# Research Papers — 2026-10 · bundle page 33 of 156 > Full-text markdown of papers #1601–1650 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/33 [← Previous bundle](https://aipod.dev/papers/archive/2026-10/page/32.md) [Next bundle →](https://aipod.dev/papers/archive/2026-10/page/34.md) ### MFVSR: A Multi-Style and Fine-Grained Benchmark for Video Subtitle Removal Authors: Xiyan Huang, Qingdong He, Peng Tang, Bo Yin, Chaoyi Wang, Xiaobin Hu Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18461v1 Video subtitle removal (VSR) is an important video restoration task, yet existing evaluation remains limited by low-resolution datasets, fragmented test sets, and generic video-inpainting protocols that fail to adequately capture localized restoration errors, unintended modifications, temporal instability, and incomplete outputs. In this paper, we introduce MFVSR, a large-scale multi-style benchmark for fine-grained and reliability-aware video subtitle removal evaluation. MFVSR distinguishes itself through three key features: (1) Large-scale and diverse data, comprising 3,000 paired videos from Real-HQ, Real-LQ, and AI-Generated sources, with an auxiliary set of 953 in-the-wild real videos for real-world coverage analysis; (2) Controlled subtitle diversity, spanning 16 languages and four factors covering spatial layout, temporal behavior, visual style, and language mode; (3) Fine-grained evaluation, introducing an information-conditioned, spatially decoupled protocol that separates blind from mask-guided removal and measures Restoration Fidelity, Preservation Fidelity, Temporal Fidelity, coverage, and failures. Experiments on six representative methods reveal substantial discrepancies between local restoration, outside-region preservation, temporal consistency, and full-set reliability that are obscured by conventional full-frame metrics. MFVSR therefore provides a more comprehensive and diagnostic foundation for evaluating and advancing video subtitle removal methods. --- ### Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints Authors: Haoxuan Gao, Qin-Wen Luo, Xiang Chen, Yu Tian, Zequn Sun, Xiaofeng Cao, Jiangchao Yao, Sheng-Jun Huang Published: 2026-10-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.18459v1 External tools can extend the capabilities of small language models (SLMs), enabling their deployment in resource constrained environments. However, their limited capabilities make it difficult for SLMs to discover effective tool use behaviors through reinforcement learning alone, while direct teacher supervision suffers from teacher student behavioral distribution mismatch and may propagate erroneous preferences. To address these challenges, we propose Selective Teacher guided Policy Optimization (SeTPO), which coordinates student exploration with selective teacher guidance and persistent demonstration supervision. Specifically, SeTPO incorporates reverse KL derived token level teacher feedback into policy advantages on low reward trajectories, while auxiliary forward KL supervision preserves teacher demonstrated behaviors throughout training. Under an idealized bidirectional KL objective, we theoretically establish that the optimal policy achieves expected reward no lower than the teacher's while retaining a guaranteed fraction of the teacher's probability mass. Extensive experiments on BFCL v4 and API Bank demonstrate that SeTPO achieves superior overall performance over supervised fine tuning, reinforcement learning, and distillation baselines across all three student scales. --- ### $\mathrm{S}^3$-PnP: Plug-and-Play Denoising for Scientific Imaging with Self-Supervised Score Priors Authors: Yukun Cui, Jiangshe Zhang, Shuang Xu, Lilun Deng, Haowen Bai, Tao Feng, Haotong Qin, Konrad Schindler, Zixiang Zhao Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18458v1 Modern image restoration methods increasingly rely on large-scale supervised training, yet clean targets are often prohibitively difficult to obtain in scientific imaging modalities such as hyperspectral imaging (HSI) and magnetic resonance imaging (MRI). Plug-and-play ADMM (PnP-ADMM) with pretrained diffusion priors offers a promising alternative, but the learned prior distribution can mismatch both the target scientific image distribution and the distribution of ADMM denoiser inputs induced by dual feedback. To mitigate these mismatches, we propose $\mathrm{S}^3$-PnP, a self-supervised plug-and-play restoration framework that learns a score prior directly from observation-derived ADMM intermediate states, without clean training targets or externally pretrained weights. Specifically, the learned score corrects the input to the analytical prior update, combining observation-driven corrections with analytical regularization. We further analyze the convergence and reconstruction error of the corrected ADMM algorithm assuming an ideal score and quadratic data fidelity. Experiments on reference-guided HSI restoration, single-image HSI denoising, and MRI denoising demonstrate consistent improvements over competing methods. --- ### Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents Authors: Kristoffer Hempel, Nils Loose, Lorenzo Cavallaro, Thomas Eisenbarth Published: 2026-10-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2610.18457v1 Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an agent to act with the user's authority on any resource it can access. The reach that gives an agent its utility is equally available to an attacker who can steer it. Anything an agent ingests can carry an injected instruction, and since the model does not reliably distinguish instructions from data, indirect prompt injection should be mitigated by mediating the effects the agent produces. Such mediation faces a structural difficulty. Legitimate work and the first step of an attack often look alike when an individual action is observed, and what separates them lies later in the trace, so a monitor limited to allow and deny is forced to decide before the evidence accumulates. We present Kairos, a reference monitor at the isolation boundary of an unmodified, opaque agent, where a tool call, a shell command, and a script the agent writes all cross the boundary as the same file and network operations, so that confinement holds regardless of the agent's behavior. A declarative policy that states which sources are trusted decides most effects deterministically and defers the rest, which are held while the agent continues speculatively. A decision oracle with bounded authority, such as a language model or a human, releases or refuses each deferred effect on the trace. Across three benchmarks and three agent models, Kairos outperforms existing defenses in the trade-off between attack success and utility. In particular, on AgentDojo, it reduces attack success from 47.0\% to 2.7\% while its benign utility stays at the level of the undefended agent. --- ### Learning Perturbation-Specific Representations through Conditional Energy Prior for Cellular Response Prediction Authors: Yuchen Yan, Yatao Bian Published: 2026-10-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2610.18456v1 AI-based cellular perturbation prediction is essential to accelerate drug discovery and therapeutic identification. However, perturbation-specific signals are generally obscured by cellular complexity, making it difficult for existing methods to correctly capture perturbation effects. To address this problem, we propose PerturbEnergy, which introduces a conditional energy-based prior over perturbation representations. It assigns lower energy (higher probability) to representations compatible with the given perturbation and higher energy to others, thereby explicitly tilting the latent space toward perturbation-preferred regions. Besides, PerturbEnergy can be integrated into autoencoder architectures as we find its Evidence Lower Bound (ELBO) is equivalent to the ELBO of the complete autoencoder. We further prove that optimizing PerturbEnergy increases the lower bound on the conditional mutual information between representation and perturbation. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our PerturbEnergy: it improves perturbation recognition especially in latent space with improvement of up to 83.2\%; It also achieves state-of-the-art performance for predicting top-50/100/200 differentially expressed gene(DEG) response and remaining competitive on highly variable gene(HVG) prediction. The code is provided: https://github.com/BlueWhaleLab/PerturbEnergy --- ### EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs Authors: Zixuan Xing, Lancheng Gao, Shengyan Li, Huiyu Duan, Zhaolin Cai, Guangtao Zhai, Xiongkuo Min Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18455v1 Rapid advances in artificial intelligence-generated content (AIGC) have significantly promoted using text-to-image (T2I) models to generate images with specific affective intentions. However, the emotional effects conveyed by generated images frequently deviate from target expectations, and it remains unclear whether multimodal large language models (MLLMs) can reliably interpret the emotion of AI-generated visual content. Existing affective benchmarks are predominantly built on natural images, while affective studies of generated images have largely focused on emotions expressed in portraits, lacking a unified benchmark for studying the emotions expressed and evoked by generated images. We therefore introduce EmoGenie, a benchmark of emotion for AI-generated images that evaluates capabilities in T2I generation and MLLM understanding across expressed and evoked emotions. It comprises 6,400 images generated by eight T2I models using 800 emotion-targeted prompts, annotated with question-answer (QA) pairs, termed EmoGenie-QA, and continuous human ratings, termed EmoGenie-Assess. EmoGenie-QA contains 90,000 closed-set questions in single-image and image-pair settings, as well as 1,057 open-ended questions for emotion description. EmoGenie-Assess benchmarks continuous affective and aesthetic prediction using 13,175 mean opinion scores (MOSs) aggregated from human ratings in terms of valence, arousal, dominance, and aesthetic quality. We further develop EmoProbe, which combines emotion question answering with response-aligned, dimension-specific regression heads for continuous score prediction. Experimental results show that EmoProbe achieves superior results on