# Research Papers — 2026-08 · bundle page 8 of 240 > Full-text markdown of papers #351–400 of 11995 published in 2026-08, newest first. AI-readable mirrors of the full 11995-paper 2026-08 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-08/page/8 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/7.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/9.md) ### Multimodal Adaptive Expert Selection with Text Routing and Ordinal Prototype Optimization for Sentiment Analysis Authors: Xiaode Chen, Jiakang Yu, Hongtao Deng, Huina Qu, Xun Zhu, Yinxia Lou Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30726v1 Multimodal Sentiment Analysis (MSA) is a fundamental component of affective computing that aims to decipher complex emotional states by integrating verbal content with non-verbal cues including vocal intonation and facial micro-expressions. While recent disentanglement-based approaches have advanced the field, their potential is hindered by two methodological challenges. First, static computation graphs process all samples indiscriminately regardless of semantic complexity, which leads to suboptimal representation for diverse emotional expressions and contextual scenarios. Second, generic contrastive objectives often neglect the intrinsic ordinal hierarchy of sentiment intensities. To systematically address these limitations, we introduce Multimodal Adaptive Expert Selection with Text Routing and Ordinal prototype optimization (MAESTRO), a novel framework designed to dynamically orchestrate and refine multimodal representations. Drawing inspiration from an orchestra conductor, we design a Text-Guided Hybrid Mixture-of-Experts (MoE) mechanism. Unlike static fusion, this module utilizes linguistic context as a routing signal to dynamically activate specific audio-visual experts, thereby resolving cross-modal ambiguity through adaptive feature enhancement. Furthermore, to capture fine-grained sentiment gradations, we propose an Ordinal-aware Prototype Contrastive Learning (O-PCL). By incorporating distance-based penalties into the prototype learning objective, O-PCL enforces a structured latent space that preserves the natural order of emotion. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks demonstrate that MAESTRO achieves state-of-the-art performance, and qualitative analysis further confirms the interpretability of our dynamic routing paradigm. --- ### Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages? Authors: Donghoon Han, SungHyun Moon, Aidyn Zhakatayev, Junghun Cha, SeungJae Lee Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30725v1 Recent multilingual vision--language encoders cover hundreds of languages in a single model, yet on two state-of-the-art instances retrieval on low-resource languages (LRL; e.g. Swahili) trails high-resource ones (HRL; e.g. English) by $30^+$\,pp. We ask where in the trained encoder this gap is located. Prior modality-gap and cross-lingual subspace work suggests a linear language direction at the output crowds out alignment-relevant geometry. We falsify this: LEACE drives the linear language classifier from $>99\%$ to near chance and iterated INLP to $37$--$50\%$ while LRL retrieval moves within $\pm 1.5$\,pp and all tier means within $2.2$\,pp, tracking random controls. The linear bias is a \emph{symptom}, not the cause. Instead, the alignment-causal factor lies along the encoder's forward path: the EOS (end-of-sequence) hidden state's per-language trajectory diverges with depth. Substituting the EOS with its parallel English value three blocks before the projector lifts Swahili from $22.1\%$ to $69.1\%$ on one encoder (and reproduces on the other); three controls rule out pooled-position tautology and English specificity. A front-layer trunk that pulls each language's projection toward the parallel-content centroid corroborates the diagnosis at training time, recovering $+9.6$ / $+17.1$\,pp on LRL XM3600 retrieval (1{,}000-image subset), with consistent gains across three further benchmarks while preserving HRL performance. --- ### BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks Authors: Pradyumna Shyama Prasad, Meiri Anto, Leon Eshuijs, Julian Moncarz, Kaustubh Kislay, Juan J. Vazquez Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30724v1 LLM agents are increasingly used to run autonomous ML experiments, iterating on target metrics with little human oversight. Prior work has documented reward hacking in these environments, bringing into question the validity of produced research and the broader safety case for AI R&D. Existing benchmarks do not measure exploits that live in the data or the modeling task itself. We introduce BAITBENCH, a suite of three synthetic tabular ML tasks that each contain a shortcut that allows agents to inflate the public test score but fail on a hidden test set. Since the shortcut is optional and using it breaks no stated rule, BAITBENCH measures how often models exploit the shortcut to achieve inflated scores. Across seven frontier agents scored by our two-stage judge pipeline, 57.1% of runs exhibit reward hacking, with five of seven above 50%. Agents cheat even under a second condition where they are prompted not to -the mean cheating rate remains above 50%. We release BAITBENCH, along with the judge implementation, and an annotated dataset of transcripts containing reward hacks as a testbed for evaluating reward-hacking mitigations head-to-head. --- ### Tracing distinguishability through transformer processing with stochastic LayerNorm Authors: Kieran Murphy Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30720v1 Representational similarity is foundational to analyses of deep networks, yet distances between point-valued representations are not intrinsically tied to downstream function: nearby states may produce different behaviors, while distant states may behave similarly. We instead give representations volume, turning similarity into statistical distinguishability. Overlapping stochastic representations necessarily induce overlapping downstream distributions, grounding latent comparison in model function and bringing it under information-theoretic tools such as the data-processing inequality. We realize this idea in pretrained transformers through a light-touch modification to LayerNorm: at each residual-stream read, we normalize the state, add isotropic Gaussian noise, and renormalize. During distillation fine-tuning, one learned allocation parameter per residual-stream read distributes a fixed global rate budget across the processing stack. The resulting model can be viewed as transformer blocks reading the residual stream with learned finite precision under a shared global rate budget. Using the Bhattacharyya coefficient, we trace which counterfactual distinctions are preserved through MLP blocks or selectively exposed to the query, key, and value computations of individual attention heads. Experiments on ViT-S and GPT-2 small reveal the depthwise propagation of continuous visual perturbations and head-specific sensitivity to token distinctions aligned with known attention motifs. These results establish distinguishability as a functionally grounded lens on transformer computation that complements existing interpretability approaches. --- ### Mind the Gap: Theory-of-Mind-Grounded Friction for Epistemic Alignment Authors: Yifan Zhu, Kyeongmin Rim, James Pustejovsky Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30719v2 Productive dialogue alignment requires distinguishing \emph{surface coordination} (acknowledgments and smooth task progression) from \emph{epistemic alignment} (convergence of belief states); standard preference-based methods typically optimize response-level preferences without explicitly modeling the latter. We operationalize Theory-of-Mind (ToM) inference as a control signal within Frictive Policy Optimization by extracting, at each referring expression, a four-part belief structure: the speaker's intended referent, the addressee's interpretation, and each participant's model of the other's belief. This makes friction mechanically computable from epistemic-state comparisons, capturing \emph{silent divergence}, where both participants proceed confidently while grounding to different referents. We evaluate the signal at two levels. At the representation level, ablating the second-order channel reduces misunderstanding recall from $65\%$ to $26\%$. At the policy level, reward-shaping (FAR) and trust-region (FTR) variants improve intervention F1 and warranted-context calibration over DPO, with Brier scores independently supporting the calibration gains. Across three training runs, FAR and FTR remain substantially more stable, whereas DPO varies widely and can degrade intervention competence already present in the base policy. Thus, ToM-grounded friction provides a trainable signal for context-sensitive intervention under referential belief divergence. --- ### SocialReasonBench: A Video-QA Benchmark for Social Reasoning with Counterfactual Narrative Videos Authors: Zheyu Huang, Zijing Shi, Haozhe Luo, Huadong Tang, Mingyu Liu, Meng Fang, Ling Chen Published: 2026-08-31 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.30716v1 Recent advances in Large Multimodal Models (LMMs) have greatly improved video understanding, yet their ability to reason about human-centered social situations remains limited. Existing benchmarks typically rely on videos with a single observed trajectory, making it difficult to determine whether models truly understand social dynamics or merely exploit recurring narrative patterns. We introduce SocialReasonBench, a video multiple-choice QA benchmark for evaluating socially grounded reasoning in scenarios