation Gating Authors: Xin Liu, Yutong Jiang, Jian Su, Ziheng Wang, Chuang Wang, Haoran Li, Dongbin Zhao Published: 2026-10-11 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2610.15401v1 VLMs provide promising solutions to embodied reward design. Most current methods that train VLMs as reward regressors not only require extensive annotations but are also primarily designed for finetuning pretrained policies, and perform less well in the more challenging from-scratch RL setting. This issue stems from a fundamental mismatch: regressing precise rewards is misaligned with what VLMs naturally excel at. We posit that it is more aligned with VLMs' inherent multi-modal VQA capabilities for the models to function as success detectors, and propose VLM success reward via Exploration-Augmented Key-Observation Gating (VLMeg) to well harness VLM for embodied reward design. As the core of VLMeg, the proposed exploration-augmented key-observation gating first determines whether the current RL episode is judgment-worthy based on its similarity to a generated success trajectory. Then, the key observation with the lowest confusion from the judgment-worthy episode will be selected for VLM evaluation as episodic reward. This gating mechanism not only avoids redundant calls but also enables higher detection accuracy of VLM. Considering the sparsity of judgment-worthy episodes, the advanced exploration incentives based on the generated trajectory are introduced, enabling more efficient exploration toward judgment-worthy trajectories for more VLM reward triggers and thus gaining higher RL efficiency. Extensive experiments in MetaWorld demonstrate VLMeg achieves state-of-the-art from-scratch RL, outperforming advanced VLM-based baselines on 12 challenging reward-free tasks. Furthermore, VLMeg also enables effective RL without any ground-truth reward in 3 challenging real-world experiments. Code will be open after acceptance at https://github.com/Raina915/VLMeg. --- ### GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression Authors: Shengkun Tang, Cong Zeng, Zongfang Liu, Dan Alistarh, Zhiqiang Shen Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15398v1 Large language models (LLMs) demonstrate strong generalization across a broad range of reasoning and generation tasks, but their large parameter counts impose substantial memory and computation costs, hindering deployment in practical resource-constrained settings. One-shot low-rank compression is a promising solution since it reduces model size and inference cost effectively. However, existing SVD-based methods primarily target multiple-choice benchmarks and often fail to preserve performance on generation tasks. Moreover, their rank allocation strategies are typically heuristic. We propose GA-SVD, a generation-aware low-rank compression framework for LLMs. First, we introduce Generation-Aware Weight Whitening (GAWW), which leverages gradients from on-policy knowledge distillation to construct whitening transformations aligned with generative behavior. Second, we develop an evolutionary global rank allocation method that searches for effective layer-wise rank allocation under a given global compression ratio. Across extensive experiments on Mistral-7B, Qwen3 series, and Llama-3.3 models, evaluated on both multiple-choice and generative benchmarks, GA-SVD consistently outperforms existing SVD-based baselines and achieves state-of-the-art (SoTA) results. We further demonstrate scalability by applying our method to models with up to 70B parameters. --- ### WUSPruner: Second-Moment-Optimal Transforms for Structured Pruning Authors: Shengkun Tang, Dan Alistarh, Zhiqiang Shen Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15394v1 Structured pruning is typically formulated as identifying which model dimensions to remove, often within the model's original representation. However, the effect of coordinate deletion fundamentally depends on the basis in which pruning is performed. This raises a more fundamental question: how should the basis be chosen specifically for coordinate deletion? We introduce WUSPruner, a transform-based framework for structured pruning of large language models. We formulate basis selection as a local linear reconstruction problem that directly minimizes the reconstruction loss induced by pruning. Inspired by the second-moment transformation in WUSH, we consider a WUS transform constructed jointly from activation and weight statistics. We show that under positive-definite second moments, WUS transform minimizes the local reconstruction loss over all invertible changes of basis. In the resulting basis, the activation and weight second moments are simultaneously diagonalized and balanced, causing the deletion error to decompose into independent spectral contributions and yielding a principled criterion for coordinate selection. Guided by this result, we develop a scalable pruning method based on blockwise WUS transformations and compact input projections. Experiments on Llama and Qwen models from 8B to 72B parameters show consistent improvements over structured pruning baselines across language modeling, knowledge, commonsense reasoning, mathematics, and code generation benchmarks, while