# Research Papers — 2026-08 · bundle page 7 of 240 > Full-text markdown of papers #301–350 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/7 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/6.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/8.md) ### VCAR: Training-Free 3DGS Segmentation via View Completeness and Axis-Aware Boundary Refinement Authors: Kun Cao, Di Wang, Haibin Zhu, Haozhi Huang, Xu Wang, Zheng Shi, Guanghua Yang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30870v1 Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature distillation, which incurs substantial per-scene training overhead and often yields blurred segmentation boundaries. We identify that these boundary artifacts are driven in part by insufficient viewpoint coverage and boundary overflow of anisotropic Gaussian primitives. To address these challenges, we propose VCAR, a training-free coarse-to-fine segmentation strategy based on View Completeness and Axis-aware Boundary Refinement. In the coarse stage, a visibility-based weighted multi-view voting scheme rapidly localizes the target. In the fine stage, an object-centric sphere derived from the coarse result generates supplementary viewpoints via Spherical Spiral Sampling (SSS), allowing multi-view voting on the augmented views to precisely refine object boundaries and suppress irrelevant 3D Gaussians. Moreover, we introduce Axis-aware Boundary Refinement (ABR) to mitigate artifacts from anisotropic primitives. By decomposing the projected 2D covariance into per-axis contributions, ABR identifies the dominant axis responsible for boundary leakage and applies targeted anisotropic compression exclusively along that axis. Extensive experiments on NVOS and LERF demonstrate that VCAR achieves state-of-the-art segmentation accuracy and efficiency without training. Our code is available at https://github.com/DDKK0526/VCAR. --- ### Exponential random graph models with soft clique constraints Authors: Yasmin Tousinejad, Vera Koponen Published: 2026-08-31 Categories: math.CO, cs.AI, math.PR arXiv: https://arxiv.org/abs/2608.30869v1 Let $r\geq3$ be fixed, and let $\mathbf{G}_n$ be the set of all simple graphs with vertex set $(n)=\{1,\ldots,n\}$. We consider an exponential random graph model which gives higher probability to $G \in \mathbf{G}_n$ than to $H \in \mathbf{G}_n$ if $G$ has fewer $r$-cliques than $H$. But all graphs in $\mathbf{G}_n$ have positive probability. The degree to which graphs with fewer $r$-cliques are given higher probability is determined by a positive weight $w$. We prove that, asymptotically almost surely as $n \to \infty$, a random graph from $\mathbf{G}_n$ has a vertex partition into $r-1$ parts of roughly equal size, the density of edges between the parts is close to $1/2$, and for every $\varepsilon > 0$ the density of edges within any part is less than $\varepsilon$. The asymptotic structural properties are independent of the weight $w$ as long as it is positive. We also extend the result to the context of several clique sizes, each one with its own weight. --- ### Beyond Good Intentions: When Does the Framing of Multilingual and Low-Resource NLP Research Become a Caricature? Authors: Nedjma Ousidhoum, Noopur Zambare, Mohamed Abdalla Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30866v1 Building language technologies and conducting NLP research for low-resource languages---particularly when led by native speakers or involving participatory research practices---are often framed as means of addressing inequality, serving local communities, and, at times, contributing to *decolonisation*. In this paper, we examine recently published NLP and ML papers, focusing on the narratives used to characterise multilinguality, low-resource languages, and underrepresented cultures. We propose a framework for analysing research framings and identify recurring rhetorical patterns that may hinder accountability and constrain equitable knowledge production for---and by---underserved communities. We further assess the evidential basis of assertions regarding community benefit and find that such statements are often weakly supported or left unsubstantiated. Although community ownership and participation are frequently presented as key objectives, our analysis, supported by statistics from the ACL Anthology, suggests that research outputs more often prioritise resource creation and benchmarking---important but distinct goals---over evidence of broader structural change. We conclude by offering practical recommendations to help authors, reviewers, and readers critically assess these assertions and avoid potentially misleading framings. --- ### Predicting Residential Rents in Dakar Using Machine Learning Authors: Amadou Tidiane Kassa Diallo Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30865v1 Dakar's residential rental market remains poorly documented despite its economic and social importance: 54.4% of households are renters, compared to 23.3% nationally. This study develops a complete machine learning pipeline to predict residential rents in Dakar, from data collection to model interpretation. An original dataset of 1,507 rental listings was built through systematic web scraping and a