derived from interactive narratives. Built from gameplay videos of Detroit: Become Human, the benchmark leverages branching storylines where player decisions lead to alternative social outcomes that can be checked against the game's own script, flowchart, and recorded branches. We develop a multi-agent curation pipeline that localizes socially meaningful clips, grounds answer labels in game-state signals, and generates theory-guided questions with diagnostic distractors. SocialReasonBench covers seven reasoning dimensions, including intent recognition, emotional empathy, moral dilemma, counterfactual reasoning, and causal antecedent. Experiments on contemporary LMMs show that models perform reasonably well on basic social understanding but struggle with counterfactual and causal reasoning. Further ablation and diagnostic error analyses reveal that models often depend on incomplete modality cues and fall into reasoning traps such as visual shortcuts, highlighting a gap between observable event recognition and deeper reasoning over latent social states. --- ### SegWave: Wavelet-Driven Segmentation of Tampered Regions Authors: Siddhi Pravin Lipare, Vishesh Kumar, Akshay Agarwal Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30714v1 Verifying image authenticity is increasingly difficult, posing serious risks across journalism, law enforcement, and political domains. Most existing forensic methods rely on high-level visual artifacts and treat frame detection as a simple binary task. To address this, we propose SegWave, a hybrid framework that jointly leverages spatial and frequency-domain cues for image tampering detection. SegWave integrates a transformer-based architecture with the Discrete Wavelet Transform (DWT) to capture localized, multi-scale frequency inconsistencies indicative of manipulation. To further improve localization effectiveness, we introduce an Adaptive Sub-band Attention module (ASA) that dynamically highlights the informative high-frequency wavelet components. Extensive experiments on multiple benchmark datasets demonstrate that SegWave consistently outperforms state-of-the-art tampering detection methods in challenging evaluation settings. --- ### GUIDE: Guiding Internal Evidence with Language Instructions Authors: Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim, Seungyeon Ji, Kyungreem Han Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30712v1 Large multimodal models follow instructions about what to generate, but not necessarily about what evidence to rely on. Hence, models may continue to depend on shortcut-associated cues even when instructions suggest otherwise. We introduce GUIDE, a framework for controlling internal evidence usage through language instructions. GUIDE combines grouped parameter-efficient adaptation with instruction-conditioned gating to modulate multimodal evidence pathways during reasoning and generation. We further introduce a pathway-level evaluation framework that characterizes instruction-conditioned evidence modulation through reliance sensitivity, controlled perturbation analysis, pathway modulation, and autoregressive decoding dynamics. Across multimodal reasoning, classification, and generation, GUIDE induces structured and instruction-aligned redistribution of evidence reliance while largely preserving task behavior. Experiments on GQA, TextVQA, MM-IMDb, CREMA-D, RAVDESS, and Flickr30K show that GUIDE improves robustness under targeted evidence perturbations and enables controllable modulation across diverse multimodal settings. This suggests that multimodal instruction following can extend beyond output control toward regulating how different evidence sources contribute to model predictions. --- ### Kolmogorov--Arnold against bounded translations Authors: Sviatoslav V. Dzhenzher Published: 2026-08-31 Categories: cs.LG, math.FA arXiv: https://arxiv.org/abs/2608.30710v1 Historically originating from Hilbert's 13th problem, the Kolmogorov-Arnold representation theorem (KART) has recently experienced a major revitalisation through its applications to neural networks, specifically Kolmogorov-Arnold Networks (KANs). While the exact representation is well established, its stability under continuous adversarial perturbations of the hidden layer remains a critical open question. In this paper, we investigate the robustness of KART against bounded adversarial translations. We provide an explicit, self-contained, and constructive proof of an approximate representation using fixed, piecewise linear inner functions. Crucially, our construction employs a single outer function that remains invariant for all summands and is independent of the specific adversarial translation, provided its maximum bound is known a priori. --- ### RailSyn: Diagnosis-Guided Image Generation for Traceable Data Completion in Railway Foreign Object Detection Authors: Quan Hao, Chenxi Zhang, Ziyang Tao, Yuyuan Zhou, Yudong Wang, Rui Shi, Lechuan Xu, Changhao Liu, Liguo Zhang Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30709v1 Railway foreign object detection (RFOD) is critical to safe railway operation, yet scarce real positive samples incompletely represent task-relevant variations in object scale, intrusion relation, railway scene, illumination, and adverse weather. Existing synthetic augmentation can improve RFOD detection, but its gains lack an explicit account of the task-relevant deficiencies complemented by the generated data. We therefore introduce RailSyn, a diagnosis-guided framework comprising a real-referenced Inspector and a requirement-aligned Generator. The Inspector constructs a variable-radius empirical cover from finite real observations to localize candidate completion regions and profile synthetic pools. The resulting audit identifies railway-context, intrusion-semantic, and visual-consistency requirements; the Generator addresses them through domain adaptation, agent-planned placement and physical contact relations, and plan-consistent conditional refinement. Using the Inspector, we further trace representation-space changes across generation variants; the complete system attains a local-shell occupation of $C_{gap}$ to 13.64%, which measures generated coverage of real-derived completion regions. Extensive experiments show AP50--95 gains of up to 4.9 points and consistent improvements across nine mainstream detectors, demonstrating broad cross-architecture utility. --- ### VisLens: Single-Pass Interpretable Visual Search for Multimodal LLMs Authors: Jingyi He, Sanghwan Kim, Zeynep Akata Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30705v1 Multimodal large language models (MLLMs) struggle with fine-grained Visual Search, the task of locating small or rare objects in high-resolution images. Existing remedies fall into two families: (1) Training-free methods based on attention or confidence scores are accurate but slow, since they require multiple MLLM queries per example. (2) Reinforcement Learning (RL) trained tool-use models are faster at inference but opaque, since their tool calls remain uncontrollable and hard to interpret. To overcome this, we propose \emph{VisLens} (Visual Focus via Logit Lens), a Visual Search method built on the logit lens, which decodes the semantics held in a hidden state by projecting it through the LLM head. VisLens further uses a lightweight tuned-lens that maps early hidden states into the final hidden state space, so visual tokens can be read out from early layers. These tokens are matched to target words in the query to generate a crop of the relevant region, which is fed back in alongside the original image to produce the final answer. The whole process, from decoding to the final answer, completes in a single forward pass without repeated queries. VisLens matches or exceeds prior baselines while delivering a substantial latency advantage, running $8.5$--$9.9\times$ faster than Thyme and up to $22.2\times$ faster than training-free multi-pass search methods. --- ### TUE-Detector: A Tool-Using Expert MLLM-Based Detector for AI-Generated Videos Authors: Yichen Wu, Haoxuan Qu, Yongxing Dai, Yan Bai, Yihang Lou, Yuqi Lin, Hossein Rahmani, Jun Liu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30704v1 AI-generated video detection, which aims to distinguish AI-generated videos from real ones, has recently received increasing research attention. To perform this task reliably, a key challenge lies in accurately identifying subtle-yet-measurable unnatural artifacts. In this work, we address this challenge from a novel perspective of tool-mediated evidence discovery and propose Tool-Using Expert MLLM-based AI-generated Video Detector (TUE-Detector), a novel framework for AI-generated video detection. TUE-Detector trains a general MLLM into a task-tailored tool-using expert detector that learns to invoke suitable tools, collect concrete evidence of unnaturalness, and reason over the evidence for reliable detection. Meanwhile, TUE-Detector further introduces novel designs to equip the expert detector with high-quality and suitable tools. Extensive experiments demonstrate the effectiveness of our framework. --- ### SingProbe Technical Report Authors: Sing Team Published: 2026-08-31 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30703v2 We present SingProbe, an open intrinsic guardrail framework for generation-time monitoring of LLMs. Intrinsic guardrails reuse hidden states already produced by the base model during autoregressive decoding, rather than relying on an independent model to repeatedly process generated text. While this route has been explored in industrial systems, the community lacks a broadly reusable open stack that combines cross-model guard