emotion-related QA tasks, while its affective and aesthetic predictions correlate better with human ratings, demonstrating its state-of-the-art capabilities of unified coarse-to-fine affective understanding for AI-generated images. --- ### FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving Authors: Yunfei Feng, Jingkai He, Shiqi Liu, Cheng Zhang, Dong Du, Erhu Feng Published: 2026-10-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2610.18451v1 Large-scale expert parallelism (EP) has become the standard deployment configuration for Mixture-of-Experts (MoE) models in production. Meanwhile, the highly dynamic nature of LLM workloads requires providers to continuously adjust serving capacity to match fluctuating demand. Scaling MoE serving cannot be efficiently achieved by simply adding or removing serving instances; instead, it often requires resizing the EP group within an existing instance, which we refer to as intra-instance scaling.Existing inference engines primarily rely on instance-level scaling, which destroys and reconstructs entire serving instances, incurring substantial scaling overhead. We present FastEEP (Fast Elastic Expert Parallel), a fast intra-instance scaling system for MoE serving based on the principle of Partial Reuse. FastEEP reuses existing runtime state across worker execution, GPU memory, and communication by separating reusable execution structures from the resources activated by the current EP configuration. This separation enables coordinated resource reclamation and reconfiguration while preserving costly-to-reconstruct state, allowing fast EP scaling without full instance teardown and reconstruction. Our evaluation shows that FastEEP achieves 4.5x--11.7x faster scaling than the existing vLLM-based approach across different models, enabling efficient, fine-grained scaling of MoE serving. --- ### Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery Authors: Yibo Wen, Han Liu Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.18449v1 AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while others that support active experimentation largely rely on simulation. We introduce Autonomous Science Bench, an initial release comprising six budgeted design-build-test-learn campaigns grounded in published experiments across biology, chemistry, and materials science. Agents select batches of designs, receive measurements from a lab service, and use the results to guide subsequent experiments before delivering a predictive model. Success requires passing two calibrated gates: a discovery gate, which evaluates the designs the agent measured, and a learning gate, which evaluates its model's ranking of held-out designs. In a pilot evaluation of eight agent-model configurations and 144 trials, the best configuration succeeds in 67% of trials, while the hardest campaign is solved in only three of 24 attempts. The two gates reveal different weaknesses: some agents build accurate rankings but find too few promising designs, while others find promising designs but fail to predict which unseen designs will perform well. These differences are obscured by overall success rates alone. We release version 0.1 of the campaigns, lab runtime, and public leaderboard at https://yibow.me/autonomous-science-bench. --- ### Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence Authors: Thinker Team, Peng Gao, Jichao Jiao, Chen Liao, Daqin Luo, Yiming Ma, Baiyu Pan, Hailin Shi, Jiyuan Wang, Xiangming Xu, Xiongwei Zhao Published: 2026-10-13 Categories: cs.AI, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2610.18447v2 World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model. In this work, we present Thinker-WM, a unified multimodal world model that jointly models and generates RGB, metric depth, and robot action through a shared intermediate Unified Dynamics Transformer with modality-specific encoders and decoders. The model performs multimodal unification at the representation level: appearance, geometry, and action are transformed into a common dynamic representation and jointly evolved by shared parameters, while their distinct output structures are preserved. The same parameterization supports multiple functions, including joint video-action generation, world prediction, policy inference, action-conditioned generation, video-to-action generation, and inverse dynamics. To examine whether the shared representation captures action-related information, we introduce a lightweight motion probe that shows the frozen visual representation contains recoverable motion information. Thinker-WM is trained on a heterogeneous corpus comprising approximately 20K hours of egocentric video, 10K hours of real-robot data, and 1K hours of simulation data, including approximately 4K hours of real-robot data with aligned depth supervision. Extensive experiments demonstrate strong performance across embodied world-model evaluations. Thinker-WM ranks first on EWMBench, WorldOlympiad and WorldArena, while controlled studies further demonstrate the benefits of action conditioning, geometric interaction, and multi-function training within the shared representation. --- ### CoTL: Compact Token Learning for 3D Scene Representation Authors: Han Liang, Sibo Wu, Anpei Chen, Rüdiger Westermann Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18446v2 We present CoTL, a framework that learns a compact set of tokens that preserves scene geometry and appearance from unposed multi-view images. Our encoder compresses the input images into small per-view sets of latent tokens that aggregate information across views to form a view-consistent scene representation. Each additional view expands the representation with only a small, resolution-independent set of tokens, allowing its capacity to grow with the available observations. To force this compact bottleneck to retain sufficient scene information, a query-based Gaussian decoder uses scene-independent queries to attend to the learned tokens and recover an explicit, renderable set of 3D Gaussian primitives. Novel-view rendering supervision trains the compact representation end to end through the reconstructed Gaussian scene. Experiments on RealEstate10K and ACID show that the resulting compact, unstructured token set supports competitive novel-view synthesis and can serve as the latent space of a generative model for 3D Gaussian scene generation. Together, these results show that 3D Gaussian reconstruction is an effective objective for compact scene representation learning and the learned token space provides a basis for broader downstream tasks in 3D vision. --- ### The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion Authors: Xiaoyu Li, Zheng Gao, Chiwun Yang, Zhizhou Sha Published: 2026-10-13 Categories: cs.AI, cs.CY, math.PR arXiv: https://arxiv.org/abs/2610.18445v1 Automating AI research creates a positive feedback loop between software capability and research effort. We study a stochastic realisation of this loop in which independent, positive, multiplicative improvements arrive at a rate proportional to a power of current capability. Within this model, randomness leaves the deterministic explosion threshold unchanged but replaces the blow-up date by an explicit distribution. For equal-sized improvements the explosion time is a geometrically weighted sum of independent exponentials; its $q$-series representation gives its transforms, moments and tail behaviour, including a two-term small-time asymptotic. For Lomax-distributed improvement sizes the explosion time is exactly Gamma distributed. Self-similarity implies that, with parameters known, the relative uncertainty about the remaining time does not vanish as explosion approaches. We formulate a fixed-sample test between constant and geometrically increasing idea-arrival rates. If the baseline rate and the alternative log-rate increment $\ell$ are known, the minimum sample size at error level $α$ is asymptotic to $(12z_α^2)^{1/3}\ell^{-2/3}$, where $z_α$ is the upper-$α$ standard normal quantile. Uncertainty about the growth exponent near its critical value produces a $1/t$ tail with an explicit constant, and hence an infinite conditional mean waiting time, although explosion is certain given a positive exponent. Separate extensions show that a fixed deployment delay prevents explosion in the specified delayed-feedback models, that power-law diversion of effort shifts the growth threshold, and that in a deterministic oversight race a fixed allocation share does not change the asymptotic regime, except at a critical equality of exponents. Numerical illustrations, which are not empirical forecasts, show how timing and detectability depend on the granularity of improvements. --- ### Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit Authors: Hoang Pham, Duc Anh Vu, Duy Tung Doan, Cong-Duy T Nguyen, Anh Tuan Luu Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18442v1 In search engines and assistants, long-form RAG answers can mislead readers with claims their sources do not support. Faithfulness rewards, the share of supported sentences, train models toward fewer such claims. We show that these rewards are hacked by copying. A sentence copied from the passages is supported almost by construction, so trained models learn to copy rather than ground what they write. Common defenses only move the hack: a KL or copy penalty leaves copying in place or trades it for shorter, emptier answers and refusals. GRPO, the standard RL algorithm, makes it worse by giving every sentence its answer's advantage, reinforcing copied and grounded sentences alike. We propose Authored-Sentence Credit (ASC) , which fixes both by moving GRPO's reward and advantage from the answer to the sentence level. The reward credits only sentences that are authored rather than copied, say more than the question, and are supported by the passages. The advantage compares each sentence with every sentence sampled for the question, so one that earns no credit ranks last and is never reinforced. Across four models and two in-domain, three held-out corpora, only ASC lowers the error rate of authored sentences and writes more supported ones in every setting, by 38% and 46% at the median under held-out evaluators, giving readers more grounded information. It takes none of these shortcuts, and two LLM judges comparing whole answers prefer no baseline to the base model but rate ASC's answers on par with it. We conclude