documented cleaning pipeline, then enriched with four purpose-built features, including a luxury score and a keyword-based quality score. Five models were compared: linear regression, Random Forest (baseline), XGBoost, and LightGBM optimized through Bayesian optimization with Optuna, using leakage-free KFold target encoding for location. The optimized XGBoost model achieved the best performance with an $R^2$ of 0.847, an MAE of 210,902 XOF, and an RMSE of 324,195 XOF. Feature importance was assessed using native XGBoost gain and SHAP values, revealing a substantial difference in the ranking of location, which appears as a minor predictor by gain but as the second most influential variable by SHAP. This result carries methodological implications for hedonic studies using target-encoded categorical variables. This study provides an interpretable benchmark for Dakar's rental market and highlights several avenues for improvement, including the integration of geospatial features and conformal prediction. --- ### GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures Authors: Yanran Xu, Chuanhang Qiu, Yue Wang, Wenbo Wu, Zhaoxing Li Published: 2026-08-31 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2608.30858v1 Off-road navigation can fail when physical structures induce irrecoverable states such as high-centering or entrapment, requiring human interventions. Identifying these structures is crucial, yet challenging. Such failure events are rare and costly to collect, resulting in limited training data. Moreover, the collected data associate frames with outcomes, but do not indicate the visual cues responsible for the failure. Learning directly from these data can therefore exploit scenario-specific visual cues, leading to poor generalization. We propose \textbf{Geo-Anchored Fine-Tuning (GAFT)}, a parameter-efficient method that adapts a vision foundation model with a geometry-derived prior. It guides LoRA adaptation by aligning a spatial attention-rollout map with the geometry prior, while preserving pretrained representations. On an intervention-verified forest hazard benchmark, across ten independently trained adaptations, GAFT consistently outperforms frozen DINOv2 and supervised PEFT baselines, improving the repeated leave-one-scenario-out mean $F_2$ from 0.0607 to 0.3757 with statistical significance under paired analysis. Within these independently trained models, the best-performing GAFT model achieves a repeated-LOSO $F_2$ of 0.570. Code and benchmark: https://github.com/Xu-Yanran/geo_anchored_fine_tuning --- ### TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Mental Health Assessment in Older Adults with Mild Cognitive Impairment Authors: Merna Bibars, Bolaji Omofojoye, Allan I. Levey, Rachel Hershenberg, Gari D. Clifford, Hyeokhyen Kwon Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30857v1 Depression and anxiety in older adults with Mild Cognitive Impairment (MCI) are frequently underdiagnosed due to limited access to care. Multimodal analysis of remote clinical interviews is a scalable screening approach, but existing methods have three limitations. First, they do not correct temporal misalignment across multimodal features extracted at different resolutions, inducing spurious cross-modal associations. Second, remote recordings exhibit uneven modality dropout, but missing values are often zero-filled, making them indistinguishable from valid near-zero measurements. Finally, they do not jointly attribute predictions to modalities, questions, and interview moments, limiting fine-grained clinical interpretation. We propose a Temporally-Aligned, Missingness-Aware, Interpretable (TAMI) multimodal fusion framework. TAMI aligns speech, language, facial, and physiological features within question-answer segments on a shared timeline, encodes modality-level missingness over time, and conditions fusion on question context. In interviews with 49 older adults with MCI, TAMI achieved area under the receiver operating characteristic curve (AUROC) scores of 0.68 (depression) and 0.69 (anxiety). Fine-grained temporal alignment of multimodal features produced the largest performance gain ($Δ{\geq}0.1$). Multi-level interpretability analysis revealed that depression classification relied on eyegaze and open-ended questions, while anxiety classification depended on eyegaze and head pose, with attribution uniformly distributed across questions. Using only responses to the open-ended questions (5.1min), the depression model achieved an AUROC score of 0.67, which was not significantly different from using the full interview (19min) ($p>0.05$). Our findings support designing interview protocols centered on open-ended questions for depression screening in older adults with MCI. --- ### You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals Authors: Ruoxuan Li, Pinqiao Wang, Sheng Li, Cameron Robert Jones Published: 2026-08-31 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2608.30856v1 Refusals are often treated as face-threatening acts in pragmatics because they can challenge the requester's socially claimed self-image. Large language models (LLMs) are increasingly trained to refuse unsafe and inappropriate requests, and these refusals