adaptations, unified training methods, serving integrations, and systematic evaluation resources. SingProbe is designed to provide this missing layer and uses a lightweight probe to continuously produce query-intent, response-safety, and hallucination-risk signals during decoding. This report describes the full intrinsic-guardrail stack: training methods, serving integrations with SGLang and vLLM, and adapted guard models for 29 open-source base models across diverse families and scales. We also introduce SingStreamBench, a benchmark that measures whether streaming guardrails remain inactive on benign prefixes while promptly detecting emerging unsafe content. Across evaluations of safety, streaming detection, hallucination detection, false-positive robustness, online monitoring, and runtime overhead, SingProbe provides performance competitive with, and in several settings stronger than, state-of-the-art standalone guardrails and specialized hallucination detectors, while adding less than 0.5% serving overhead in our implementation. Beyond passive monitoring, we show that intrinsic guard signals can guide constrained decoding and selectively activate medical-risk interventions in SingProbe-Med. By open-sourcing our infrastructure, training methods, and model adaptations, we aim to facilitate the broader adoption and deployment of intrinsic guardrails, as well as further research in this direction. --- ### An Agentic Retrobiosynthesis Framework with Learned Frontier Selection Authors: Philippe Meyer, Guillaume Gricourt, Thomas Duigou, Joan Hérisson, Jean-Loup Faulon Published: 2026-08-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30702v1 Large language models are increasingly used as agents for multistep retrosynthesis, raising the question of how much their search policy contributes independently of the underlying reaction model. We investigate this question in a biological setting through rule-based retrobiosynthesis: a deterministic biochemical engine generates the same validated transitions for every method, searching for routes that terminate in metabolites available to an \emph{Escherichia coli} chassis, while the policy only selects which frontier molecule to expand next. Prompted and LoRA-tuned Qwen2.5-7B policies use a strict choice-only interface. The fine-tuned policy reaches $65\pm1$\% solve rate at 10 expansions on LASER versus 59\% for MCTS, and at 200 expansions reaches $78\pm1$\% versus 75\% on LASER, $88\pm3$\% versus 80\% on the RetroPath RL Golden benchmark, and $63\pm2$\% versus 45\% on the BioNavi-NP benchmark. Fine-tuning also consistently outperforms direct prompting. These results show that route-supervised frontier selection can improve budgeted search without altering biochemical generation, although performance remains dependent on frontier construction and reaction ranking. --- ### Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning Authors: Yue Cheng, Jiajun Zhang, Xiaohui Gao, Weiwei Xing, Zhanxing Zhu Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30699v1 Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to degraded generalization. While many long-tailed semi-supervised learning (LTSSL) methods have been proposed, the mechanisms by which they implicitly debias logits remain poorly understood. In this work, we revisit LTSSL through the lens of learning dynamics and provide a theoretical characterization of logits debiasing. Specifically, we derive a step-wise decomposition of the logits updates, showing that predictions are dominated by class-imbalance bias that reliably reflects label priors. To expose this effect, we use the logits of a task-irrelevant baseline image as an indicator of accumulated bias and prove that they converge to the class prior. This provides a unified view where LTSSL remedies such as logit adjustment, reweighting, and resampling correspond to reshaping gradient dynamics. Based on this insight, we propose DyTrim, a principle-based dynamic pruning framework that reallocates gradient budget through class-aware pruning on labeled data and confidence-based soft pruning on unlabeled data. We provide theoretical guarantees that DyTrim reduces class bias and improves generalization. Extensive experiments on standard LTSSL benchmarks show consistent gains across architectures and methods. Code available at: https://jiajun0425.github.io/DyTrim --- ### Liquid Gated Attention Authors: Yiheng Jiang, Yuanbo Xu, Yongjian Yang Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30695v1 Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arbitrary intervals without prohibitive scaling costs. Discrete-time methods collapse variable time intervals into static positional steps; solver-dependent continuous-time models preserve temporal structure but rely on sequential integration, precluding parallelization; and solver-free approximations avoid this cost yet none couples observed time intervals with input-driven state modulation. We propose Liquid Gated Attention (LGA), a solver-free parallel temporal operator. By parameterizing an input-driven gating mechanism with observed time intervals, LGA introduces a continuous-time inductive bias and formulates hidden state evolution as a fast-weight associative memory, enabling parallel computation across the temporal dimension. Using matrix associativity in non-causal encoding and a prefix scan in causal encoding, LGA attains linear temporal complexity in sequence length in both modes. A sequence-level normalization bounds cumulative temporal decay for stable long-horizon optimization. Building on LGA, we instantiate LFormer, a modular backbone for continuous-time representation learning. Across six tasks and sixteen datasets spanning up to 17,984 steps, LFormer demonstrates long-range dependency modeling, fine-grained state tracking, and trajectory reconstruction from sparse and noisy observations, while delivering competitive performance against state-of-the-art discrete-time and continuous-time baselines with linear scaling efficiency. --- ### Can Video World Models Track Unobserved World States? Authors: Joonghyuk Shin, Yicong Hong, Jaesik Park, Xun Huang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30692v2 Video world models are increasingly used as simulators, but visual fidelity alone does not show that a model maintains the hidden state of the world. We examine this difference with an action-conditioned video Shell Game, a visual analogue of $S_5$ state tracking that separates visual rendering from compositing the unobserved world state. Trained on 5-swap chains, standard backbones (e.g., bidirectional and autoregressive Transformers, Mamba, and linear attention) render plausible videos and predict the correct ball location up to 5 swaps. However, they fail to learn the rule and generalize to longer swap chains, even with more denoising steps. As the pixel-based diffusion loss does not force the generated frames to hold the unseen ball position, output tokens cannot carry it, and the state has to live within the architecture. In a causal Transformer, this implicit state is an append-only KV cache, which is written once and never revised, so the model must re-compose the swaps at every chunk. Tracking $S_5$ this way requires depth to grow with sequence length, which no fixed-depth Transformer provides. We study what enables learning the rule, and find that length generalization requires a revisable state carried across chunks and an update expressive enough to apply a swap. Linear attention can achieve this by allowing negative transition eigenvalues, and autoregressive Transformers can do so with nonlinear TTT fast weights (e.g., SwiGLU) whose online updates change the feature map used to read their state. We further examine Memory Maze and Block World, where the state is not fixed by the input action stream alone and must be corrected from observations or keeps changing out of view, and discuss the implications for building stateful video world models. --- ### Failure or Drift? Evaluating Monocular SLAM under Synthetic and Real-World Corruptions Authors: Abhay Skaria Thomas, Shashank Agnihotri, Margret Keuper Published: 2026-08-31 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2608.30690v1 Visual SLAM is commonly evaluated on clean trajectories, although deployment failures are often caused by adverse weather, illumination, blur, and sensor artifacts. Controlled corruptions are attractive because they isolate such factors, but a synthetic stress test is useful only when it leads to the same engineering conclusion as the condition it is intended to approximate. This work examines that question for monocular SLAM. We evaluate a classical feature-based system and two learned trackers under image-space, geometry-aware, and compound corruptions, and compare their behavior with adverse conditions from 4Seasons. Rather than reducing robustness to a single trajectory error, the evaluation separates explicit tracking failure from drift accumulated by methods that remain active. The results show that learned trackers largely replace catastrophic loss with sustained, and sometimes severe, drift. More importantly, the apparent ordering of the learned systems changes with the physical fidelity of the corruption: structured rain and fog proxies preserve the real-world ordering, whereas a simple illumination proxy does not. Code is available at: https://github.com/abhaythomas/master_thesis_vslamlab_robustness. --- ### CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generation Authors: Yichen Wu, Haoxuan Qu, Yihang Lou, Hossein Rahmani, Jun Liu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30689v1 Autoregressive large models have recently advanced Text-to-SVG