that a faithfulness reward should credit what a model writes, not what it copies. --- ### Estimating Surprisal from the Speech Signal Authors: Zachary Hopton, Samuel Kiegeland, Francesco Ignazio Re, Patrick Haller, Matthew B. Winn, Ryan Cotterell, Eleanor Chodroff Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18439v1 Although language is predominantly spoken, empirical tests of surprisal theory rely almost entirely on written text. In practice, surprisal is estimated using language models (LMs) trained on text and applied to transcriptions, creating a text bottleneck that limits evaluation of the theory in the spoken modality. We remove this bottleneck by estimating surprisal directly from the speech signal using a speech LM. This raises a key question: should surprisal be defined over realization-specific acoustic inputs or over abstract linguistic units? Since a single unit can have many distinct acoustic realizations, each assigned a different probability by the model, defining surprisal over abstract units is difficult. To address this, we introduce an importance sampling estimator that approximates the probability of an abstract unit by marginalizing over realizations generated by a text-to-speech model. Using pupillometry data from a listening study, we evaluate surprisal theory in this text-free setting at multiple levels of granularity. Obtaining surprisal from several speech LMs, we consistently find that surprisal estimated via importance sampling better predicts pupil dilation than realization-specific surprisal for words. We also find that surprisal values for sub-lexical units are predictive of pupil dilation. While we find that surprisal can be estimated without recourse to text, and that marginalizing over distinct realizations of words is more predictive of lexical processing effort, surprisal as a whole is not a strong predictor of change in pupil size, regardless of its source. --- ### STAMP as a topology-aware molecular language for fragment-level learning and editing Authors: Yuxuan Ren, Jiatong Li, Ziqiao Meng, Yatao Bian Published: 2026-10-13 Categories: q-bio.QM, cs.AI arXiv: https://arxiv.org/abs/2610.18438v1 Molecular fragments provide chemically meaningful units, but existing molecular languages rarely make their locations and connections explicit for editing. Here we introduce STAMP (Sequential Tree Attachment-based Motif-Preserving representation), a topology-aware molecular language that connects fragment-level representation learning with precise structural editing. STAMP separately encodes motif identity, attachment sites and tree topology, making fragments reusable across contexts and subtrees directly accessible. Learned representations capture motif similarity and recurring transformations, and lower activity-cliff prediction error on 23 of 30 targets versus a matched SMILES encoder. Compatible subtree operations support scaffold-preserving optimization, ranking first among six methods on 15 of 23 benchmark objectives. A deterministic compiler enables frozen language models to act on indexed fragments, improving molecular editing, optimization, transformation transfer and change identification by 9 to 56 percentage points over plain SMILES. Together, these results establish an executable molecular language in which learned chemical units remain directly operable during design. --- ### How Well Do LLMs Perform in Peer Review? Evidence from Finance and Accounting Authors: Hai Lu, Yichen Luo, Luping Yu Published: 2026-10-13 Categories: q-fin.GN, cs.AI arXiv: https://arxiv.org/abs/2610.18435v1 Referees increasingly use large language models (LLMs), while finance and accounting journals disagree about whether to allow it. We ask which part of a referee's job the models can do. GPT-4o, whose training data end before the 2024 conference season, referees the papers presented at the 2024 AFA and NBER finance meetings, and we compare its verdicts with publication in the top-three finance journals over the next two years. Papers the model scores one standard deviation higher are 44\% more likely to be published, net of author reputation. The result is not driven by look-ahead bias, as the model does not recall the outcomes. The information comes from its judgements of correctness and exposition. Its judgements of originality and significance carry none, and a referee guide that stresses importance does not help. The split between correctness and contribution holds for accounting papers and for a newer model, GPT-5. LLMs can check whether research is right, but not whether it matters. The technical check can go to the model, while the judgement of contribution stays with people. --- ### Principled Design of Expected Improvement for Continuous Simulation Optimization Authors: Songhao Wang, Jianglin Xia, Haowei Wang, Szu Hui Ng Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.18434v2 Expected improvement based on stochastic kriging (SK) surrogate is widely used in continuous simulation optimization, but unknown heteroscedastic noise makes three basic design choices consequential: the incumbent to define improvement, replication allocation, and final recommendation. Existing methods typically either assume the noise levels are known or choose these components separately through heuristic rules or empirical calibration. We instead derive a high-probability upper bound on the simple regret and systematically choose the three components within general rule classes to tighten this bound. We first establish a finite-sample confidence bound for the SK predictor as a foundation for the three design choices. Within general posterior-quantile rule classes, tightening the regret certificate selects a lower-quantile incumbent and an upper-quantile recommendation among sampled designs. The opposing quantiles reflect the different roles of exploratory experiments and the final implemented decision. Under mild conditions satisfied by common kernels, minimizing a tractable kernel-specific bound yields a logarithmic replication order. Based on these design choices, the resulting simple regret matches the existing results under known homoscedastic noise up to logarithmic factors. To our knowledge, this is the first simple-regret guarantee of this form for a continuous-domain EI-type simulation optimization method that learns unknown heteroscedastic variances through replications. --- ### FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation Authors: Xi Chen, Chunyi Zhou, Rui Zeng, Xiaogang Xu, Zhe Liu, Shouling Ji Published: 2026-10-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2610.18430v1 Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce targeted behaviors while maintaining normal performance on benign inputs. In this work, we make a key observation specific to federated LLM fine-tuning: malicious clients tend to exhibit strong consistency in their model updates, whereas benign clients produce more diverse and dispersed updates. This structural difference is not well captured by existing defense methods, which typically rely on direct anomaly detection in high-dimensional parameter space and therefore struggle in the presence of entangled LLM updates. Motivated by this observation, we propose FedGraph, a graph-based aggregation framework that explicitly models relationships among client updates. By representing clients as nodes in a dynamically constructed graph and extracting structural features that characterize their relative positions and interactions, FedGraph derives compact client representations that effectively separate malicious and benign behaviors. These representations are then used to identify and suppress malicious contributions during aggregation. Extensive experiments demonstrate that FedGraph significantly improves backdoor defense. It consistently reduces attack success rates to below 10% while achieving high detection accuracy (95.5% on average) and a low false positive rate (2.33%), substantially outperforming existing federated learning defenses. --- ### Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments Authors: Hoang Pham, Cong-Duy Nguyen, Dong Le, Ponhvoan Srey, Anh Tuan Luu Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18427v1 Persistent textual memory lets language-model agents reuse lessons from past tasks to improve on future multi-step tasks without retraining. Systems such as ACE and Dynamic Cheatsheet keep it as a playbook: lessons the agent writes after each task and reads in its prompt. A key challenge is to decide which lessons improve later tasks. Current systems leave the decision to the agent itself, which makes performance unstable: the same procedure can write a playbook that helps or one that falls up to 69.6 points below no playbook. These findings motivate valuing lessons by their measured effect on task success rather than by the agent's judgment. We propose Randomized Block Curation (RBC), which measures this effect with a randomized experiment on practice tasks. It groups related lessons into blocks large enough to move success measurably and, on each practice task, includes or leaves out every block at random. Random inclusion makes tasks with and without a block comparable, so the gap in their success estimates the block's effect. RBC keeps the blocks that help and, since the same procedure can write a helpful or a harmful playbook, grows several and serves whichever curated, whole or no playbook scores best on fresh practice episodes. Across two memory systems, three models and three benchmarks, RBC raises average success to 66.9, against 55.5 with the whole playbook, 54.1 with no playbook and 53.8 when the agent's own judgment picks the lessons to keep. --- ### Receiver Decides Agent-to-Agent Negotiations Authors: Fardeen Sadab, Alif Hasnain, Afsana Shehrin, Md. Azam Hossain, Abu Raihan Mostofa Kamal Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18424v1 When one language-model agent asks another for money, which of the two decides how much changes hands? We ran a round-robin tournament of 1,049 negotiations among fifteen agents. In each game a requester tries to raise money from a holder that has been told to keep a $100 endowment. Knowing which agent holds the money explains 47% of the variance in the amount transferred; knowing which agent asks explains 2%. Dropping the most extreme agents narrows the split to 22% against 4%. Changing the requester's appeal from one