may harm users when models fail to manage this interactional cost properly. While existing work has mainly approached LLM non-compliance as a safety-alignment outcome, it does not provide a way to evaluate whether LLMs refuse appropriately across different harmful contexts. To study this question, we propose (to our knowledge) the first taxonomy of LLM refusals that is grounded in pragmatic theory. Applying this taxonomy to responses from 16 modern LLMs across 14 harm categories, we find that although models differ in how they refuse, their refusals are overall explicit and strongly morally evaluative, with interactional repair occurring mainly through offering or providing safer alternatives instead of interpersonal facework. This pattern is especially consequential in sensitive harm contexts, where overuse of negative framing may make users feel shamed or provoked, undermining the purpose of safe non-compliance. We therefore call for alignment evaluation that considers not only whether models refuse harmful requests, but also whether they refuse in ways that are contextually adaptive and socially accountable for the interactional consequences of saying no. --- ### Linguistic Distance Segregates Latent Representations in Automatic Speech Recognition Systems Authors: Ting-Hui Cheng, Line Katrine Harder Clemmensen, Sneha Das Published: 2026-08-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30853v1 While automatic speech recognition (ASR) models have achieved remarkable improvements in recent years, performance disparities persist across different speaker populations. One such disparity is for speakers whose first languages (L1) are from families distant from English. This paper investigates the relationship between first language background and English ASR performance. Through empirical analysis, we observe that the correlation between speakers' L1 distance and ASR error rates yields a systematic effect on English Speech, with its strength varying across datasets and models. This association is statistically significant in a follow-up analysis accounting for dataset-level variation in Tweedie mixed-effects models ($p<0.001$ across evaluated models). In addition, analysis of the latent space reveals a L1-based spatial segregation across deeper acoustic layers in the majority of evaluated architectures --- ### VFR-Audit: Verdict-Level Reliability for Fairness Audits in Hospital Length-of-Stay Prediction Authors: Md Jannatul Rakib Joy, Viet Vo, Caslon Chua Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30846v1 Fairness audits in clinical Artificial Intelligence convert continuous fairness metrics into binary pass-or-fail verdicts against operational thresholds, where hospital governance boards, payers, and regulators act on the resulting verdicts. Such audits are repeated over time and across hospital sites, thus the same verdict can flip between pass and fail across audits. Existing uncertainty methods such as Bayesian posteriors, bootstrap confidence intervals, and permutation tests address verdict instability only at the continuous-metric level. Converting metric-level uncertainty into a verdict-stability claim remains a manual step that scales poorly across the (model, metric, attribute) cells an audit covers. Existing uncertainty methods also leave open whether bias-mitigation steps, such as reweighing or per-group threshold shifts, yield a stable passing verdict at the cost of model discrimination measured as AUROC or AUPRC.To address this verdict-stability gap, we propose VFR-Audit, a framework built around the Verdict Flip Rate (VFR), a scalar bounded between 0 and 0.5 that measures the probability of verdict reversal under stratified bootstrap resampling. VFR-Audit reports VFR alongside three reliability axes, namely within-cohort resampling stability, audit-size sensitivity, and cross-hospital verdict agreement via Fleiss' kappa. --- ### Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipeline for AutoPET V Authors: Xinglong Liang, Chunyao Lu, Tianyu Zhang, Jiaju Huang, Tao Tan, Yunchao Yin, Lishan Cai Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30844v1 Interactive lesion segmentation in whole-body PET/CT requires a model to provide a strong initial prediction while also responding efficiently to sparse corrective scribbles during inference. This setting is particularly challenging because tracer distributions, physiological uptake patterns, lesion appearance, and acquisition characteristics differ substantially between FDG and PSMA studies. We present TRIAGE, Tracer-aware Refinement via Interactive Anatomy-Guided sEgmentation. The core backbone is a 3D STU-Net initialized through masked autoencoding pre-training with an asynchronous masking strategy, aiming to learn transferable anatomical and cross-modal representations before task-specific fine-tuning. In parallel, we train an auxiliary organ segmentation model whose predictions provide explicit anatomical context and help distinguish physiological uptake from malignant lesions. A dedicated tracer classifier first routes each study to an FDG- or PSMA-specific branch. Within each branch, a first-stage segmentation model consumes CT, PET, and organ context to generate an