generation from simple icons to complex, long-context graphics, yet standard autoregressive decoding often fails to maintain global consistency across geometry, layout, occlusion, and composition. We introduce CANVAS (Consistency-Aware Navigation via Visual Adaptive Sampling), a training-free, render-aware inference framework that combines power-sharpened trajectory likelihood with visual feedback from rendered futures and derives a stroke-wise navigation rule. It effectively estimates each candidate stroke's future value under a limited generation and rendering budget and adaptively allocates samples according to candidate uncertainty, decision influence, and rollout cost. Experiments across multiple autoregressive SVG backbones and complementary benchmarks demonstrate improvements in global consistency, which includes sound geometric relationships, spatial layouts, occlusion ordering, and overall composition, without additional training, demonstrating the effectiveness and generalization ability of our framework. --- ### UFPR-PEs: A Brazilian Face Recognition Benchmark with Self-Declared Race/Color Labels Authors: Alexandre Diano, Bernardo Biesseck, Gabriel Polo, Vinicius Gregorio, Laura Lopes, Diego Addan, David Menotti Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30688v1 While face recognition systems are widely deployed, ensuring their demographic reliability and robustness under uncontrolled visual conditions remains a critical challenge. To bridge this gap, we present UFPR-PEs, a benchmark for face recognition bias evaluation using public videos of elected Brazilian politicians annotated with official self-declared race/color categories. The dataset adopts the Brazilian census taxonomy, including the parda category, which has no direct equivalent in the U.S.- or Europe-centric schemas commonly used in prior benchmarks. Our benchmark is built from compressed public video and preserves difficult samples so that performance can be analyzed under realistic conditions. We describe the construction pipeline, report dataset statistics, and evaluate face recognition performance across verification and (closed- and open-set) identification settings, including subgroup analysis by race/color and difficulty level. The results show that recognition performance varies substantially with image quality, and that subgroup gaps must be interpreted jointly with visual difficulty rather than in isolation. Overall, UFPR-PEs provides a reproducible and demographically grounded setting for studying face recognition bias under challenging public video conditions. --- ### Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning Authors: Fukang Zhu, Binbin Zhao, Ruixiao Lin, Ping He, Tianyu Du, Shouling Ji Published: 2026-08-31 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2608.30686v1 Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on repository poisoning largely focuses on attacker-controlled injection and disguise, but developers also shape risk through everyday invocation choices: what task to delegate, how to phrase the request, and which skills or rules to supply. We term these user-side choices Prompt-Level Configurations (PLCs) and introduce CIPR (Coding In Poisoned Repos), the first benchmark that systematically varies PLCs in poisoned real-world repositories. CIPR comprises 1,920 instances across 20 repositories, four task types, three social-media-grounded prompt styles, and three skill/rule conditions, and measures attack success rate (ASR) and agent alert rate (AR) using automated runtime and trace-based oracles. Our evaluation reveals two key insights: (1) Vulnerability is highly context-dependent, with task type creating up to a 4.5-fold difference in ASR, with test-execution task forming a silent attack surface (high ASR, low AR). (2) Prompt expression shifts risk indirectly: underspecified prompts reduce ASR by truncating execution depth; noisy prompts exhibit a directional trend toward suppressing alerts by making malicious content less conspicuous. These findings highlight that coding agent vulnerability is not a static property, but a dynamic outcome shaped by everyday user configurations. --- ### ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents Authors: Wei Chen, Peilun Zhou, Zhaoyu Hu, Jiajun Chai, Zhongni Hou, Yufei Zhang, Derong Xu, Guojun Yin, Wei Lin, Zhi Zheng, Tong Xu Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30685v1 Large language model (LLM) agents are increasingly deployed in user-facing services that require iterative tool use under dynamic business conditions. Reliable evaluation is essential for sustained improvement: it must reveal capability deficiencies, inform priorities, and assess interventions. Yet industrial agent service unfolds both through the iterative trajectory of a current request and through continued user interaction. Final-outcome assessment can therefore obscure where deficiencies arise and whether later service remains aligned with context from earlier exchanges. We propose ATLAS, a dual-horizon diagnostic evaluation framework for industrial tool-use agents. At the request horizon, trajectory-wise diagnostic signals relate deficiencies to execution locations and capability concerns. At the interaction horizon, user-wise signals assess whether service remains responsive across continued interaction. Together, these views provide structured diagnostic evidence for analyzing execution deficiencies and sustained service behavior. ATLAS instantiates them as executable signals with explicit evidence scopes and decision boundaries. LLM judge interfaces are calibrated against high-confidence references from real business logs; when needed, their decision behavior is distilled into efficient diagnostic models for lower-latency, lower-cost evaluation. The resulting feedback supports policy optimization. We evaluate ATLAS on Meituan Xiaotuan production traffic. Offline experiments assess diagnostic-signal fidelity and replay-based policy improvement, while online A/B experiments show concurrent gains in user engagement, downstream business outcomes, and sampled human-audit quality. --- ### WildSEEK: Evaluating Language Models for Information-Seeking Authors: Tanise Ceron, Joachim Baumann, Elisa Bassignana, Berat Cabuk, Dirk Hovy, Debora Nozza Published: 2026-08-31 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2608.30683v1 Language models are increasingly mediating information access to end users, urging a systematic evaluation of their responses for a fair and reliable information ecosystem. Existing evaluations, however, are often topic-specific or synthetic, limiting their ability to capture the complexity of "in the wild" information-seeking queries and the risks present in model responses. To address this gap, we introduce WildSEEK, a manually annotated dataset of 3k information-seeking queries from real user interactions, and an evaluation framework for LLM-generated responses. WildSEEK includes annotations for risk-sensitive domains (e.g. health and financial information), and distinguishes factoid queries from analytical queries which seek responses beyond facts. We train classifiers on WildSEEK to analyze more than 1.8M realistic user queries. We find that over a third of information-seeking queries are high-risk and more often analytical. Our findings show that LLM responses fail more often in four criteria: sycophantic behavior, overreliance, a default US-centric perspective, and poor handling of vulnerable populations -- with failure rates being mostly higher for analytical queries. By providing methods to monitor the reliability, safety, and fairness of LLM behavior, our dataset and evaluation framework offer an empirical foundation for the broader question of how these systems should behave as they take on a growing role in information access. --- ### Learning Materials Properties from Scarce Labels and Unlabeled Crystals Authors: Wentao Li, Yizhe Chen, Jiangjie Qiu, Yijun Li, Leyi Zhao, Xiaonan Wang Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30682v1 Learning materials properties from scarce labels and unlabeled crystals is a central challenge for data-driven materials discovery. We present SemiMat, a controlled benchmark for semi-supervised materials property regression, and MatRank, a reliability-weighted objective for continuous pseudo-label uncertainty. SemiMat fixes labeled and unlabeled crystal inputs, graph-backbone interfaces, validation-only checkpoint selection, held-out test reporting, normalized MAE (NMAE), and method-rank summaries across six scarce-label tasks, four graph backbones, and five predefined split runs. MatRank builds pseudo-targets from labeled anchors, weights them by local reliability and weak-prediction agreement, trains weak and strong graph views consistently, and adds ranking signals so that unlabeled crystals shape both values and candidate order. Across the retained 24 backbone-task blocks, one fixed MatRank objective gives the lowest aggregate held-out test NMAE (0.896) and best average method rank (2.208). The component, OOD, and generated-pool diagnostics identify where the gain is reliable and where further screening evaluation remains necessary. Code is available at https://github.com/littlepeachs/SemiMat. --- ### LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language Models Authors: Bérénice Jaulmes, Mehwish Alam Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30679v1 Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching the conclusion. However, these steps often contain contradictions, unsupported inferences, or irrelevant steps, even when the final answer is correct. We propose Long Chain-of-Thought Graph Verifier (LCoT-GV), a graph-based framework that represents LCoTs as reasoning graphs. Each node in the graph represents a reasoning step and the edges encode semantic and logical relations. A Graph Attention Network is then trained to predict chain-of-thought correctness from the reasoning graph. We construct a new graph-oriented verification dataset from multiple reasoning benchmarks for question answering in various domains. The results show that our method is competitive with the most similar approaches. --- ### OCR-MetaReasoning Benchmark: Evaluating the Meta-Reasoning Ability of MLLMs in Text-Rich Image Understanding Authors: Gengxu Li, Yuan Wu, Yi Chang Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30678v1 Text-rich image understanding requires multimodal large language models (MLLMs) to organize OCR (Optical Character Recognition)-grounded evidence across words, layout, fields, charts, and visual correspondences. Existing evaluations often conflate extraction with reasoning and rarely test whether models follow the required reasoning direction: applying visible rules, abstracting hidden regularities, or recovering missing premises. We introduce OCR-MetaReasoning, a controlled single-image benchmark that treats deduction, induction, and abduction as distinct directions and separates final-answer correctness from reasoning-process compliance. The benchmark contains 1,500 verified samples in a balanced \(3\times5\) taxonomy crossing three reasoning types with five OCR-object categories, along with reference reasoning steps, automatic answer scoring, the Meta-Reasoning Macro Score (MRMS), and the Reasoning Process Compliance Score (RPCS). Experiments with representative closed-source and open-source MLLMs show that OCR-grounded meta-reasoning remains far from saturated: models struggle with visible-rule application and layout-sensitive inference, while process-compliant rationales can accompany incorrect final answers under exact-match evaluation. The code is available at https://github.com/gengxuli/OCR-MetaReasoning. --- ### MedAgent-R1: Faithfulness-Aware Reinforcement Learning for Evidence-Grounded Medical Reasoning Authors: Jiangwang Chen, Chenghao Zhang, Hengxing Cai Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30676v1 When medical AI systems hallucinate clinical reasoning, the consequences extend beyond incorrect answers: fabricated justifications that superficially reference retrieved evidence can mislead clinicians into unsafe treatment decisions. Medical reasoning agents must therefore produce not only correct answers but also faithful justifications that clinicians can verify against cited evidence. We identify a systematic failure mode in RL-trained retrieval agents: outcome-only rewards improve accuracy while degrading faithfulness, a phenomenon we term confident hallucination. The agent learns to answer from parametric memory and backfill plausible but unsupported justifications; citation fabrication rates rise from 16.5% to 31.8% even as accuracy improves by 5 points over the supervised baseline. We address this with a faithfulness-gated reward design: accuracy credit is conditioned on evidence grounding via a hard gate, complemented by retrieval validity and conciseness signals that close exploitation paths unique to agentic retrieval. The resulting system, MedAgent-R1, reduces citation fabrication from 31.8% to 4.7% and raises evidence completeness from 58.7 to 82.6 while maintaining 75.1% accuracy, with 13.2-point gains on HealthBench Safety. Under the same agentic retrieval setup, MedAgent-R1 outscores GPT-4o on faithfulness-specific dimensions (Factual Support 4.55 vs. 4.25; Overclaiming 4.40 vs. 4.15) while remaining below GPT-4o in overall accuracy, suggesting that explicit faithfulness training yields evidence-grounding gains not achieved by scaling alone. --- ### CoMPASS: Collaborative Molecular Property Prediction via Adaptive Small-Large Model Synergy Authors: Wentao Li, Jiangjie Qiu, Yijun Li, Leyi Zhao, Xiaonan Wang Published: 2026-08-31 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.30674v1 Accurate molecular property prediction requires both statistical reliability and chemical reasoning. Graph neural networks can be calibrated directly on labeled assays but remain limited by the coverage of their training data. Large language models (LLMs) can compare molecular evidence and articulate chemical rationales, yet are unreliable as standalone quantitative predictors. The central challenge is therefore to determine when an LLM should influence a calibrated model and by how much. Here we present CoMPASS, a retrieval-calibrated framework for small-large model collaboration. CoMPASS retains a graph attention network (GAT) as the predictive anchor, retrieves locally relevant training molecules, provides attention-grounded evidence to an LLM, and converts its proposal into a bounded correction through an agreement-aware gate. Across six classification and two regression benchmarks, CoMPASS improves the GAT anchor in regions of correctable uncertainty while limiting LLM intervention in high-confidence regimes. Ablations show that the gains arise from validation-calibrated retrieval and bounded fusion rather than prompting alone. These results suggest that generative reasoning should augment calibrated prediction through evidence-grounded, controlled corrections rather than direct output replacement. Code is available at https://github.com/littlepeachs/CoMPASS. --- ### HiRS-Agent: A Hierarchical Multi-Agent System for Reliable Long-Horizon Remote Sensing Task Solving Authors: Boyang Mu, Zhiwei Wei, Mugen Peng, Wenjia Xu Published: 2026-08-31 Categories: cs.AI, cs.MA, cs.MM arXiv: https://arxiv.org/abs/2608.30672v1 Recent advances in large language models and multimodal models have pushed remote sensing (RS) processing from simple perception models to agentic systems designed to tackle complex, long-horizon RS tasks. However, existing systems often rely on monolithic decision-making frameworks, which fail to accommodate the multi-stage, interdependent nature of RS tasks. This centralized approach leads to challenges such as unstable task execution, incorrect tool usage, and error propagation across stages. To address these issues, we propose HiRS-Agent, a hierarchical multi-agent system for long-horizon RS task solving. HiRS-Agent adopts a two-level collaborative architecture: the Manager Layer handles dynamic routing, step-level verification, replanning, and termination control, while the Specialist Layer organizes domain-specific tools according to the RS workflow and is responsible for subtask reasoning and tool execution. To further enhance the system's capability, we introduce a two-stage supervised tuning strategy and a verification-guided hierarchical reinforcement learning stage to jointly optimize coordination and tool-use policies. Experiments on Earth-Agent Benchmark and ThinkGeo show that HiRS-Agent substantially improves long-horizon tool-use capability and final-task correctness, demonstrating the effectiveness of structured multi-agent collaboration for reliable RS agents. The code is publicly available at https://github.com/IntelliSensing/HiRS-Agent. --- ### MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines Authors: Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang, Federico Tiblias, Jingcheng Niu, Subhabrata Dutta, Richard Eckart de Castilho, Iryna Gurevych Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30662v1 This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers across disciplines. These studies often combine loading, recording, attribution, intervention, and evaluation, while existing libraries tend to focus on different parts of this workflow. As a result, researchers using several libraries may need to adapt outputs from one for use by another. To bridge this gap, Murano represents operations from these five areas as composable steps. Steps exchange named result artifacts and declare the inputs they require and the outputs they produce. A pipeline executes its steps in the order supplied, and Murano uses canonical addresses when component identities pass between operations. Murano builds on existing interpretability and machine learning libraries. We demonstrate Murano through two reproductions of established interpretability studies and one illustrative sparse autoencoder case study. --- ### SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators? Authors: Jinshan Gao, Zhuoran Jin, Tianyi Men, Kang Liu, Jun Zhao Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30661v1 Large language model-based multi-agent systems are evolving from fixed interaction topologies toward dynamically orchestrated Agent Swarms. However, existing benchmarks are still largely based on single-agent or general-purpose agent tasks, making it difficult to systematically evaluate key orchestration capabilities. We propose SwarmBench, a benchmark that evaluates model performance from multiple perspectives, including accuracy, efficiency, cost, and process quality. Experimental results show that current models exhibit substantial differences in orchestration capability. These differences are reflected not only in final accuracy, efficiency, and cost, but also in the overall quality of the orchestration process itself. Based on these findings, we further propose SwarmExp, a simple yet effective method based on experience extraction and experience replay, which consistently improves the orchestration performance of large language models. --- ### InfraOcc: An Infrastructure Occupancy Benchmark with Static-to-Dynamic Reasoning Authors: Lei Yang, Xiaokai Bai, Boqi Li, Chunmian Lin, Li Wang, Ziying Song, Jiahuan