named person to a group changed what requesters wrote, but the amounts transferred under the two framings are statistically equivalent. The holders that lose least are the ones that turn down the opening request, and their turn-1 refusal rate ranks them by total losses (Spearman correlation = -0.73). Training moves this behaviour in both directions. Fine-tuning Qwen3-8B on a persuasion corpus with almost no refusals raised what it gave away as a holder from 12% to 84% of the endowment. Distilling two never-losing holders into a 4B student cut its losses from 95% to 1%. Evaluations of agents that hold resources should test them in the holder role, including after persuasion fine-tuning. --- ### Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages Authors: Ramchand Kumaresan, Madhusudhanan G, Kaushik Kezendirane Published: 2026-10-13 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2610.18420v1 We trained Agaram 2.5B, a 2.5-billion-parameter Tamil-English language model, from scratch on about 50 billion tokens (58% Tamil, the rest English, math, code and parallel text) on one node of eight H100 GPUs in about six days, with a new tokenizer that, unlike our first model's, keeps line breaks. Supervised fine-tuning on 134,428 conversations, whose replies an open-weight teacher model wrote, and three short targeted rounds turned it into a chat model that answers in Tamil script, romanized Tamil (Tanglish) and English and can call tools: on 25 tool prompts whose schemas appear in training it picks the right tool 23 times and gives exactly the expected arguments 13 times. The released model translates better than Sarvam-1, a 2B Indic base model, in all six FLORES and IN22 directions (FLORES chrF 54.3 into Tamil and 55.2 into English, against 49.2 and 44.2), and nearly doubles its base model on native-Tamil IndicIFEval (19.3% from 10.0%). It is weak on knowledge: reading-comprehension and knowledge benchmarks sit near chance, and on 50 held-out everyday questions written by one native speaker, one LLM judge rated 46% of its replies usable (22-24 of 50 over three passes; 95% interval for 23 of 50, 33-60%), with nearly every failure a wrong fact. Our two further SFT experiments changed answer format but not the knowledge measures. We also describe our first model, Agaram 1.5B, whose failures shaped the choices here; how the judge's scores varied between passes on identical replies; and, item by item, what the targeted rounds trained against and where frontier-model text entered the data. The project ran on compute credits and our own funds, about USD 13,300 across both models; the weights are released (licence to be announced after legal review), with GGUF files for llama.cpp, at https://huggingface.co/murai-labs/agaram-2.5b-instruct; code at https://github.com/Murai-Labs/Agaram2.5b --- ### Resource-Efficient 3D Shape and Orientation Estimation of Road Users using Roadside RGB Camera and 3D Radar Authors: Shiva Agrawal, Savankumar Bhanderi, Gordon Elger Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.18417v1 End-to-end deep learning pipelines for camera-radar 3D object detection are well established in driver assistance systems and autonomous vehicles; however, adapting them to roadside-mounted infrastructure presents significant challenges. On vehicles, sensor heights, pitch angles, and relative geometries remain largely uniform, allowing end-to-end models to generalize effectively. On the contrary, roadside sensor installations vary drastically in height, tilt, and field of view across locations, rendering end-to-end models prone to failure and difficult to adapt without massive location-specific datasets. Hence, instead of designing a complex end-to-end pipeline for direct 3D bounding box estimation, a low-cost, resource-efficient two-stage approach is proposed for real-time 3D shape and orientation estimation. The first stage utilizes any off-the-shelf, state-of-the-art method to extract 2D camera bounding boxes and associated 3D radar points for each road user. The proposed second stage then processes these inputs to construct 3D oriented bounding boxes where radar data determines 3D position, predefined templates define size for each road user, and a tiny neural network predicts a site-specific and optimized yaw angle. The algorithm is successfully validated at a curved road with a junction for pedestrians, bicycles, and cars, where it achieves 25 frames per second on an NVIDIA Jetson ORIN for real-time applications. --- ### Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison Authors: Pratuat Amatya, Vinay Setty, V Venktesh, Avishek Anand Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.18415v1 Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment steps such as RLHF do not focus on factuality of LLMs, hence they may generate non-factual information, which could result in unintended consequences. In response, a number of factuality alignment approaches have been proposed in the literature which claim to improve factuality of LLMs on their own benchmarks. However, these methods have not been reproduced independently and are also not comparable since each uses a different base model, training data, evaluation set, judge, and metric. In this paper, we present the first independent reproduction of five factuality alignment methods, which span on-policy RL (PPO, GRPO, and Dr.~GRPO) and offline preference optimization (DPO and KTO), and compare them on a common benchmark with common evaluation metrics. We found that none of these methods reproduces in full, and on the common benchmark none of the methods significantly outperforms the base model. On closer inspection, the rewards optimize for format, length, or brevity rather than factuality and relevance, whereas the choice between on-policy and offline training matters little. Furthermore, the evaluation metrics and benchmarks are also part of the problem since they do not measure relevance of text to the prompt. Since there is no ground truth associated with the prompts, the reliance on LLM judges and retrieval for verification also makes the evaluation fragile. We release our code, data, and checkpoints. --- ### Revisiting the Estimation of Unigram Surprisal in Computational Psycholinguistics Authors: Zachary Hopton, Francesco Ignazio Re, Samuel Kiegeland, Andreas Opedal, Eleanor Chodroff, Ryan Cotterell Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18414v1 Contextual and unigram surprisal are standard predictors of reading time in computational psycholinguistics. While contextual surprisal is typically derived from neural language models, unigram surprisal is usually obtained from independent corpus counts. Although both quantities are deterministic functionals of a single underlying distribution---capturing conditional and marginal structure respectively---this practice breaks their probabilistic link and may introduce estimation error from the mismatch. We propose three principles for estimating unigram surprisal in psycholinguistic research, including the requirement that both quantities be derived from the same language model. We operationalize this principle by introducing a Monte Carlo estimator of unigram surprisal from a language model, along with a marginalized variant that has lower variance empirically. When unigram surprisal is re-estimated under this unified framework, we find evidence that predictors change in their predictive contribution to reading time. We also confirm prior findings that frequency can be a stronger predictor of processing effort than contextual surprisal under this unified framework. --- ### Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs Authors: Mikhail Aleksandrov, Nail Bashirov, Maksim Ivanov, Andrew Tsukanov, Timofey Karyagin, Alexander Miasnikov, Gleb Molodtsov, Valentin Samokhin, Aleksandr Beznosikov Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.18412v1 Prompt-based adaptation offers several ways to specialize a frozen language model, ranging from natural-language prompt optimization to learned continuous prompts. These methods are usually compared through downstream performance, although similar outputs need not arise from similar internal computations. We study how discrete prompt optimization, prompt tuning, and prefix tuning alter the processing of dense and mixture-of-experts language models. Our analysis shows that the location of the adaptation predicts how task information is carried to the output: optimized text primarily changes response construction, input-level prompts write their influence into content representations, and layer-wise prefixes maintain direct control through attention. In MoE models, these differences further induce distinct expert-routing patterns. At the same time, common representation-level measurements respond strongly to generic context changes and do not reliably distinguish useful adaptations from matched placebos. We argue that understanding prompt adaptation requires separating representation drift from the part of that drift that is aligned with, and causally used by, the model's task computation. This perspective provides practical guidance for selecting, evaluating, and interpreting prompt adaptation methods. --- ### Graph-free Retrieval with Graph-Modified Embeddings Authors: Federica Santi, Vasilije Marković, Daniel Scott, Lazar Obradović Published: 2026-10-13 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2610.18410v1 Dense vector retrieval can miss evidence connected through intermediate entities, while direct graph retrieval requires access to the graph at query time. We compare five offline graph-based embedding transformations and strategies for using the resulting graph-modified embeddings alongside the originals, without query-time graph access. On a synthetic professional-network benchmark with complete supporting-evidence sets, direct replacement of the original embeddings reduces evidence recovery. Multi-stage strategies improve recovery by using graph-modified embeddings to guide the search while retaining the originals for semantic relevance. On questions requiring linked facts or comparisons among candidates, the strongest configuration improves recovery by up to 25.9% relative to plain vector retrieval. It also matches baseline recovery with 40% fewer returned nodes. Controls confirm that graph information contributes beyond multi-stage retrieval alone. Across the tested methods, retrieval