also delivering practical reductions in inference latency and memory usage. --- ### DC-Flow: Target-Conditioned Cyclic Peptide Design via Delayed-Coupling Flow Matching Authors: Yitian Wang, Minjie Cheng, Yaning Cui, Maohua Yang, Dongdong Wang, Hongteng Xu Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15391v1 Target-conditioned cyclic peptide design requires coordinating interfacial side chains with macrocyclic closure. Existing end-to-end generators concurrently update geometric and chemical variables from noise, assigning residues to disordered coordinates. Meanwhile, predictor-assisted workflows often get stuck in local traps because they lack feedback in the propose-and-filter stage and ignore 3D structural proposals during sequence search. To overcome the drawbacks of these two paradigms, we propose DC-FLOW, a staged generative framework built around Delayed-Coupling Flow Matching. In principle, DC-FLOW postpones sequence and side-chain activation until a target-conditioned backbone takes shape, resolving structural ambiguity before chemical assignment. Then, it feeds delayed activations back into the backbone, achieving co-evolution of backbone geometry and emerging residue identities by coupling their flows. This mechanism enables more reliable macrocyclic closure and favorable interface packing. For predictor-assisted workflows, DC-FLOW supplies 3D proposals with in-trajectory guidance, enabling cascaded test-time scaling to prune redundant backbones and terminate unpromising refinement early. Extensive experiments show that DC-FLOW improves cyclization fidelity, diversity, and interface energetics, substantially increasing the yield of confident cyclic peptide binders under a fixed final-candidate budget. Our code is available at https://github.com/mianqiu00/DCFlow. --- ### From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents Authors: Binhong Wang, Haidong Kang, Yanfeng Zhang, Hong-Ning Dai, Guo Yu, Shangce Gao Published: 2026-10-11 Categories: cs.CR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2610.15390v1 Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied systems, where acoustic inputs can propagate from perception into persistent state and consequential execution. This setting extends security analysis beyond model behavior to the system conditions that determine how acoustic inputs can influence agent behavior and external actions. Existing surveys examine acoustic security, LLM-based agents, and edge deployment in isolation, leaving their security interactions in deployed Audio LLM-based agents insufficiently characterized. This survey introduces an Acoustic Sensing-to-Action (S2A) system model that traces these security implications along the path from acoustic sensing to external execution, while accounting for edge-cloud runtime and lifecycle transformation. We use the model to synthesize attacks, defenses, and evaluation methods across the acoustic, agent, and edge-system literature. The synthesis shows that security gaps can emerge within components and at the transitions between stages, where protections developed for one stage do not necessarily provide end-to-end assurance in the deployed system. These findings motivate security evaluation that follows acoustic influence from sensing to action across persistent state, system boundaries, and changing deployment conditions in real-world agents. --- ### VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding Authors: Weixin Xu, Yifan Liu, Yi Wang, Mingfei Rong, Zhenyu Yang, Zhisheng Zhong, Shengsheng Qian, Changsheng Xu Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15389v1 Video understanding agents rely on a harness to acquire evidence, use tools, and reason, but improving it requires substantial effort. Recent self evolution methods seek to optimize harnesses through execution feedback to reduce human intervention. However, existing methods often rely on annotated video questions and answers or focus on updating model parameters, leaving harness evolution from unlabeled videos underexplored. VideoEvoHarness jointly evolves a Questioner and a Solver harness from unlabeled videos with frozen model parameters. The Questioner constructs questions and computes reference answers directly from video memory records. Question quality assessments and Solver execution trajectories guide question generation policy revisions. The Solver supports evolving skills, strategies, hyperparameters, and tools using execution feedback. Executable strategies define workflows in code, reducing repeated interpretation of natural language instructions. Each round, candidate harnesses are compared on identical validation questions, with validated improvements retained for later use. Experiments on benchmarks and a dedicated benchmark question set, using videos disjoint from evolution videos, show higher overall accuracy than initially and transfer gains across backbones. Overall accuracy on this set also improves progressively across rounds. This supports our foundational framework for harness evolution from unlabeled videos, opening a promising direction for self evolving video agents. Code is available at https://github.com/Wei-Xin-Xu/VideoEvoHarness. --- ### Approximation