initial lesion mask. The initial prediction is then combined with cumulative foreground/background scribbles and refined by a second interactive segmentation network. The FDG and PSMA branches share the same overall processing pipeline but are trained independently to account for tracer-specific appearance and error modes. We additionally employ curriculum-style training and model ensembling to improve robustness across interaction steps and heterogeneous cohorts. Experiments are conducted using the official AutoPET V data and ten-fold split; quantitative results, ablations, and final test-set performance are left as placeholders to be completed after the challenge evaluation. Code: https://github.com/Liiiii2101/AUTOPET2026-MEDAI. --- ### Thesis Proposal: Toward a Human-Centered and Perspective-Aware Framework for Reproducible ML Evaluation and AI Alignment Authors: Deepak Pandita, Christopher M. Homan Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30842v1 Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often disagree with each other and sometimes with themselves over time. It is essential to take disagreement into account when building human-centered AI systems, especially in domains where it is prevalent, such as AI safety, content moderation, or sentiment analysis. Disagreement often arises from subjective human opinion and can vary with one's identity, beliefs, and social environment. Despite this, current LLM evaluation approaches frequently rely on aggregating labels (often via plurality voting) to represent consensus, thereby obscuring minority perspectives. By failing to account for human disagreement, these evaluation methods contribute to the reproducibility crisis in AI. Human feedback is also crucial for ensuring that AI systems align with human values. For these systems to be trustworthy, it is critical to ensure that they reflect diverse human values and perspectives. In this thesis proposal, we present a human-centered and perspective-aware framework for reproducible ML evaluation and AI alignment. --- ### HSRM: Hidden-State Reward Models for Test-Time Verification Authors: Xianzhi Li, Xiaodan Zhu Published: 2026-08-31 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.30841v1 Large language models can often generate plausible mathematical reasoning traces, but reliably identifying the correct solution among multiple candidates remains a key challenge. Existing test-time reasoning pipelines typically rely on text-based verifiers that re-read each generated solution, making verification an expensive component of inference. Prior work has shown, however, that LLMs often encode correctness-related signals in their internal representations, including awareness of when their own answers are likely to be wrong. Building on this observation, we introduce HSRM, a lightweight hidden-state reward model that verifies candidate solutions by directly reading the generator's internal representations rather than re-processing its text. HSRM extracts hidden states from a frozen generator at reasoning-step boundaries and uses a small Transformer encoder to rank candidates. It is trained from self-generated trajectories with outcome labels, requiring neither human-written process supervision nor a large pretrained verifier. Across four mathematical reasoning benchmarks, HSRM matches or outperforms a 55M-parameter text-only energy verifier in 15 of 16 generator--dataset settings while using only about 2M parameters, providing an efficient alternative to text-only verification by reusing representations already computed during generation. --- ### Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling Authors: Xiaopei Zhu, Siyuan Huang, Zhanhao Hu, Jianmin Li, Jun Zhu, Xiaolin Hu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30839v1 Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios. The design of the adversarial clothing is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling. We optimized the black patch layout pattern of 3D clothing based on the adversarial example technique and made physical adversarial clothing using the aerogel. The idea is to paste a set of square aerogel patches, which display black squares in thermal images, in the inner side of clothing at specific locations with specific orientations. To enhance realism, we propose a method to build infrared 3D models with real infrared photos and develop texture maps for 3D models to simulate varied infrared characteristics over time and location. In physical attacks, we achieved an attack success rate of 80.11\% indoors and 76.85\% outdoors against YOLOv9. In contrast, randomly placed patches yielded much lower success rates (26.53\% indoors and 23.03\% outdoors). The adversarial clothing also showed good transferability to unknown detectors with an ensemble attack method, demonstrating the effectiveness of our approach. --- ### Reliable Benchmarking of Artifact Detection in Computational Pathology: A Reproducibility and Uncertainty Analysis Authors: Konstantinos Moutselos, Ilias Maglogiannis Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30835v1 Background and Objective: Quality control is a prerequisite for whole-slide image analysis, yet the benchmarks