performance depends more on how graph-modified embeddings are used than on how they are produced. --- ### Prompt-Injection Probes Learn the Conversation, Not Just the Injection Authors: Kaan Kale, Sriram Vishwanath Published: 2026-10-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2610.18408v1 Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and send suspicious ones to a slower second check, so every false alarm has a cost. But a probe learns whatever separates its training examples. The standard evaluation of injection probes can be passed without the model: conversation position and text lengths alone reach 0.91-0.98 AUROC. When each attack is compared with the same conversation without the injection, or with harmless text formatted like an injection, standard probes flag most of these harmless cases. We add such cases to the training data as matched negatives. Across six open models, in applications seen during training and at the default threshold, changing only the training data cuts false alarms on injection-free conversations from 41-80% to 4-27%, and on harmless look-alikes from 92-98% to 3-16%. With a threshold set on normal traffic, our probe still catches a median 95% of the attacks that fooled the agent (91% without our data). In new applications, false alarms stay low, but detection depends on the model and on how the threshold is set. The same data also helps a text-only filter. --- ### Multi-Stream Residual Computation in Diffusion Language Models Authors: Ekaterina Alimaskina, Suren Kazarian, Gleb Molodtsov, Aleksandr Beznosikov Published: 2026-10-13 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2610.18407v1 Diffusion language models reconstruct masked tokens in parallel, offering an alternative to autoregressive generation. Yet their Transformer backbones typically carry visible evidence and evolving masked predictions through a single residual stream. We equip masked diffusion models with multiple residual streams that persist through depth and adaptive routing between them, then investigate how they support these complementary roles. On the pretraining task, two streams reduce reconstruction perplexity by 5.71% on validation data and 5.13% on average across external corpora compared with standard residual connections. We observe that, without predefined roles, visible and masked positions learn distinct routing patterns. Causal interventions show that this distinction organizes read and write routing, while token-specific write strength remains important within each role. Guided by these findings, a model trained with role-conditioned routing recovers half the validation gain from adding a second stream. State interventions explain the benefit of the additional stream: it preserves early token representations for later reuse while evidence accumulates at masked positions. This mechanism recurs at a larger model scale, showing how persistent streams support context preservation alongside prediction refinement. --- ### Overcoming Catastrophic Forgetting: Continual Learning for Radar Waveform Classification Authors: Mohamed Rabie, Chinthana J. Panagamuwa, Konstantinos G. Kyriakopoulos Published: 2026-10-13 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2610.18404v1 Automated radar waveform recognition classifies the waveform and modulation type of a received signal. As new waveform variants appear over time, a deployed classifier must learn them without retraining from scratch. Catastrophic Forgetting occurs when learning new waveforms overwrites prior knowledge. Continual Learning (CL) methods tackle this challenge, but prior radar studies only evaluate a few methods on narrow benchmarks. Practitioners lack evidence on which method to deploy or which mechanisms are effective. This work presents the first large-scale benchmark of continual learning for radar waveform recognition. Eighteen CL methods are evaluated on a sequential ten-task problem, drawn from four public datasets spanning 54 waveforms, under task- and class-incremental (TIL, CIL) settings and single- and multi-epoch regimes. Methods that retain data from old tasks lead both TIL and CIL settings. Plain replay alone closes 77-88% of the gap between the lower and upper practical limits under TIL, but only 46-55% under CIL. The internal mechanisms of the leading methods are ablated and statistically tested to identify effective mechanisms. Each ablation is paired against its full method over n=6 training seeds, topped up to n=12 when inconclusive, and p-values are Holm-Bonferroni corrected within each method's family. Ablation results show that several mechanisms confer smaller but statistically significant gains. Combining these mechanisms improves the leading F1 score by 3.4-5.5% and 2.7-4.9% under TIL and CIL, respectively, and the combined models exceed every benchmarked method in both settings for all SNRs. These results give researchers of radar waveform classification systems a mechanism-level basis for design. --- ### Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs Authors: Peiran Yin, Hao Wu, Zihao Yang, Fengyu Zhou, Yijuan Liang, Haozhe Hu, Xudong Wang, Wei Zhang, Xiaoyu Shen Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18399v1 Visual token pruning for multimodal large language models (MLLMs) appears highly effective, with existing methods retaining over 95% of unpruned performance on common VQA benchmarks using a quarter of the visual tokens or fewer. However, our extensive evaluation of ten methods across three MLLM families and five ability groups reveals a critical gap: strong general performance often comes at the cost of severe degradation on fine-grained tasks such as OCR and visual grounding. We trace these failures to two limitations of the prevailing paradigm of retaining the highest-ranked native patches. A single importance ranking overlooks the complementary evidence required by different tasks, while sparse patch selection disrupts both image content and spatial integrity. To address these limitations, we propose Bifocal, a training-free, two-stage pruning method built on a mixed-granularity framework. It allocates separate budgets to query-focused and image-intrinsic evidence, complemented by a pooled coarse representation of the entire image. Before the LLM, Bifocal matches question words to visual regions through a soft conjunction balanced against norm-debiased image saliency, while selecting image-intrinsic evidence to maximize representational coverage. Inside the LLM, it further prunes tokens using density-adjusted text-to-image attention. With roughly a quarter of the original visual tokens, Bifocal is the only evaluated method to retain over 90% of unpruned performance in every ability group across all three models, and ranks first on average in all nine model-budget settings. The code is available at: https://github.com/EIT-NLP/Bifocal --- ### LunaTP: Enabling Efficient and Scalable Tensor Product for Equivariant MLIPs Authors: Yuanchang Zhou, Mingzhen Li, Chen Wang, Xiangyu Zhang, Guangming Tan, Weile Jia Published: 2026-10-13 Categories: cs.DC, cs.LG arXiv: https://arxiv.org/abs/2610.18393v1 Equivariant machine learning interatomic potentials (MLIPs) promise atomistic simulations with accuracy approaching that of quantum-mechanical calculations. However, the high computational cost of their core Clebsch--Gordan tensor product (CGTP) convolutions severely limits model scalability and efficiency. In this paper, we rethink the parallel execution of CGTP convolutions and introduce LunaTP. Built on node-centric execution, LunaTP exploits path-group parallelism and multi-level reuse to accelerate CGTP convolutions and higher-order derivative computation while preserving the underlying mathematical formulation. On an NVIDIA H100 GPU, LunaTP achieves kernel speedups of up to 250.0$\times$ over e3nn and 17.1$\times$ over OpenEquivariance. It also delivers end-to-end training throughput gains of up to 28.7$\times$ over e3nn and 3.11$\times$ over OpenEquivariance. Finally, LunaTP demonstrates scalability and robust performance across models, workload scales, and GPUs, delivering substantial acceleration for training and atomistic simulation with high-accuracy equivariant MLIPs. --- ### Beyond RMSE and Granger Gain: Multi-Horizon Forecast-Error Entropy for Nonlinear Predictive Coupling Authors: Andrei Velichko Published: 2026-10-13 Categories: nlin.CD, cs.LG arXiv: https://arxiv.org/abs/2610.18390v1 We investigate whether the past of an auxiliary time series provides predictive information about a target beyond that contained in the target's own history. We compare matched out-of-sample target-only and target-plus-source forecasts and introduce the forecast-error distribution entropy (FEDE) predictive-causality framework, where predictive causality is understood in the Granger sense: auxiliary history is informative when it improves prediction beyond the target's own past. FEDE quantifies how the full signed forecast-error distribution changes across prediction horizons. Controlled nonlinear benchmarks hide source-target dependence behind nonlinear transformations not supplied to the predictors. LightGBM recovers these hidden channels, whereas Ridge does not. Across four equal-power nonlinearities and four noise levels, the mean response-sensitivity statistic for FEDE remains 29.00, 27.47, 23.22, and 28.67, compared with 14.09, 10.68, 12.67, and 12.71 for mean log-RMSE gain. Directional and source controls separate the true source-to-target channel from the reverse direction and from independent periodic, quasiperiodic, chaotic, and autoregressive auxiliaries. Chronological Granger-style comparisons show strong model-form dependence: a degree-2 polynomial model is exceptionally sensitive to the matched quadratic channel but becomes weak or oppositely aligned for other nonlinearities, while basic convergent cross mapping is weak or directionally inconsistent in this stochastic, partly non-invertible setting. FEDE remains positively aligned across all 108 tested combinations of window length, history length, and maximum forecast horizon. Together, these results establish FEDE as a sensitive and robust horizon-resolved tool that extracts predictive information beyond conventional error-magnitude measures when the nonlinear interaction form is unknown. Code available in Zenodo. --- ### PRISM: Calibrating Black-Box Judges with Counterfactual