in Contrastive Representation Learning Authors: Yuanfan Li, Zihan Zhang, Yiming Ying, Ding-Xuan Zhou Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15388v1 Contrastive representation learning (CRL) is a fundamental paradigm for learning transferable representations. Recent work identifies its population target as the pointwise mutual information (PMI) $\log\frac{p(x,y)}{p_X(x)p_Y(y)}$ between two modalities $X,Y$, where $p$ is the joint density function and $p_X,p_Y$ are the marginals. However, it remains unclear why standard inner-product scores $f(x)^\top g(y)$ can effectively approximate a generally nonseparable population target PMI. In this paper, we address this question from the aspect of approximation for CRL. By linking PMI to a compact operator, we show that $D$-dimensional inner-product models perform rank-$D$ spectral approximation, with error controlled by the spectral tail. We then study neural network realizations: in general settings, we show that deep neural network scoring functions are universally consistent, and the approximation error rates depend on the smoothness of the PMI function; under structured low-rank data models we obtain improved rates attained by moderate-width encoders. Finally, we establish a fast calibration rate from contrastive excess risk to downstream retrieval error under a density-ratio Tsybakov noise condition. --- ### E8 Lattice Key Quantization for Low-Bit KV-Cache Compression Authors: Sasho Nedelkoski, Alexander Acker, Soeren Becker, Dominik Scheinert, Odej Kao Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15384v1 Compressing the key-value (KV) cache is essential for serving long-context large language models (LLMs) under memory constraints. While current scalar quantization methods achieve significant compression, they typically face a quality-fidelity trade-off, either suffering from performance instability at 2-bit precision or necessitating 3-bit keys to maintain model quality. In this work, we demonstrate that a uniform low-bit k2v2 configuration (2-bit keys and 2-bit values) can preserve near-baseline quality by using vector quantization (VQ) based on the $E_8$ lattice for KV keys. We show that structured VQ exploits correlations across adjacent dimensions to achieve signal-to-quantization-noise ratios (SQNR) higher than those of independent scalar quantization at the same key payload rate. To ensure practical utility, we adapt a table-based asymmetric scoring algorithm that avoids explicit codebook dequantization during attention computation and preserves decode-throughput parity with scalar baselines. Across five LLM families, our $E_8$ k2v2 approach yields \textasciitilde$6\times$ KV compression, roughly 20\% smaller than scalar k3v2 (3-bit keys and 2-bit values), while retaining near-baseline long-context perplexity. In our full-suite perplexity evaluation, $E_8$ improves over scalar k3v2 in 80\% of model--dataset--context settings. These results indicate that $E_8$ lattice VQ improves quality per byte while keeping throughput at parity, suggesting that structured key quantization is a useful primitive for KV-compression stacks. Overall, our work provides a low-overhead primitive for expanding the quality-memory frontier in long-context LLM inference. --- ### Analyzing the Dynamics of WSBM-based Echo State Networks using InputDSA Authors: Huy Mai, Robert Clarke Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15380v1 Bridging the structural gap between biological brains and artificial neural networks presents a pathway to altered computational dynamics. This paper introduces a Reservoir Computing framework that replaces random networks with biologically realistic modularity by applying the Weighted Stochastic Block Model (WSBM) to Echo State Networks (ESNs). This topological parameterization constructs reservoirs reflecting latent functional sub-circuits. Furthermore, the integration of Input Dynamical Similarity Analysis (InputDSA) provides a mechanism to isolate and compare how structural priors modulate intrinsic recurrent dynamics versus external inputs. By evaluating these architectures, we establish that structural diversity does not necessarily predicts behavioral diversity across the selected network subset. Furthermore, our demixed analysis confirms Anna Karenina principle of dynamics, demonstrating that environmental constraints enforce dynamical convergence in successful agents, while failing networks degenerate into idiosyncratic trajectories. --- ### LiveAnon: Improving Privacy and Utility in Streaming Speaker Anonymization with Codec Language Models Authors: Yejin Kim, Kyungsu Kim, Seungu Han, Kyogu Lee Published: 2026-10-11 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2610.15379v1 Speaker anonymization (SA) aims to conceal speaker identity while preserving linguistic content and emotion, but existing streaming systems often lose emotion information through discrete content bottlenecks or require emotion-specific modeling. We present LiveAnon, a voice-conversion-based streaming SA system that directly conditions an autoregressive codec language model on hidden features from a pretrained streaming ASR encoder, preserving emotion without