Zhang, Enhui Ma, Haibao Yu, Jiaqi Ma, Kaicheng Yu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30657v1 Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle perception: a near-persistent static scaffold is overlaid with sparse, short-lived dynamic events. Existing occupancy benchmarks and methods, however, are built around moving ego vehicles and neither measure nor exploit this structure, instead treating occupancy as flat one-shot voxel classification. We address this gap from both data and model perspectives. We build InfraOcc, to our knowledge, the first real-world infrastructure-side semantic occupancy benchmark, with dense voxel annotations for 290 multi-modal sequences in a fixed roadside frame, a static-dynamic decoupled annotation pipeline, unified camera-only, LiDAR-only, and multi-modal evaluation, and diagnostics for static and dynamic occupancy. InfraOcc shows that static infrastructure fills 97.3% of occupied voxels and persists across frames, whereas dynamic participants have a median occupied-frame ratio of only 1.8% per location, revealing a structural static-dynamic asymmetry beyond semantic long-tailedness. We further propose ProSD-Occ, which reformulates occupancy as progressive static-to-dynamic evidence reasoning: it explains persistent layout, exposes residual dynamic evidence under static-confidence guidance, and recomposes static, dynamic, and free-space evidence into a unified field. ProSD-Occ ranks first in overall, dynamic, static, and geometric occupancy on every track, e.g., a 23.5% relative camera-only dynamic-mIoU gain over the strongest baseline and 65.87 multi-modal overall mIoU, establishing fixed-viewpoint roadside occupancy as a distinct problem with its own reasoning paradigm. The benchmark and code will be publicly available at https://github.com/yanglei18/InfraOcc --- ### APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images Authors: Suhyeon Ha, Woo Jae Kim, Joonsung Jeon, Sooel Son, Sung-eui Yoon Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30656v1 Proactive tamper localization embeds an imperceptible signal into an image prior to distribution, enabling pixel-level manipulation detection. Existing methods assume a spliced (SP) setting, where synthesized regions are composited onto the original background, leaving embedded signals intact. However, real-world diffusion-based inpainting operates in a fully regenerated (FR) setting, where the entire image undergoes denoising, disrupting background signals and rendering existing frameworks ineffective. We propose APT, a semi-fragile latent-space perturbation that embeds a dense, vector-wise localization signal. By aligning each spatial feature vector toward a fixed anchor direction, APT localizes tampering via the alignment disparity between synthesized foreground and anchor-aligned background features after inpainting. The proposed hard negative mining loss and noisy perturbation branch further enforce uniform alignment. Experiments on COCO demonstrate that APT achieves an FR IoU of 0.92, outperforming the strongest baseline (WAM, 0.84), while existing methods collapse to near-random performance (AUC 0.5), establishing APT as a practical forensic framework generalizable across tampering types unknown at test time. --- ### Seasonality-Aware Hybrid Convolutional Transformer for Antarctic Sea Ice Concentration Forecasting Authors: Danyang Li, John Taylor, Thang Bui, Quanling Deng Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30654v2 Antarctic sea ice concentration (SIC) forecasting is an important yet challenging task due to the coexistence of complex spatial structure, long-range temporal dependencies, and strong seasonal variability. Conventional convolution-based models are effective at capturing local spatial patterns, but often have limited ability to model long-term temporal evolution. To address these challenges, we build on a hybrid convolutional transformer forecasting framework for monthly Antarctic SIC forecasting. This framework combines convolutional encoding for spatial feature extraction with space-time factorised self-attention for SIC modelling. We further introduce two season-based mechanisms: a month-aware positional encoding that injects calendar-month information into the token representation, and a seasonal temporal bias that encourages attention to periodically related historical states. Experimental results show that the proposed framework achieves better performance than convolutional and recurrent baselines as well as ECMWF's physics-based dynamical model SEAS5 under both classification and regression metrics. Ablation studies further indicate that the seasonality-aware components provide consistent additional gains in both short- and long-horizon prediction. These results demonstrate the value of combining convolutional structures, attention mechanisms, and periodic prior information for Antarctic SIC forecasting. --- ### Fine-Grained Multi Image Object Hallucination Benchmark Authors: Joonki Min, Chaeyun Kim, Hyungwook Choi, Yejin Kim, Kihyun Kim, Yohan Jo, Joonseok Lee Published: 2026-08-31 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30653v1 Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundamentally limited by object hallucination-generating plausible yet factually inconsistent descriptions about objects. Existing benchmarks, designed primarily for single-image settings or providing only high-level multi-image assessments, cannot systematically diagnose how visual complexity and reasoning demands trigger hallucination. To address this gap, we introduce MIOH, a fine-grained multi-image object hallucination benchmark that systematically evaluates object hallucination across four foundational tasks (existence, counting, attribute, position) through three multi-image reasoning patterns (comprehensive, comparative, selective) under three controlled adversarial pressures (visual context scale, perceptual difficulty, contextual bias). Through evaluation of 29 models, we reveal that even state-of-the-art systems like GPT-5 and Gemini-2.5-Pro exhibit distinct failure patterns across different reasoning patterns and tasks. Our evaluation reveals that hallucination stems not merely from perceptual failures but from integration-stage limitations when maintaining object representations across multiple images. MIOH provides a controlled framework for analyzing multi-image object hallucination and serves as a critical evaluation tool for developing more reliable multimodal AI systems. --- ### PyKEEN-NSX: A Modular Framework for Static, Dynamic and Schema-Aware Negative Sampling in PyKEEN Authors: Ivan Diliso, Nicola Fanizzi, Claudia d'Amato Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30652v1 Embedding methods have become popular due to their scalability on link prediction and/or triple classification tasks on Knowledge Graphs (KGs). Embedding models are trained relying on both positive and negative samples of triples. However, since KGs generally contain only positive assertions, negative samples are artificially generated through negative sampling strategies, ranging from simple random corruption to more sophisticated approaches that exploit structural, semantic, or embedding information. The design and implementation of advanced negative samplers remains challenging, as most popular Knowledge Graph Embedding (KGE) libraries provide support only for basic strategies and lack a unified framework for developing more advanced and customized solutions. To address this gap, we introduce PyKEEN-NSX, an extension of PyKEEN, the popular KGE framework, that provides a modular engineered abstraction for negative sampling. The proposed architecture separates the generation of candidate negative pools, conditioned on an explicit context, from the selection strategy, enabling the development and integration of static, schema-aware and dynamic approaches within a consistent framework. Based on this abstraction, we implement six negative samplers, while remaining fully compatible with existing PyKEEN workflows and pipelines. As a proof of concept, we study negative availability across four datasets, showing that constrained pools frequently fall below the requested number of negatives, so that the encoded criterion is to a large extent replaced by the random fallback that supplements them. --- ### Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning Authors: Jie Liang, Zhengxin Yu, Hamid Nasiri, Peter Garraghan Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.30650v1 LLM agents need to sustain goal-consistent reasoning across long multi-turn interactions under strict resource constraints. However, as the multi-turn context accumulates, it can destabilize the underlying LLM's internal representation of task-relevant information from earlier turns, blurring the boundary between constructive reasoning and representation drift. We formulate multi-turn reasoning as a hidden-state trajectory of the underlying LLM that is characterized via two complementary signals: temporal curvature that captures the directional consistency of turn-to-turn updates, and variance slope which measures the expansion or contraction of the exploration space. Across four tasks and three underlying LLMs, we observed that these geometric signals distinguish between correct and incorrect episodes prior to completion. We further decompose each episode into three-action chains formed from four actions (Read, Write, Respond, Transfer) and show that separability is action-dependent, with different signals distinguishing various chain patterns. Our experiments demonstrate that trajectory geometry can identify critical turns in the reasoning process, increasing