on which quality-control methods are compared share four properties that make their reported differences hard to interpret: few independent slides, annotation concentrated in a minority of them, pooled ratio metrics with no closed-form standard error, and a single inherited train/test partition. We propose a reliability protocol for such benchmarks. Methods: The protocol quantifies four sources of variability - test-set sampling, training stochasticity, partition composition, and undocumented preprocessing - a claim is reportable only if it survives all four; three of the four cost minutes of compute. We apply it to an independent reconstruction of a published diffusion-based artifact detector, evaluated on the original 24-slide partition and against a supervised baseline. Results: The method's central mechanism reproduces: the auxiliary contrastive term improves pooled F1 from 0.673 to 0.688 and replicates under a second seed (+0.0156, p = 0.031; +0.0190, p = 0.005), although it acts on pen marking rather than the artifact types cited to motivate it. Its comparative claims do not: differences between design variants, and against the supervised baseline, fall inside the uncertainty of the evaluation. Four of 24 slides carry 70% of scored annotated pixels, giving an effective sample size of 6.2, and the inherited partition sits at the 7th percentile. An unreported tissue-restriction step excludes 41.4% of out-of-focus annotation against 2.6% of air bubble; such a gate is confounded with blur by construction. Conclusions: Small-cohort benchmarks support far weaker conclusions than current reporting implies. The four checks are cheap enough to accompany any evaluation on such a resource and separate reproducible effects from differences the evaluation cannot resolve. --- ### Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments Authors: Ivan Porupski, Nikola Ljubešić Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30828v1 We present three large-scale studies of spoken parliamentary speech across four Slavic languages (Croatian, Czech, Polish, Serbian), drawing on over 6,000 hours from the ParlaSpeech 3.0 corpus. The first study examines how utterance-level sentiment shapes acoustic realisation: negative speech is consistently produced with higher pitch, greater intensity, and faster rate across all four parliaments, with a secondary arousal-driven upturn at the most positive extreme. The second study models filled pause frequency using negative binomial GEE, finding that speech rate, age, and sentiment are robust cross-lingual predictors, while gender effects reverse between South Slavic (men produce fewer filled pauses) and West Slavic parliaments (no gender difference) - a pattern invisible to single-language designs. The third study investigates primary stress variation in Croatian, showing that speaker-level preferences for early versus late stress cohere across verbs, adjectives, and nouns but decouple for adverbs and proper nouns. We conclude with a research agenda spanning corpus phonetics, disfluency modelling, and political rhetoric. --- ### Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels Authors: Elena Merdjanovska, Jonas Golde, Alan Akbik Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30827v1 Large language models are increasingly used to annotate datasets for training smaller, task-specialized models such as named entity recognition. While this method yields effective models, it assumes that the synthetic dataset is correctly annotated. In this work, we find that (i) current fine-tuning processes simply ignore LLM-introduced annotation noise, resulting in degraded performance and (ii) existing noise-robust losses are not transferable to sequence labeling because annotation noise in named entity recognition is heterogeneous: for example, missing mentions and type errors affect the training signal in different ways. Treating all noisy tokens equally in noise-robust losses and applying a single reweighing criterion for all may therefore remove useful supervision or reinforce incorrect labels. To address this limitation, we propose error-type-aware loss reweighting for NER, which introduces separate reweighing rules for different types of potentially erroneous tokens. Our approach is simple and efficient, does not require additional training resources, and improves F1 by 0.8 - 2.0 percentage points on dataset-level average for noise levels between 15% and 40%, with a maximum improvement of 4.6 percentage points with 24.1% noise on Wikigold. --- ### Whole-Body MRI Classification via Prompt-Based Clinical Conditioning Authors: Laura Daza, Marta Hasny, Cristina González, Julia A. Schnabel Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30824v1 Combining whole-body magnetic resonance imaging (WB-MRI) with clinical variables has the potential to improve systemic disease diagnosis by leveraging complementary sources of patient information. However, structured clinical variables are often incomplete or missing, limiting the applicability of conventional multimodal fusion methods that assume fixed inputs. In this work, we propose TACTIC (Tabular-Attribute Conditioned Transformer for Image Classification), a prompt-based multimodal