emotion-specific supervision. To reduce codec-generation latency, we introduce capped RVQ decoding, which preserves dependencies among coarse codebooks while predicting the remaining codebooks in parallel. Under VPC24, LiveAnon improves intelligibility and emotion preservation over fixed-target Stream-Voice-Anon (SVA), a strong prior streaming SA system, matches emotion-prompted SVA in emotion preservation, and achieves the strongest semi-informed privacy among streaming systems. Under VPC26, it ranks second across all metrics among the evaluated anonymization systems, demonstrating a strong privacy-utility balance. --- ### In-Place Indic Tokenizer Expansion and Continual Pretraining of Nemotron-3-Nano-30B-A3B Authors: Avinash Benki, Prasanjith Pasunuti, Sutanshu Saksena Raj, Parijat Chatterjee, Nayanjit Sarkar, Daksh Maan Published: 2026-10-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.15373v1 We adapted Nemotron-3-Nano-30B-A3B for eight Indian languages without changing its backbone architecture. We expanded the vocabulary in place from 131,072 to 163,072 entries using continued byte-pair encoding and AdaptMix rebalancing, reducing tokens per word by 38.6%. We initialized new input and output rows by averaging their original constituent rows, then trained them on 90% Indic and 10% English text before updating the backbone. Continual pretraining then progressed through broad training, high-quality annealing, and long-context training over approximately 1.27 trillion tokens. The annealed checkpoint gained 12.9 points on the Indic MILU benchmark but lost 3.4 on English MMLU. We also report practical negative results. Direct token addition underperformed continued byte-pair encoding. AdamW weight decay changed rows intended to stay fixed. Perplexity on an Indic-heavy holdout did not select the learning rate that best preserved English performance. --- ### Fewer Bits, More Tries: Recovering Capability Under Memory Constraints Authors: Tomer Galanti, Josh Susskind, Eran Malach Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15372v1 Large language models are generally more capable than smaller ones, but their memory requirements can make local deployment difficult. We ask whether part of this capability gap can instead be recovered by running a smaller or more compressed model multiple times and selecting among its outputs using public or model-generated tests. Single-user local inference can leave hardware underutilized, allowing parallel candidate generation to trade additional test-time computation for accuracy at modest latency cost. Across four code-generation benchmarks, verified retry recovers substantial accuracy lost to model size or compression. A 7B Qwen model with eight parallel attempts essentially matches a 32B model on MBPP+ and exceeds it on the other three benchmarks, while using about $4\times$ less model memory, running up to $6\times$ faster, and using less energy, as measured on Nvidia GPU. We observe similar tradeoff across model sizes, compression levels and hardware choices, although exact benefit depends on the hardware profile and problem setting. These results show that model capacity can be traded for verified test-time computation when correct solutions remain reachable within a modest retry budget. --- ### A Sovereign, Indic-First, Reasoning Model Authors: Sutanshu Saksena Raj, Prasanjith Pasunuti, Parijat Chatterjee, Daksh Maan, Purusharth Malik, Nayanjit Sarkar, Avinash Benki Published: 2026-10-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.15371v1 Gnani-Evon-v3.3-30B-A3B is a long-context hybrid Mamba-Transformer mixture-of-experts model for reasoning, instruction following, and tool use in English and eight Indian languages. Starting from NVIDIA's Nemotron-3-Nano-30B-A3B checkpoint, it retains the 52-layer backbone and changes the vocabulary, training data, and post-training objectives. An in-place expansion from 131,072 to 163,072 tokens reduces mean Indian-language fertility by 38.6%. The new embedding rows are initialized from their upstream decompositions and warmed before the backbone is updated. Continual pretraining then adds broad English-Indic data, high-quality annealing, and direct training at a 131,072-token sequence length. The central result appears after post-training. Reinforcement learning across four verifiable task environments improves mathematics, graduate-level science, and instruction following, but degrades Indic extractive question answering because the rewards do not require an answer in the requested language. The share of Indic extraction items answered in English rises from 8.7% to 91.7%. Accuracy conditional on answering in the target script roughly doubles, which is consistent with preserved reading ability but is measured on a self-selected subset. Two unreleased studies test repairs. A scoped Indic reward restores the language convention. A 26B-A4B generative judge outperforms a 235B-parameter model on RM-Bench, and distillation restores 81% of the capabilities displaced by optimizing against it. Relative to the architecture-identical starting checkpoint, the released model gains 5.2 points on an Indic aggregate while giving up 1.7 points of English retention. The