task success rates on $τ$-Bench from 24.1% to 39.6% while reducing token cost by 11.2%. --- ### Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models Authors: Kangwook Ko, Jaehyuk Jang, Wonjun Lee, Hee-Seon Kim, Changick Kim Published: 2026-08-31 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2608.30649v1 Removing a specific individual's information from multimodal large language models (MLLMs) is often needed after deployment, but existing methods rely on a retain set, which is hardest to obtain at that point, and rebuilding it recreates the privacy exposure that unlearning aims to remove. Forgetting from the forget set alone instead damages the shared visual-language computation, harming perception. We cast retain-free unlearning as a localization problem: causal tracing, weight transplant, and Fisher overlap all point to early-to-mid decoder MLPs as the layers where identity information is stored and, unlike other module families, can be modified without substantially disrupting vision. We turn this into Pathway-Aware Visual-attribute Anchoring (PAVA), which confines updates to these layers and pairs a forget loss with a visual-attribute anchor that preserves image-grounded behavior by distilling the model's own pre-unlearning answers from the forget images alone. On MLLMU-Bench and ReMem, PAVA gives the strongest forget-retain trade-off among forget-set-only methods and remains competitive with retain-based baselines. --- ### What It Costs to Compose, Rebuild, and Correct Precomputed Memory Authors: Asa Shepard Published: 2026-08-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30647v1 Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at each. This paper maps where that practice preserves correctness and the conditions under which it fails. Across experiments on Llama-3.1-8B-Instruct using both saved key-value caches and trained compressions of them, precomputed memory degrades when assembled from separately prepared parts, stays current only through rebuilds costing a large fraction of full preparation in our measurements, and ignores corrections served beside it conditional on phrasing. If precomputed memories can be served alongside one another, be cost-efficiently rebuilt, and be superseded by new information arriving in real-time, they can serve as a way to avoid re-feeding context to a model over repeated queries. The implication of our results for a deployed system that deals with a variety of queries is that precomputed memories are best rebuilt on the cadence at which new information changes what the memory was originally computed from. Both warm-rebuilding trained compressions of key-value caches and serving specifically-phrased updates beside a memory, as pasted text or injected cache state, show particular promise for keeping precomputed memories current, the latter as an interim measure between rebuilds, and we measure the cost and name the remaining questions associated with each. --- ### BiG-SURE - Bipartite Graph for Semantic Uncertainty and Reliability Estimation of LLMs Authors: Debarpan Bhattacharya, Malay Phadke, Sriram Ganapathy Published: 2026-08-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30646v2 Reliable uncertainty estimation is a crucial requirement for deploying large language models (LLMs) and vision-language models (VLMs) in safety-critical settings, especially when the model parameters are not accessible (black-box). We propose BiG-SURE, an uncertainty estimator based on cross-temperature semantic agreement. The method samples low-temperature responses as stable semantic anchors and high-temperature responses as probes under meaning-preserving input transformations. It then constructs an anchor-probe Bipartite Graph (BiG) using NLI-based entailment scores and defines confidence through the normalized squared spectral energy of this matrix, with uncertainty given by its complement. This bipartite graph-based Semantic Uncertainty and Reliability Estimation (SURE) score measures whether high-temperature probes remain semantically aligned with the model's stable low-temperature belief or not. We evaluate BiG-SURE on text QA, multilingual QA, and multimodal QA tasks across multiple model families. In these experiments, BiG-SURE improves average abstention AUROC over prior black-box uncertainty estimators, while remaining simple, unsupervised, and applicable to black-box model settings. --- ### Marginal Coordinate Test for Fréchet Regression with Random Objects Authors: Jiaye Chen, Rui Qiu, Roulin Wang, Zhou Yu Published: 2026-08-31 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2608.30644v1 We develop a marginal coordinate test for regression with Euclidean predictors and a random-object response in a separable metric space. The goal is to test whether a predictor provides additional information about the response conditional on the remaining predictors. In a semi-supervised design, an unlabeled sample is used to estimate predictor conditional means, while an independent labeled sample is reserved for inference. The resulting residuals are combined with a product-space kernel to form a kernel conditional mean dependence (KCMD) U-statistic without requiring a response residual. The primary identity-based test targets a necessary conditional mean restriction, while a multiple-transformation extension probes broader alternatives. We establish a weighted centered chi-square null limit, wild bootstrap validity, consistency against fixed detectable alternatives, and local power under mean-element alternatives. For simultaneous inference, truncated p-to-e calibration combined with e-BH provides asymptotic false discovery rate control under general dependence. Simulations with Euclidean and non-Euclidean responses, together with a New York City taxi-flow analysis, illustrate the method. --- ### Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL Authors: Michal Korniak, Kamil Dybek, Benjamin Eysenbach, Marco Bagatella, Michał Bortkiewicz Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30640v1 While self-supervised approaches to reinforcement learning have achieved strong results by learning representations of states and actions, a key open question is the time scale over which actions should be modeled. Departing from the standard formulation relying on single-step actions, we extend contrastive reinforcement learning (CRL), a prototypical self-supervised method, to operate over action chunks, and find that this results in large, pervasive gains across established offline and online benchmarks: +31.7% and +93.1% across 18 and 11 environments respectively. While action-chunking-driven gains are generally explained through the ability to model non-Markovian, temporally extended policies, and to propagate unbiased multi-step returns, interestingly, we find that these arguments only partially apply to CRL. Our empirical studies suggest that, in the context of CRL, an action chunk carries more information about the goal than a single action, measurably improving the critic's representations, and rendering the algorithm significantly more effective. --- ### MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributions Authors: Christina X. Ji Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30636v2 Optimizing absorption, distribution, metabolism, and excretion (ADME) is an important part of small molecule drug discovery. Many machine learning models have been built to predict ADME properties to facilitate this optimization process, but explaining model predictions is challenging. We propose a new graph neural network architecture with built-in atom attributions. Our model MolLedger learns a global context vector for each molecule and a per-atom head to output atom scores that sum to the predicted property. The atom scores are regularized to align with relevant chemical properties. We prove that MolLedger is a universal approximator and demonstrate empirically that the new architecture obtains explainability with little effect on performance. We show that the interpretations from MolLedger are faithful, concordant with held-out physical properties, and align with the changes between matched molecular pairs. Our case studies comparing interpretations from multiple methods on molecular pairs reveal that MolLedger is much better at producing sensible explanations for predicted property changes. --- ### Quantum-Grassmann-Plucker Token Mixing for Deep Learning-Based Post-Disaster Damage Assessment Authors: Kooroush Farahkhah, Umut Lagap, Taha Rezaei, Saman Ghaffarian Published: 2026-08-31 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.30633v1 Timely post-disaster building damage assessment from satellite imagery is a critical engineering decision support task, yet it remains constrained by class imbalance, ambiguous intermediate damage states, and limited cross-event transferability. This study presents, to our knowledge, the first application of Grassmann-Plucker (GP) token mixing to computer vision and introduces two extensions for image classification: the Quantum-inspired Grassmann-Plucker (QGP) head and the Hybrid Quantum Machine Learning Grassmann-Plucker (HQML-GP) head. The GP head represents multiscale relationships among image patch tokens by encoding subspaces formed by token pairs with Plucker coordinates; QGP enriches these coordinates with amplitude-derived probability features, whereas HQML-GP incorporates expectation values generated by a simulated quantum circuit into the geometric token representation. Paired pre- and post-event image patches from the xBD tornado dataset were processed using a frozen six-channel Vision Transformer base encoder with 16 x 16-pixel patches. The three