Probes Authors: Kakei Yamamoto, So Kuroki Published: 2026-10-13 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2610.18389v1 Large language models are increasingly used as judges to reduce reliance on costly human evaluation, yet their scores can systematically disagree with human judgments. We ask whether responses to an explicitly imposed evaluative bias can help correct a judge's implicit scoring biases. We introduce PRISM (Probe-based Residual Inference of Scoring Misalignment), which holds the evaluated content fixed and measures score changes when attributes are emphasized or de-emphasized. A local sensitivity model motivates representing these responses as a surrogate Jacobian. Ridge regression on human labels learns a correction to the baseline score. The resulting scoring protocol is rubric-free: it uses overall scores without requesting criterion-level ratings. In the main Jev and Sol comparisons on SummEval summarization and HANNA story evaluation, PRISM and its learned-baseline variant significantly improve agreement with human rankings over uncalibrated scores while remaining competitive with rubric-based methods. A controlled SummEval comparison yields similar agreement for rubric-derived quality probes and style probes, supporting calibration without reproducing rubric criteria. The learned coefficients reveal shared and opposing correction directions across judges. --- ### ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing Authors: Yi Liu, Wentao Jiang, Shuo Ni, Zhiming Luo, Di Wang, Zengmao Wang, Jing Zhang, Bo Du Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18388v1 Multimodal large language models (MLLMs) have shown strong potential for remote sensing understanding, yet reliable reasoning remains challenging when tasks require fine-grained visual grounding and multi-step inference. Existing approaches typically rely on either costly pre-constructed reasoning trajectories or self-generated signals such as response consistency, which can reinforce shared errors and provide unreliable supervision. We introduce \textbf{Reasoning--Diagnosis Self-Evolution (ReDiS)}, a framework that separates reasoning exploration from candidate evaluation while allowing the two processes to evolve jointly. ReDiS instantiates two role-specific experts from a shared multimodal backbone: a \textbf{Reasoner} that explores diverse visual evidence--answer candidates and a \textbf{Diagnoser} that jointly evaluates the complete candidate set and provides credibility-aware feedback. As the Reasoner evolves, it exposes new candidate distributions and failure modes; the Diagnoser adapts to these changes and, in turn, reshapes the learning signal for subsequent exploration. To handle groups in which all sampled answers are incorrect and group-relative advantages vanish, we further introduce \textbf{Failure-Triggered Recovery (FTR)}, which provides minimal outcome-level correction without prescribing intermediate reasoning trajectories. Experiments on LHRS-Bench, MME-RS, and CHOICE show consistent improvements over Qwen3.5 backbones at 0.8B, 2B, and 4B scales. ReDiS improves category-averaged accuracy by 6.47 percentage points at 0.8B, while ReDiS-4B achieves the highest average performance among the compared remote sensing MLLMs. --- ### Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matching Authors: Langrui Zhou, Guang Li, Xinyu Huang, Ziteng Zhou, Zuyang Huang, Hongming Shan, Shouhua Luo, Ning Gu Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18379v1 With the rapid development of deep learning, supervised convolutional neural network methods have greatly improved the performance of low-dose computed tomography (CT) denoising. However, they require paired noisy-clean training data, which is difficult to obtain in practice. Some classic self-supervised denoising methods rely on the assumption of pixel-wise independent noise, making them ineffective for correlated noise in low-dose CT (LDCT) images. Considering the high similarity and weaker noise correlation between adjacent CT slices, several recently proposed self-supervised methods use adjacent LDCT slices for training. Nevertheless, these approaches fail to effectively account for the non-rigid misalignment between slices caused by anatomical variation, hindering them from satisfying the equal-mean condition required by the classic Noise2Noise framework. In this paper, we propose Noise2Match, a self-supervised LDCT denoising method based on adaptive inter-slice matching. Noise2Match introduces an inter-slice matching network to model the label transition process between adjacent slices, and then applies correction to the denoiser's outputs to better satisfy the equal-mean condition. We theoretically prove that, under idealized conditions, training Noise2Match using adjacent LDCT slices is equivalent to supervised training with paired noisy-clean images. We further find that Noise2Match can also effectively perform low-dose conebeam CT (CBCT) denoising, which could be attributed to its correction operation that reduces inter-slice noise correlation. To the best of our knowledge, Noise2Match is the first effective image-domain self-supervised method for low-dose CBCT. Extensive experiments demonstrate that Noise2Match outperforms existing image-domain selfsupervised methods, offering broader applicability and higher practical value. --- ### Delegating Earth science model calibration to knowledge-guided LLM agents Authors: Zhanliang Zhu, Ziwei Li, Liujun Zhu, Yuchen Liu, Junliang Jin, Jianyun Zhang Published: 2026-10-13 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2610.18378v1 Applying process-based Earth science models to new sites and questions often requires expert calibration decisions. Reliable delegation to language-model agents must preserve scientific competence and reproducibility. Here we develop a general calibration harness (GCH) for end-to-end delegation from a calibration request to assessed results. Constrained by a knowledge infrastructure (KI) and a validation convention, agents define parameter domains, observation mappings and objectives, and generate model-specific code. GCH checks the formulations against the same declarations and freezes them before numerical search and assessment, which require no further agent judgement. Agent-authored workflows executed across six model families, with assessment identifying unmet criteria. In snow-model tests, five of five knowledge-guided specifications executed on the first attempt, compared with none of five given only the model name, achieving validation Nash-Sutcliffe efficiency (NSE) of 0.81-0.94 against 0.57 for defaults. Under a common objective, independent GR4J formulations yielded scores within 0.001 NSE; re-evaluating eleven saved parameter vectors reproduced their metrics. In ten paired VIC tests with matched budgets, fixed search was non-inferior to continuing agent proposals (margin, -0.02 NSE; median difference, -0.003). This separation enables end-to-end calibration delegation with inspectable scientific choices and reproducible numerical evaluation. --- ### Beyond Task Success: A Theory of Representation Reuse Authors: Zibo Meng, Andrew C. M. Austin, Alin Achim Published: 2026-10-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2610.18375v1 A learned representation is useful beyond its source task only if later tasks can make use of what the encoder has already learned. Source-task performance, however, gives no guarantee that the representation itself will remain useful once the original head is removed. We study representation reuse with respect to a specified family of future tasks. For such a family, we define the task-relevant state as the coarsest deterministic state sufficient for all of its tasks. A larger task family can require a finer state, and losing a required distinction makes at least one future task unrecoverable on a target support containing that conflict. Exact reuse also depends on how the retained information is presented to the downstream rule. We separate this into structural accessibility, which concerns whether the required distinctions remain recoverable, and coordinate consistency, which concerns whether those distinctions can be interpreted by the same downstream rule across samples. Both failure modes appear separately in the experiments. Reuse improves as task-relevant distinctions become more accessible. Reversible sample-dependent coordinate changes can sharply reduce reuse even when the representation remains recoverable, and inverting the applicable coordinate change restores performance. The same accessibility-reuse ordering appears in prospectively specified CIFAR-100 experiments with both ResNet-18 and DenseNet-121. Finally, preserving a candidate state that contains the distinctions needed by the anticipated task family improves reuse on compatible held-out tasks, with the clearest benefit when target supervision is limited. Representation reuse is therefore relative to the tasks that follow source learning: a useful representation must retain the distinctions those tasks need and make them available in a form that a shared downstream rule can use. --- ### SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema Authors: Shuang Wu, Jiude Wei, Cewu Lu, Jianhua Sun Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18374v1 RGB-based category-level 9D pose estimation remains highly challenging because a monocular system must generalize across unseen object instances while jointly inferring 3D translation, 3D rotation, and 3D size. Unlike instance-level pose estimation, the category-level setting requires the network to learn both what is shared across objects within a category and how individual instances vary in structure. This challenge is amplified in the RGB-only setting, where pose cues, category-level commonality, and instance-specific variation are entangled in appearance without direct geometric constraints, making it difficult for existing frameworks to learn a representation that is truly aligned with the category-level estimation objective. To address this problem, we propose SchemaPose, a schema-guided framework for RGB-based category-level pose estimation. SchemaPose equips the estimation pipeline with an explicit parametric schema for modeling category-level regularities together with structured instance variation, and uses the inferred schema variables to guide pose-related