unreleased Indic-aware branch trades further, gaining 14.6 Indic points at a cost of 5.4 in English. A planned FP8 release reduces the artifact to 32GB with near-zero mean change across 32 paired benchmarks. --- ### ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs Authors: Yi Ge, Kangrui Ruan, Jifan Chen, Manish Prajapat, Christian Bock, Xiaoyang Wang, Rein Houthooft, Aritra Sengupta, Varun Kumar Published: 2026-10-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.15368v1 Rapid advances in large language models have made software engineering agents capable of tackling complex coding tasks. Within a containerized environment, a coding agent receives tool responses or execution results, and determines its later actions by those earlier results. However, most existing coding agents never look ahead: their policies do not anticipate the consequences of actions, and the terminal reward barely attributes a failure to certain earlier steps, so an ill-judged edit can corrupt the repository state irreversibly before any signal arrives. Recent code world models aim to address these challenges, but they are either trained and then frozen before reinforcement learning (RL), or reduced to an auxiliary next-token loss on the environment's outputs. We present ANTE (Anticipate, Then Execute), an agentic RL framework that verifies the policy's pre-action predictions by real execution and turns them into per-step credit for its actions and trust-or-abstain decisions. With an internal belief stated before each action, Belief-Anchored Policy Optimization (BAPO) turns the settled predictions into per-step advantages by anchoring credit on the policy's own forecasts. To turn the trained forecasts into better actions at inference, thereby facilitating effective test-time scaling, ANTE-TTO (test-time optimization) selects among candidate actions without an external scorer. ANTE raises Qwen3-32B from 25.0% to 57.2% pass@1 on SWE-bench Verified, 6.2% above a matched GRPO baseline trained without the belief state; its world model's accuracy climbs from 44% to 69% during RL, and the learned foresight capability transfers across harnesses and out-of-distribution domains. In summary, we aim to build a code world model that knows what has happened, what holds now, and what the next action will achieve. --- ### TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation Authors: Ankur Garg, Xuemin Yu, Hassan Sajjad, Samira Ebrahimi Kahou Published: 2026-10-11 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.15365v1 Large language models (LLMs) can produce harmful content while generating a response. A useful safeguard should not only detect this risk during generation but also intervene while leaving safe responses largely unchanged and provide an auditable record of the internal patterns supporting its decisions. We propose TRACE (Temporal Risk Assessment and Concept Editing), a framework that tracks harmful-response risk during generation, selectively edits token activations, and leaves an auditable trace of its detection and steering decisions. TRACE learns a codebook of recurring activation patterns, with each codebook vector representing a latent concept. At inference time, it assigns each token activation to the nearest codebook vector to obtain the corresponding concept. A gated recurrent unit (GRU) processes the activations and their assigned concept features to predict completed-response harmfulness and a monotone cumulative streaming risk. During steering, activations assigned to harmful concepts are steered along directions defined by nearby benign targets. An external LLM labels the learned concepts post hoc, making detection sequences and harmful-to-benign edit records interpretable. Experiments across three generators and the WildGuard and S-Eval benchmarks show that TRACE improves streaming F1 over Kelp in five of six comparisons while remaining competitive on completed-response detection. TRACE's selective steering reduces Harmbench attack success with little change in refusal on originally safe responses. The post-hoc audit reveals recurring semantic structure in the learned concepts and distinct traces associated with harmful detection, safe generation, and activation edits. --- ### Adversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification Authors: Rui Zhang, Xinle Cao, Huazhen Yu, Jian Liu, Youwen Zhu Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15359v1 Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified $\ell_2$ defenses today face a costly trade-off: randomized smoothing (RS) requires hundreds of noisy queries per input, while Lipschitz networks (LN) constrain the architecture and sacrifice clean accuracy. We take a detection-oriented approach instead: rather than certifying that predictions are invariant inside an $\ell_2$ ball, we certify that adversarial inputs within an $\ell_2$ ball are \emph{detected} --- a guarantee aligned with security-critical deployments where missing an attack is costlier than flagging a clean input. To realize this, we prove a Lipschitz-margin reduction from certified $\ell_2$ robustness to certified detection, which reduces the problem to handling a single Lipschitz constant $L$. We