framework that integrates WB-MRI and structured clinical data through conditional visual feature learning. By encoding clinical attributes as prompts, TACTIC supports an arbitrary number of tabular inputs and naturally handles missing data without requiring imputation or fixed input structures. We evaluate TACTIC on five WB-MRI classification tasks spanning systemic and oncologic applications, including diabetes, chronic obstructive pulmonary disease (COPD), breast cancer, prostate cancer, and metastasis diagnosis. Across all tasks, TACTIC consistently improves performance over image-only baselines when clinical information is available while maintaining strong predictive capability under incomplete tabular inputs. Our results demonstrate the effectiveness of prompt-based models as a flexible approach for improving WB-MRI analysis using clinical context. The model weights and code are available at https://github.com/lauradaza/TACTIC --- ### Vocal Music under Phoneme-Conditional Analysis Authors: Hayoon Kim, Kyogu Lee Published: 2026-08-31 Categories: cs.SD, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2608.30823v1 The vocal music of each language carries a distinctive sonic identity, even without instrumental accompaniment. We ask whether these differences are measurable and traceable to specific phonemes. To tackle this question, we introduce phoneme-conditional analysis, which isolates the acoustic effect of typologically distinctive phonemes by comparing marker syllables against matched non-marker controls within the same song, holding singer, melody, and genre constant. Across nine typologically diverse languages and thousands of songs, we measure effects along five acoustic dimensions. Song-level profiles built from these effects identify the language of an unaccompanied vocal at 85.5% balanced accuracy in a nine-way classification with folds grouped by artist; whether the separability arises by accumulation of the phoneme-local effects themselves is left open. Our findings suggest that phonological structure leaves systematic and measurable traces in how each language is sung. --- ### Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling Authors: Minghan Qin, Yuang Wang, Xiuyu Yang, Yushi Long, Yujian Zhang, Ruihuan Wang, Kai Ye, Yangang Zhang, Hang Li Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30821v1 Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observed, giving robot simulation and embodied AI a simulation-ready replica of the real environment whose objects can be manipulated individually. Existing pipelines decompose the task into three steps---parse the observations into instances, generate an asset for each, and place each asset back---but every step presumes an input that a cluttered capture rarely provides: accurate instance geometry, unoccluded views, and assets that accurately match the observations. We propose Lucida, which keeps this order but redistributes the requirements, so each step consumes only what a real capture reliably provides and precision is reached at the end of the pipeline rather than demanded at its start. Lucida parses the video into a scene graph whose nodes carry per-instance multi-view evidence, generates a complete asset for each instance from its evidence, and places assets with GizmoAct, a VLM policy that casts placement as multi-turn GUI interaction, manipulating the object's gizmo in a closed loop and deciding itself when alignment is reached. Across scene-level 3D object detection, object pose estimation, and scene reconstruction, Lucida improves mAP over Boxer by 69% on R2S-Scene, raises ADD-SB@0.05 from 57.8% to 83.4% on CA-1M, and increases scene F-Score from 0.794 for SAM3D to 0.924. --- ### RealOOB: A Definition-Consistent Real-World Oriented Occlusion Boundary Benchmark Authors: Lintao Xu, Yinghao Wang, Chenchu Rong, Xuchong Qiu, Chaohui Wang Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30820v1 Occlusion boundaries (OBs) are pixel-level image boundaries corresponding to surface visibility discontinuities caused by occlusion. Through precise boundary localisation and occlusion orientation, OBs encode local surface layout and depth ordering, providing geometry-driven mid-level cues for scene understanding. However, progress in pixel-level OB estimation has been limited by fragmented supervision: Existing benchmarks often suffer from limited coverage, category-specific designs, missing self-occlusion annotations, or inconsistent annotation definitions. Meanwhile, modern edge detectors and monocular depth estimators have become strong boundary and geometry predictors, yet their relationship to definition-consistent OBs remains underexplored. We introduce RealOOB, a carefully annotated real-world benchmark with 4.26M definition-consistent, geometry-grounded OB labels covering both inter-object and self-occlusion boundaries, together with validity-aware occlusion-orientation maps that restrict supervision to pixels whose cross-boundary depth ordering is reliably measurable. Based on RealOOB, we evaluate forty OB estimators and edge detectors alongside six monocular depth estimators. Our evaluation reveals a clear gap in occlusion reasoning: modern edge detectors perform