GP-based heads were compared with multilayer perceptron and Transformer baselines under identical training, checkpoint selection, and evaluation protocols. Joplin and Moore tornado samples were used for model development and seen-event testing, while Tuscaloosa was reserved for unseen-event evaluation. QGP led both test sets in accuracy and macro-F1: 83.46% and 64.50% for the seen events, and 66.45% and 52.70% for the unseen event. Although HQML-GP obtained the highest validation macro-F1 of 65.63%, it did not surpass QGP on either test set and required substantially more training time per epoch. These results establish GP token mixing as a competitive attention-free alternative to conventional Transformer-based token mixing for paired satellite image damage classification. --- ### GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning Authors: Outongyi Lv, Yuanwei Zhang, Xiaoqun Zhang Published: 2026-08-31 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.30632v1 Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language models' (LLMs) reasoning abilities, demonstrating remarkable effectiveness across reasoning tasks. Recent studies suggest that high-entropy tokens play an exceptionally important role in model training, since training with only the highest 20% entropy tokens yields significant performance gains. However, why such high-entropy tokens are beneficial remains insufficiently understood. In this work, we find that although high-entropy tokens within one answer tend to correlate with large gradient magnitude, entropy alone fails to consistently reflect token importance across different answers, considering the variations in the answer-level reward signals. Based on this observation, we introduce the Gradient Magnitude-based Token Selection (GMTS) method to quantify token importance, which leverages the entropy-gradient connection to approximate gradient-magnitude rankings for token selection. We find that training on the top 20% tokens ranked by GMTS consistently outperforms entropy-based token selection across three reasoning domains and various model sizes, suggesting that GMTS provides a more fine-grained estimate of token contribution for RLVR training. --- ### REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation Authors: Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30627v1 As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token prediction supervises what follows a context but leaves the intermediate reasoning behind that continuation implicit. We introduce \textbf{REER-PT}, a scalable framework that extends Reverse-Engineered Reasoning (REER) to raw pre-training data. REER-PT identifies continuations that are difficult to predict but can still be inferred from the preceding context, and inserts concise reasoning annotations that reconstruct the missing connection between context and continuation. Candidate annotations are generated and refined offline, with perplexity serving as the optimization signal. Constraints on length and target leakage filter out unhelpful or trivial annotations. This sparse transformation preserves the source text and remains compatible with standard next-token prediction, avoiding online reasoning rollouts during pre-training. We apply REER-PT to transform a source pre-training corpus into an augmented one. Across augmented-data, original-token, and selected-continuation comparisons, perplexity reductions range from 0.42 to 7.29, and only about 0.05\% of annotation 13-grams appear verbatim in the source text. We then train two 680M-parameter models with the same architecture and training configuration on the source and augmented corpora, respectively. The augmented-data model gains up to 2.07 percentage points on several knowledge and reasoning benchmarks. Together, the perplexity analysis indicates improved continuation predictability, while the controlled pre-training experiments suggest that this augmentation can improve model performance without changing the standard pre-training objective. --- ### Cost-efficient Active Learning for Referring Image Segmentation and Grounding Authors: Junbeom Hong, Seonghoon Yu, Hyung Rok Jung, Sundong Kim, Jeany Son Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30621v2 Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regions from visually similar ones. We tackle this by formulating active learning (AL) for VG under the realistic setting where only raw images are available without accompanying text. Since ground-truth text is unavailable, sample selection must estimate which images contain ambiguous regions that would require discriminative referring expressions. To address this, we generate auxiliary region-text pairs using foundation models, and introduce Referred Region Ambiguity, a new acquisition function that measures whether the model's confidence collapses onto a single region or disperses across multiple candidates. It allows our method to prioritize images with strong cross-region competition, which are more informative due to their visual ambiguity. We also design a referring-expression annotation interface that helps annotators quickly focus on writing discriminative language with a few clicks. Experiments on RIS and REC benchmarks show that our AL framework consistently outperforms several AL baselines, while a user study shows up to 1.6X faster description labeling of ours. --- ### Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text Authors: Minkyung Cho, Jihyo Kim, SeungWoo Song, Junghun Yuk, Minjoon Kee, Hoyun Song, KyungTae Lim Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30619v1 Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such mechanisms can be exploited to inject targeted social biases into aligned models through semantically benign synthetic data. We construct a pipeline in which a misaligned teacher model generates filtered synthetic datasets across domains such as creative writing and code generation, which are then used to fine-tune aligned student models. Our experiments show that benign-looking synthetic data can act as a covert channel for transmitting targeted biases while largely preserving the student model's general task capabilities. These results reveal a previously underexplored security risk in synthetic data-driven LLM training pipelines and highlight the need for improved safeguards. As one possible step toward this goal, we suggest that log-linearity-based scoring may provide a useful signal for screening seemingly benign synthetic data. --- ### AQ3D: Adaptive Query Transformer for 3D Instance Segmentation Authors: Keno Moenck, Thorsten Schüppstuhl Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30618v1 Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary widely in spatial extent and object count, so a fixed query set over-initializes small scenes and under-initializes large ones, while learned absolute and relative encodings are bound to the training scenes' extents and can saturate. We present AQ3D, which is designed to handle scenes of various sizes during training and inference. Queries are instantiated at a fixed ratio of the scene's superpoints, forming an overcomplete set whose background rejection is entirely left to the decoder. Positional information is encoded using 3D RoPE over quantized metric coordinates, replacing learned bounded lookup tables of prior decoders. Further, we improve the decoder itself by using attribution-based superpoint pooling, a mask refinement branch, and a cosine classifier for background rejection. Experiments show our method sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation. Code is available at \href{https://github.com/kenomo/aq3d}{github.com/kenomo/aq3d}. --- ### RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias Authors: Yihe Sun, Ziyu Lu, Kaihua Tang, Xian-Sheng Hua Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30617v1 Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. However, existing image-to-CAD methods are developed predominantly on synthetic renderings and face two coupled obstacles: a substantial appearance domain gap between synthetic and real images, and a previously overlooked parameter bias in widely used CAD data. We show that the local normalization adopted by DeepCAD concentrates several geometric parameters around a few discrete values while encoding substantial information in a single scale factor. Consequently, a model can achieve deceptively high parameter accuracy by exploiting these frequent values rather than inferring geometry from the input image. In this paper, we propose RealCAD, a unified framework that addresses these limitations at the representation, image, and feature levels. At the representation level, we redistribute scale information to the corresponding geometric parameters, producing less concentrated parameter distributions in a shared scale space. At the image level, geometry-constrained translation converts synthetic renderings toward the real-image domain while conditioning on object contours. At the feature level, a multi-positive contrastive objective aligns representations of the same CAD model across viewpoints and image domains, enabling CAD sequence prediction from each individual view. We further introduce OpenRealCAD, comprising four-view photographs of 392 3D-printed objects paired with ground-truth command sequences. Experiments show that the revised representation substantially reduces the accuracy attainable from parameter-frequency priors, making parameter accuracy a more reliable measure of image-conditioned geometric inference. RealCAD further improves real-domain command and parameter accuracy, while retaining competitive synthetic-domain performance. ---