introduce two detector families: $\mathbb{D}_{Adv}$, which estimates $L$ from a single defender-side perturbed pair, and $\mathbb{D}_{lc}$, which augments that pair with a local margin centroid to keep the estimate above what the certificate requires. Both deploy on any pretrained classifier without retraining. With a valid global bound, the detector is fully certified at that radius; with a local estimate $L'$, certification is sample-wise and applies only when our certified condition holds. Across MNIST, CIFAR-10, and ImageNet-1k on four backbones (LeNet-5, VGG16, ResNet-50, ViT-B/16), our detectors match or outperform five baselines (CTT, SortNet, CRM, ContraNet, A$^2$D). For CIFAR-10 with 1-Lipschitz SortNet, our reduction delivers $100\%$ certified detection at the lowest FPR among compared certified detectors; on the standard CIFAR-10 VGG16, our detectors reject all evaluated in-budget adversarial examples, with 62-82\% both rejected and formally certified. --- ### UniForge3D: Joint 3D Reconstruction and Generation in a Shared Anchor-Guided Space Authors: Wenjue Chen, Wenyue Chen, Heliang Zheng, Rongfei Jia, Yuan Liu, Meng Li Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15357v1 Generating complete 3D assets from sparse, unposed images requires preserving observed geometry while completing unseen regions. Joint reconstruction and generation offers a way to address both goals: reconstruction recovers the geometry observed in the input images, while generation contributes learned shape priors. However, combining camera-relative reconstruction with canonical-space generation introduces a coordinate mismatch that makes direct geometric interaction more difficult. Moreover, conditioning each 3D location on all views without accounting for their relevance may mix useful geometric evidence with unrelated image content, hindering local detail recovery. We present UniForge3D, which jointly models reconstruction and generation in a shared anchor-guided space, resolving their coordinate mismatch. This space follows the anchor view's azimuth while keeping the object upright. The two branches exchange features bidirectionally to predict per-view point maps and a complete sparse voxel structure. We further condition point-map prediction on the generated structure to establish pixel-to-voxel correspondences and select the most informative input view for each voxel. Features from the selected views then guide detailed shape generation, helping preserve observed geometric details. Our method achieves state-of-the-art appearance and geometry results on Toys4K and GSO, generating complete 3D assets with improved fidelity. Project webpage: https://xishuxishu.github.io/uniforge3d-project/ --- ### JSIR: An Audio-Aligned, Multi-Task Dataset of Jazz Standard Recordings Authors: Sihun Lee, Dasaem Jeong Published: 2026-10-11 Categories: cs.SD, cs.DL, cs.LG, cs.MM, eess.AS arXiv: https://arxiv.org/abs/2610.15356v1 Beat tracking, chord estimation, and structure analysis are staple tasks of music information retrieval. Their datasets are drawn largely from Western popular music, and jazz remains a repertoire on which state-of-the-art systems underperform. We present JSIR, the Jazz Standards dataset for Information Retrieval. Its 267 recordings of 44 jazz standards span 25.6 hours, 3.7 times the audio of JAAH, the closest existing resource. For each recording, we provide annotations for beat and downbeat positions, chords, and sections, all produced by a jazz musician and revised in several passes. In baseline experiments, models trained with JSIR also improve on other jazz datasets: the downbeat F-measure of a state-of-the-art beat tracker rises from 87.7% to 89.2%, and the seventh-chord accuracy of a pop-trained chord estimator on JAAH from 34% to 41%. We publicly release the annotations, the annotation tool used to create them, and a web application that displays them in sync with the audio. --- ### Video-Based Sexual Harassment Detection Using Fine-Tuned Video Transformers Authors: Jubayer- Al- Mahmud, Md Shamimul Islam, Md Nur Hossain Published: 2026-10-11 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.15354v1 Sexual harassment represents a pervasive societal challenge, with a substantial proportion of incidents remaining unreported due to insufficient evidence and delayed intervention mechanisms. Smart surveillance systems capable of detecting such incidents in real-time could assist law enforcement and serve as a deterrent. However, video-based harassment detection poses significant challenges, including variations in clothing, illumina- tion, partial occlusions, low resolution, and diverse camera view- points. Despite its social importance, this problem has received limited research attention, primarily due to the scarcity of large- scale annotated video datasets. To address this gap, we extend the Sexual Harassment Video (SHV) dataset to 600 short video clips sourced from YouTube and annotated into harassment and non-harassment categories using consistent labeling guidelines. We fine-tune three state-of-the-art video transformer models, VideoMAE, ViViT, and TimeSformer, pretrained on Kinetics- 400, for binary harassment classification. Experimental