competitively with OB methods in localisation, whereas orientation prediction remains challenging for all evaluated methods. Meanwhile, even strong depth estimators often fail to exhibit measurable geometry at true OBs. We believe RealOOB provides a strong reference benchmark for the OB estimation community and a real-world testbed for assessing depth discontinuities and geometry fidelity in broader low-level vision tasks. Dataset and code will be released. --- ### What Emerges and What Breaks in Self-Play Driving Authors: Laur Sisask, Ardi Tampuu, Tambet Matiisen Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30819v1 Training autonomous driving policies through pure self-play has recently shown promising results. Following Gigaflow and Puffer- Drive, we train driving policies in a similar self-play fashion, but extend the models from MLPs to Transformers and train on the high-definition map of a real city, where we ultimately aim to deploy them. On the CARLA and Waymax benchmarks, our policies fall short of Gigaflow, and we trace the gap to specific failure modes, including reward hacking at traffic lights and a missing incentive to stop at stop signs. We further analyze which traffic rules emerge from self-play and how closely they match human driving, and we confirm that reward conditioning yields the intended diversity of driving behaviors. A demonstration of a trained policy is available at https://laursisask-ut.github.io/eccvdemo. --- ### A Composition-Aware Pretraining Framework for Geospatial Foundation Models Authors: Aryan Kashyap Naveen, Abhishek Srinivas, Pranav Moothedath, Shrutilipi Bhattacharjee Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30817v1 Geospatial foundation models have emerged as state-of-the-art methods for downstream Earth observation tasks. However, existing pretraining methodologies process imagery through a single-concept lens, failing to capture the highly compositional nature of complex satellite scenes. We propose a composition-aware pretraining framework that explicitly encodes fractional land-cover mixtures. Each satellite image cell is mapped to a histogram representing its fractional land-cover distribution, which we term the "composition target". These targets serve as the primary prediction objective and are distilled into the backbone using Earth Mover's Distance. Experimental evaluation shows that composition-aware pretraining yields substantial gains on region-level understanding tasks requiring semantic similarity judgment, including zero-shot image retrieval and scene classification, while remaining competitive on tasks requiring fine-grained spatial precision, such as segmentation and object detection. With a 36.8M-parameter backbone, our framework outperforms SatMAE and Prithvi-EO-2.0, which contain 303M and 600M parameters, respectively, in most retrieval and scene classification settings. On the fine-grained ForestNet-12 dataset, a rigorous testbed for compositional discrimination, our method boosts baseline mAP@10 from 0.279 to 0.434, a 55.6% relative improvement, providing direct evidence for the effectiveness of explicit composition modeling. The code implementation can be found at https://github.com/05kashyap/GFM_Composition_Pretraining --- ### TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories Authors: Daniel Agyei Asante, Yang Li Published: 2026-08-31 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.30811v2 Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment important evidence, require additional training or alignment, and often depend on the target model for effective compression. We introduce TopoCompress, a training-free and model-agnostic framework that compresses long contexts by selecting coherent semantic spans. TopoCompress first scores each span using dense and lexical query relevance together with semantic acceleration. It then constructs a hybrid graph that connects spans based on semantic similarity and sequential adjacency, and propagates the query-guided relevance scores over the graph. Across five long-context tasks-HotpotQA, 2WikiMQA, MuSiQue, Qasper, and MultiFieldQA-en-TopoCompress consistently outperforms strong compression baselines. Notably, TopoCompress achieves performance comparable to the strongest baseline while using a 4x smaller compression budget, and provides a 1.41x smaller compression time over the fastest baseline. --- ### Aggregate Disambiguation Systems Authors: José María Lago, Albert Castellana, Edgars Nemše Published: 2026-08-31 Categories: stat.ME, cs.AI arXiv: https://arxiv.org/abs/2608.30805v1 Natural-language tasks can elicit different verdicts from protocol-following evaluators that receive the same declared information. We study aggregate disambiguation systems (ADSs). Given a task and a candidate solution, each evaluator casts a binary vote on whether the solution should be accepted, and the system aggregates the votes of a finite panel. The target is protocol reproducibility relative to an explicitly declared evaluator reference, not semantic truth. We separate fixed finite censuses, probabilistic evaluator populations, and growing-census limits, since their endpoint laws and guarantees are not interchangeable. In the