prediction in an end-to-end query-based framework. The same formulation also supports template instantiation, synthetic annotation, and pose learning within a unified framework. Experiments on synthetic and real data show that SchemaPose achieves state-of-the-art performance among RGB-based methods for category-level 9D pose estimation. --- ### Hallucination-aware Faithful Reasoning in Remote Sensing Authors: Yi Liu, Jing Zhang, Xiang Feng, Xiaoyu Tian, Haonan Guo, Di Wang, Zengmao Wang, Bo Du Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18369v1 Multimodal large language models (MLLMs) have demonstrated promising capabilities for remote sensing reasoning, yet they frequently generate visually unsupported reasoning that contradicts the visual evidence. Existing post-training methods optimize primarily for final-answer correctness, providing limited supervision for identifying and correcting hallucinations that arise during the reasoning process. To address this limitation, we propose \textbf{FaithRS}, a hallucination-aware self-reflection framework for faithful reasoning in remote sensing. We first construct \textbf{SFHD-43K}, a dataset of 43K structured, fine-grained hallucination annotations, and train a detector to identify hallucination types, underlying causes, and supporting visual evidence. FaithRS then incorporates this diagnostic feedback into a Safe Detector-Guided Corrective Rollout framework, where a safety-aware gate selectively determines whether and how to revise the response. Training is driven by a composite reward that jointly optimizes answer accuracy, reasoning faithfulness, hallucination reduction, format compliance, and revision safety. Experiments with Qwen3.5 backbones (0.8B, 4B, and 9B) show consistent improvements across four remote sensing benchmarks, with gains of up to 11.64 points. --- ### Visual Sevoing from Lines Authors: Nicolas Andreff, Bernard Espiau, Radu Horaud Published: 2026-10-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2610.18363v1 In this work, we present a fundamentally new approach to visual servoing using lines. It is based on a theoretical and geometrical study of the main line representations which allowed us to define a new representation, the so-called binormalized Plucker coordinates. They are particularly well suited to visual servoing. Indeed, they allow the definition of a proper image line alignment concept. The control law which realizes such an alignment has moreover several properties: partial decoupling between rotation and translation, analytical inversion of the motion equations and global asymptotic stability conditions. This control law was validated both in simulation and experimentally in the specific case of an orthogonal trihedron. --- ### Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key Authors: Paweł Batorski, Przemysław Spurek, Paul Swoboda Published: 2026-10-13 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2610.18359v1 Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows to alter the watermarking message. This allows to, for example, exchange the embedded account ID to an arbitrary different one. The attacker mainly needs access to a few accounts for generating LLM output and model logits, but crucially not the secret key used to watermark. The attacker then rewrites the text, keeping its meaning, so that the watermarking message decoder recovers the watermarking message embedded by the attacker. We are, to our knowledge, the first to propose such an attack, which we call a targeted displacement. Theoretically, we present upper and lower bounds on the probability of our attack succeeding. This bound depends on the number of accounts the attacker has access to, the length of the message and some characteristics of the given text. Our attack can succeed whenever we can bound the ambiguity of the generated text well enough. Empirically, we test our attack technique against five watermarking methods and four LLMs. Attack success tracks our predicted bounds, allowing us to alter watermarking messages in almost all cases with high accuracy, given enough accounts. Our code can be found at https://github.com/Batorskq/PinIt. --- ### Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes Authors: Yu Wang, Rui Dai, Wei Chen, Yi Wang, Bo Dang, Kaikui Liu, Xiangxiang Chu, Yansheng Li Published: 2026-10-13 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2610.18356v1 City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic vision-language framework that instead casts grounding as active spatial search. Urbex represents a city-scale 3D scene as an interactive multi-view environment, allowing a VLM agent to query landmarks, zoom into local regions, render oblique views, and commit a grounded bounding box. We optimize this tool-use policy with reinforcement learning on CityRefer, using smooth localization rewards and lightweight shaping rewards for efficient exploration. Experiments show that Urbex achieves the best Hit@1 and IoU on CityRefer, supports candidate-free grounding without ground-truth boxes, and is substantially faster than the strongest city-scale ranking baseline. Zero-shot results on STPLS3D-Refer further indicate improved cross-scene robustness. --- ### ABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution Authors: Qiuyu Ding, Heng-Da Xu, Changda Xia, Jiajun Shen, Zihao Guan, Zhengchen Yuan, Jianfang Zhang, Di Yang, Jiayi Tian, Yuting Xu, Fei Wang, Shiao Liu et al. Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.18355v2 We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. Embodied intelligence demands the joint mastery of perception, planning, and execution, yet reconciling generality with specialization across this spectrum remains an open challenge. Within a single unified model, ABot-ER commands specialist-level depth across all three competencies, spanning spatial, scene, and temporal reasoning in perception; long-horizon action organization in planning; and point grounding and affordance in execution. The Agentic Data-Model Self-Evolution Engine continuously adapts data strategies to the model's evolving capability state. The Task-Conditioned Adaptive Training Strategy uses task tokens to activate lightweight low-rank residuals over a shared backbone, separating updates from heterogeneous output formats while retaining shared embodied knowledge. Across a systematic evaluation on twelve benchmarks covering three core competencies and five capability dimensions, ABot-ER achieves state-of-the-art overall performance across perception, planning, and execution within a unified parametric framework, demonstrating that breadth and depth can coexist in unified embodied reasoning. --- ### Choosing LLMs for Strategic Agent Interactions Authors: Arastun Mammadli, Herbert Woisetschläger, Jawad Fayaz, Shiqiang Wang Published: 2026-10-13 Categories: cs.AI, cs.IR, cs.MA arXiv: https://arxiv.org/abs/2610.18354v1 Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. However, they only evaluate strategic performance across individual fixed models. In parallel, contemporary LLM routers pick models under quality-cost trade-offs, but with no notion of a strategic structure. They do not account for an opponent that might be unknown, and that can adapt over time and shift the feedback signal. To address this, we extend the game-theoretic evaluations and define strategic selection as the meta game layered on top of the base game. In each round, a strategic selector fields an LLM from a portfolio of models to navigate a game payoff matrix that is latent and learned online. We find that the evaluation signal is game-specific, and that extracting a reliable signal requires a much higher number of seed runs $N$ compared to traditional benchmarking setups. Evaluating across 5 games and 10 LLMs, we show a model's strategic competence varies significantly depending on the game setup and the opponent faced. Building on this, we implement a suite of selector methods and find that approaches that rely on query embeddings or LLM self-reflection do not consistently capture the underlying strategic signal. A lightweight multi-armed bandit algorithm performs more reliably across games, though it still falls short of the best fixed model. Finally, we show that simple non-stationary and adversarial bandit variants fail to outperform a stationary bandit baseline, pointing to a gap in how current methods handle a shifting opponent in strategic settings. --- ### Let the Mind Conceive, Let the Hand Achieve: Following Multimodal Instructions for Long-Horizon Robotic Manipulation Authors: Youpeng Wen, Gang Wang, Tianyu Huang, Weiwei Zhang, Zhijian Huang, Wei Chen, Xieyuanli Chen, Yunhui Liu Published: 2026-10-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2610.18352v1 A robot following a multi-step instruction needs to act on the right objects in the right order, even as the scene changes. It must also maintain awareness of task progress and determine when to advance. To address these challenges, we introduce Orchestra, an agent harness that separates task planning and execution management from action generation. Orchestra decomposes a complete multimodal instruction into ordered subtasks, tracks completed steps, and updates the locations of relevant objects and destinations during execution. It maintains a shared context containing the active subtask, spatial grounding, and recent observations. An action policy uses this context to generate actions, while a separately trained progress evaluator estimates when to advance to the next subtask. To evaluate whether robots trained on atomic instructions and short trajectories can execute longer subtask sequences, we introduce a benchmark named RMBench-Compose. Orchestra achieves a mean success rate of $68.22\%$ across nine RMBench tasks, outperforming Mem-0 by $26.22$ percentage points. On RMBench-Compose, it achieves an Average Success Length (ASL) of $7.35$ subtasks, $2.46$ times that of HarnessVLA. Across four real-world multi-step tasks, it improves mean ASL by $25.0\%$ over Orchestra using the base $π_{0.5}$ policy. These results show that Orchestra helps robots carry out longer sequences of subtasks while preserving the requested subtask order and acting on the specified objects. Our code and project page are available at https://youpengwen.github.io/Orchestra. --- ### Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English