results show that all three models achieve competitive classification performance, with TimeSformer attaining the highest test accu- racy of 92.27%, outperforming VideoMAE 91.71% and ViViT 91.16% on the extended SHV test set. Our analysis reveals that performance is notably influenced by dataset size, video quality, frame sampling strategy, and model architecture. This work presents a comprehensive evaluation of modern video transformers for this sensitive real-world task. --- ### Siam-ALS: An Explainable Siamese Deep Learning Framework for Early ALS Detection Using EEG and Eye-Tracking Signals Authors: Abdur Rahman, A. A. M. Muzahid, Istiak Ahmed, Dipto Biswas, Hua Han, Yujin Zhang, Ferdous Sohel Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15351v1 Amyotrophic lateral sclerosis (ALS) diagnosis remains challenging due to heterogeneous symptoms and reliance on clinical assessment, underscoring the need for objective, data-driven approaches that leverage patient-generated physiological signals. We propose Siam-ALS, an explainable Siamese deep learning framework that jointly models synchronized electroencephalography (EEG) and eye-tracking (ET) signals. EEG captures ALS-related changes in brain activity, while ET provides information about oculomotor control, allowing the model to learn complementary patterns associated with ALS. The framework employs two modality-specific encoders: a convolutional EEG encoder that captures spatiotemporal neural patterns and an MLP-based ET encoder that models oculomotor dynamics. These modality-specific features are processed through weight-sharing Siamese branches and fused into a compact 64-dimensional joint embedding. A lightweight classifier is used to predict ALS, while pairwise metric learning helps the model learn more effective patterns from the small, diverse ALS datasets. Performance was evaluated on the public EEGET-ALS dataset using strict subject-level cross-validation, where Siam-ALS achieved an accuracy of 0.988 and an AUROC of 0.998, demonstrating strong performance compared with classical machine learning, DL, and non-Siamese fusion approaches. Cross-dataset evaluation on the independent BigP3BCI dataset achieved an AUROC of approximately 0.98, supporting the generalization capability of Siam-ALS across different BCI paradigms. To enhance interpretability, six XAI methods were evaluated in the learned embedding space, with SHAP achieving the highest, though statistically comparable, fidelity in identifying important EEG and ET patterns that contribute to ALS predictions. Overall, Siam-ALS provides an accurate, generalizable, and explainable framework for multimodal ALS detection. --- ### Gugak-VocalSet: A Multi-Genre Studio-Quality Dataset of Korean Traditional Singing with Sigimsae Annotations Authors: Danbinaerin Han, Wonil Kim, Seah Hong, Dongjoo Moon, Jaeok Lee, Jongpil Lee, Chaewon Kim, Juhan Nam Published: 2026-10-11 Categories: cs.SD, cs.AI, cs.DB, cs.DL arXiv: https://arxiv.org/abs/2610.15350v1 We present Gugak-VocalSet, the first publicly available audio dataset for Korean traditional singing with dense annotations of sigimsae, a structured pitch contour system of vocal expressions. Gugak-VocalSet contains 24.5 hours of unaccompanied solo vocal recordings across 305 tracks of representative repertoire curated by the National Gugak Center, performed by 20 professional singers in a controlled studio environment with fixed key and tempo. In addition to genre, lyrics, and mood/timbre tags, the dataset provides a unified sigimsae ontology and approximately 68,000 segments (71,700 instances including multi-label) of audio-grounded sigimsae annotations; the ontology adopts a functional-position-based hierarchy designed for consistent application across genres, and 14 expert annotators specializing in Korean traditional music performed segment-level labeling accordingly. Baseline experiments on sigimsae classification and event detection show that domain-informed F0 representations remain competitive with, and on classification surpass, frozen probing of a general-purpose music foundation model, while pitch and spectral cues play complementary roles in event-level detection. Companion page: https://www.danbinaerin.com/Gugak-VocalSet/ --- ### CodeWalk: Generating Coding Benchmarks by Walking a Problem Graph Authors: Jiaxin Fang, Runyuan He, Arnav Gupta, Sahil Kumawat, Huanzhi Mao, Alvin Cheung Published: 2026-10-11 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.15345v1 High-quality coding problems are expensive to collect. Benchmarks such as SWE-bench rely on substantial human curation, while synthetic alternatives typically rely on costly model generation and validation. In this work, we show that new coding problems can be created at almost no cost by composing existing ones. We formulate problem generation as code composition: verified atomic problems are combined into level-$N$ tasks, and a task is kept only if every atomic problem remains unsolved and a joint reference solution passes the same check used at evaluation time. The entire task-construction process is programmatic and requires no language-model generation or validation. We instantiate this approach in four coding