Authors: Jophin John, Michael Hoffmann, Piroska Lendvai, Florent Dufour Published: 2026-10-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2610.18343v1 Post-training quantisation reduces the memory cost of large language models, but it remains unclear whether compression preserves language skills of regional varieties as reliably as their standard-language counterparts. We study this question for Bavarian, Standard German, and English using BAVGROUND, a multiple-choice benchmark, where 206 source questions are aligned across all three languages. Across 14 open-weight 7B--10B instruction models, we compare BF16 with 8-bit GPTQ and two 4-bit settings, GPTQ and AWQ. Eight-bit GPTQ remains close to BF16 and largely preserves the relative behaviour of the three languages, while 4-bit quantisation was found to be much less stable. The two 4-bit methods reduce average accuracy by about 1.4--1.5 percentage points and change 11.9--16.0% of BF16 decisions, with changes concentrated on examples where the BF16 model is already uncertain. This instability does not translate into a consistent Bavarian disadvantage. Although Bavarian, a low-resource dialect, has lower baseline accuracy than German and English, the language most affected at 4 bits varies across models and quantisation methods. Calibration further shapes these cross-language effects: the relative Bavarian--German effect changes with calibration language, while changing the calibration source has little average effect on GPTQ-4 but can affect AWQ-4 much more strongly. Free-form evaluation on five models further shows that 4-bit compression can degrade generated responses even in settings where multiple-choice accuracy changes only modestly, while 8-bit GPTQ remains comparatively stable. Overall, our results show that quantisation robustness for regional language varieties depends on the model, quantisation method, calibration data, and evaluation setting, and cannot be measured by aggregate multilingual accuracy alone. --- ### CityCode: Building Agent-Operable 3D Cities from Sparse Aerial Observations Authors: Jiahui Sun, Ran Bi, Yifei Liu, Xiaolong Zhou, Yishuo Xu, Yuanqi Li, Congcong Zhu, Lei Yang, Yanwen Guo, Zhihang Zhong, Hongjie Zhang Published: 2026-10-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2610.18342v1 Urban spatial intelligence calls for 3D cities that agents can measure, interpret, and modify across successive tasks. Maintaining such cities as persistent, code-based states requires lightweight acquisition and support for consistent state updates without repeated dense reconstruction. We therefore formulate a new setting for grounded urban world construction: generating large-scale, instance-level parameterized 3D cities from one low-altitude aerial RGB image per region and known camera parameters, while recovering metrically scaled buildings and explicit road geometry and connectivity. We introduce CityCode, an agent-operable representation that unifies metric geometry, urban topology, visual semantics, and 3D assets through persistent entity identities, with dependency-aware versioned execution for validated updates and historical restoration. We further develop Air2Code to construct this representation by combining visual structure extraction with adapted metric depth estimation. To address occlusion and incomplete coverage, recovered structure and observed appearance guide generative completion and subsequent structure-aware 3D generation for buildings and backgrounds. Experiments on CitySample-Aerial and UrbanScene3D demonstrate substantially more accurate metric structure recovery and superior visual fidelity to the target cities compared with the evaluated baselines. Across 50 task chains of 50 steps each, CityCode supports continued querying, editing, planning, and historical restoration over evolving city states. Together, CityCode and Air2Code turn sparse aerial observations into persistent, agent-operable urban worlds for long-horizon urban spatial intelligence. --- ### On the Optimality of Random Features under General Conditions: Misspecified Cases and Robust Learning Authors: Caixing Wang Published: 2026-10-13 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2610.18333v1 Random features provide a standard approach to scaling kernel methods to large datasets by approximating the kernel with a finite-dimensional feature map. Existing works of random feature methods primarily focus on well-specified models and light-tailed noise conditions, leaving a gap in understanding their performance under more general conditions, such as misspecified models and heavy-tailed noise. In this paper, we provide a comprehensive and improved analysis of kernel ridge regression with random features (KRR-RF) under general conditions. In the light-tailed noise setting, we improve upon the worst-case uniform bounds of the feature map used in the previous works and lead to the minimax optimal learning rates with $2r+γ>α_0$, where $(r,γ,α_0)$ denote the regularity of the target function, the effective dimension of the kernel, and the embedding index of the RKHS, respectively. In the heavy-tailed noise setting, we leverage a recently developed Hilbert-valued Fuk-Nagaev inequality and extend the same optimal results under finite weak moment conditions. The additional cost to achieve robustness is a mildly stronger explicit sample-size requirement than in the light-tailed case. For both settings, our results recover the conditions random features budgets (up to log factors) required in the previous works. In the most benign case when $α_0=γ$, KRR-RF are minimax optimal for all $r \in (0,1)$. To the best of our knowledge, this is the first work to establish optimal learning rates for KRR-RF under weak moment conditions in the misspecified setting. Numerical experiments and a real data analysis validate the derived learning rates and demonstrate their practical relevance in the presence of mis-specification and heavy-tailed noise. --- ### Probing the Geometry of Color Representations in Multilingual Language Models Authors: Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-Idrobo Published: 2026-10-13 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2610.18331v1 Do multilingual language models learn a universal internal geometry for color, and is it perceptually grounded or primarily linguistic? We decompose color representations into two geometric axes: (P1) alignment to perceptual color space, and (P2) cross-lingual symmetry. Analyzing layerwise embeddings across models and multilingual datasets, we find that perceptual grounding is weak: alignment to CIE-LAB peaks in intermediate layers, then collapses toward output layers. Cross-lingual symmetry degrades with depth, suggesting later layers encode language-specific structure. Functionally, we show that geometric properties predict task performance: models achieve 96.7% accuracy on color classification at layers where P1 alignment peaks, with P1 alignment (r=0.70) significantly correlating with downstream capabilities. Our results reveal a dissociation: text-only LMs learn universal color-language geometry, not universal color-perception geometry, providing diagnostics for where perceptual structure is preserved in language models. --- ### AssetForge: Asset-Augmented Task Synthesis for Business Automation Agents Authors: Xiangrui Liu, Shuo Tang, Siheng Chen Published: 2026-10-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2610.18330v1 Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state. Traditional Rubrics requires Authors to recreate application interfaces, initial records, policy evidence, and outcome checks for each task, entangling business logic with repeated infrastructure work. We introduce AssetForge, an asset-augmented task-construction pipeline that pairs a reusable construction-asset library with task-specific Rubrics. The assets provide application interfaces, world-state components, policy/evidence carriers, and native assertion definitions; the Rubric directs their instantiation for a particular business task. Executable checks and an additional model-based review validate each candidate, return targeted feedback, and support bounded repair before acceptance. On AutomationBench v1.0.6 public-600, fine-tuning Qwen3.6-35B-A3B on 6,000 AssetForge examples yields 41.17% on the official strict pass@1 metric, 4.4 times the 9.33% base score (+31.83 points). With the same backbone and GLM-5.3 supervision, AssetForge reaches 41.17% versus 30.33% for traditional Rubrics, a 10.84-point gain (35.7% relative) at the same accepted-example scale (6,000 versus 6,000 examples). Both DeepSeek- and GLM-supervised AssetForge models improve AppWorld completion over the base model on Test-Normal and Test-Challenge. These results establish the advantage of AssetForge's complete construction pipeline on AutomationBench public: the coupled asset-Rubric interface directs Authors toward business logic, while executable checks and model-based review validate their tasks. --- ### Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees Authors: Wenbin Hu, Huihao Jing, Haochen Shi, Yuxuan Liu, Changxuan Fan, Sirui Zhang, Kawai Chung, Hanyu Yang, Zhenhuan Wang, Ziyi Chen, Haoran Li, Yangqiu Song Published: 2026-10-13 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2610.18326v1 Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such models incur high inference latency and are often poorly aligned with customized policies. To address these problems, we present Jev-Guard, a unified model for safety classification and policy routing. We further construct a policy tree over which Jev-Guard performs routing, spanning diverse domains including content moderation, cybersecurity, privacy, and legal compliance. Specifically, Jev-Guard first navigates the policy tree to select the applicable audit policy given the caller's audit context, and then performs safety classification conditioned on the retrieved policies. On 7,033 evaluation cases, Jev-Guard achieves 93.72\% safety accuracy, a mean latency of 58ms, and 93.10\% hierarchical routing accuracy. The full routing-and-classification pipeline averages 240ms. Furthermore, we integrate Jev-Guard into the Hermes harness framework. Across agent trajectories, its separate permission gate cuts mean review time per task from 4.80s for an SFT-LLM judge to 1.33s, with no policy violations are observed for either guard. ---