settings: multi-bug repair, proof completion, complexity analysis, and clone equivalence. The generated tasks are challenging for frontier models, which all degrade as compositional depth increases. The generated tasks are also useful as training data: rejection-sampling fine-tuning on them improves Qwen3.5-9B at every composition level. --- ### Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models Authors: Song Xia, Meiwen Ding, Chenqi Kong, Wenhan Yang, Xudong Jiang Published: 2026-10-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.15343v1 World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial threats remains largely underexplored. We study whether a single physical adversarial texture can mislead the victim model across different real-world scenarios where observing viewpoints vary along uncontrolled object--camera trajectories. We identify that heterogeneous video semantics and trajectories induce poorly aligned gradients for optimizing the adversarial texture. To address that, we propose the Trajectory-aware adversarial Alignment and Refinement Attack (TARA), which incorporates trajectory-aware optimization to capture the evolving geometric variations of a printed texture under real-world scenarios. To improve cross-instance optimization compatibility, TARA incorporates trajectory-aware contrastive alignment to encourage attacked representations from diverse video--trajectory instances to approach a shared adversarial region and then performs trajectory-aware task refinement to translate the aligned representation into task-level prediction errors. For reproducible evaluation, we develop a geometry-grounded tracking pipeline that provides physically plausible adversarial regions with temporally consistent trajectories on EPIC-KITCHENS-100 and Something-Something V2. We further collect real-world print-and-recapture videos to validate attack effectiveness under physical deployment conditions. Together, the annotated benchmarks and real-world captured data form a reproducible testbed for future evaluation. Notably, our results reveal that a single printable adversarial texture can persistently disrupt world models and video understanding models under physical conditions, highlighting the fundamental security challenge. --- ### StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching Authors: Bui Van Hung, Dang Thanh Vu, Hoang-Son Vo, Mai Duc Minh Huy, Mai Tien Dung, Soo-Hyung Kim Published: 2026-10-11 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.15341v1 The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders often operate in compressed latent spaces and condition predominantly on semantic features, which provide limited low-level cues for early visual cortex. We propose StimFlow, which synthesizes fMRI directly in native voxel space using conditional flow matching with a linear path. This design aligns training and inference distributions, enabling competitive performance with a single sample and reducing reliance on averaging. To match the visual hierarchy, StimFlow combines structural DINOv2 features with semantic CLIP features, which prove complementary along the cortical processing stream. With a single sample, StimFlow achieves a per-voxel Pearson correlation of 0.371, matching baselines that average five draws. Generation in voxel space allows direct ROI analysis and concept localization without a decoder. Furthermore, it recovers over half of full-data performance from just one hour of scans, supporting efficient cross-subject adaptation. --- ### MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching Authors: Bui Van Hung, Hoang-Son Vo, Mai Duc Minh Huy, Dang Thanh Vu, Soo-Hyung Kim Published: 2026-10-11 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.15339v1 Current fMRI encoding models frame prediction as deterministic regression, yet identical stimuli evoke a distribution of neural responses (arising from physiological noise, hemodynamic variability, and cognitive fluctuations) that a single point estimate cannot capture. This work introduces MultiFlow, a generative fMRI encoding framework based on Conditional Flow Matching (CFM) and a formulation termed Stimulus-Informed Source Flow Matching (SISFM). SISFM generalises CFM by conditioning the source distribution on the stimulus: a learnable temporal convolution shapes the source mean with an HRF-length receptive field, while a variance head shrinks its scale, shortening the expected transport path. SISFM is instantiated with a Diffusion Transformer (DiT-X) decoder parameterising the velocity field, with sub-layer Attention Residuals, heterogeneous fusion of ten frozen vision, audio, language, and audiovisual backbones, and per-subject Yeo-network heads. On the Algonauts 2025 dataset, a single MultiFlow checkpoint recovers most of the benefit of large deterministic ensembles: it trails the 1000-model TRIBE ensemble in-distribution by 0.003 PCC (0.3163 vs. 0.3195), and the strongest in- and out-of-distribution ensembles (VIBE-20, MedARC-50) by 0.010 and 0.009 PCC, using a single trained model rather than an ensemble of 20-1000. The same checkpoint also provides stimulus-conditioned uncertainty estimates and sample-based diversity. ---