population setting, we use finite samples to estimate how often a finite panel reaches the same decision as the declared evaluator population. We provide a lower confidence bound on the fraction of candidate solutions for which the disagreement probability is at most a chosen tolerance. The calculation accounts separately for sampling candidate solutions and sampling evaluators. The construction permits arbitrary dependence among columns induced by shared evaluator rows and uses exact binomial intervals at the evaluator layer and an exact one-sided binomial inversion at the generator layer. Simulations check the implementation against known population coverages and expose power limitations. --- ### Geometric Attractor Monitoring: A Robust and Frugal Framework for Multi-modal Industrial Robotic Cycles Authors: Martin Bonsergent-Brachet, Jesse Read, Dany Abboud Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30804v1 Monitoring the health of heterogeneous industrial robot fleets is severely challenged by the multi-modal nature of their operational cycles and a persistent scarcity of run-to-failure data. Standard data-driven approaches, particularly deep learning architectures relying on sequential reconstruction, often struggle in this specific setting; they tend to over-smooth complex dynamics, masking early signs of degradation. To address these industrial constraints, we reframe the monitoring problem through a framework based on Phase Space Reconstruction (PSR). Instead of predicting temporal sequences, this framework transforms univariate sensor data into a geometric attractor, explicitly unfolding the mechanical states independently of their temporal occurrence. By evaluating various anomaly scoring techniques within this space, we demonstrate that discrete support estimation provides an effective and computationally frugal Health Indicator (HI). Validated on a real-world dataset of 21 heterogeneous robots over three years and a synthetic Langevin system, our approach outperforms standard deep learning baselines. We show that aligning the algorithmic bias with the geometric properties of the target system yields a pragmatic, traceable and easily deployable approach perfectly tailored to the realities of industrial constraints. --- ### Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions Authors: Rodrigo Almeida, Noelia Otero, Jost Arndt, Simon Baur, Wojciech Samek, Jackie Ma Published: 2026-08-31 Categories: physics.ao-ph, cs.LG arXiv: https://arxiv.org/abs/2608.30795v1 End-to-end weather forecasting systems produce skillful global gridded and station forecasts directly from raw Earth observations, replacing the numerical weather prediction pipeline, including data assimilation, at a fraction of its cost. These systems are deterministic and issue no uncertainty. Here we render the Aardvark Weather model probabilistic by attaching one stochastic mechanism to each component: learned, input-dependent noise at the observation encoder, capturing aleatoric uncertainty inherited from the observing system, and Monte Carlo dropout in the processor, capturing epistemic uncertainty in the learned dynamics. The resulting nested ensemble attributes forecast spread to the two sources through a law-of-total-variance decomposition, cross-checked by withholding observation streams. Probabilistic finetuning significantly improves the mean forecast, by 4.2% on average across variables and lead times. The ensemble is calibrated against ERA5 through the medium range (spread-skill ratio 0.98), keeps station RMSE within 2.4% of the deterministic model while beating it in CRPS at every lead time, and trails the operational ECMWF ensemble. The encoder branch behaves as observation-driven uncertainty. Component-attributed uncertainty makes end-to-end forecasts more transparent, a step toward observation-driven digital twins of the atmosphere. --- ### Conjoint Audio-to-Spikes Encoding and Processing for Efficient Neuromorphic Speech Recognition Authors: Valentin M. Meunier, Amélie Gruel, Pierre Lewden, Adrien F. Vincent, Sylvain Saïghi Published: 2026-08-31 Categories: cs.NE, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2608.30792v1 Obtaining data from neuromorphic sensors and processing it with Spiking Neural Networks is a promising solution to lower the energy cost of artificial intelligence. The current rarity of natively neuromorphic datasets promotes the development of software tools to translate input sensory data into spikes. However, highly bio-mimetic simulators can be challenging to implement on digital hardware. In this work, we evaluate the neuromorphic encoding and subsequent classification of audio into spikes using a non-learnable, high-level, programmable encoder targeting hardware implementation on FPGA. We quantify the pipeline's efficiency with hardware-agnostic metrics based on the quantitative spiking activity. Our study focuses on the simultaneous optimisation of encoder and classifier: the first provides efficient and informative data so that the latter achieves a better performance with an overall lower energy cost at learning and inference. This work introduces the first end-to-end neuromorphic spike-encoding and evaluation of the TIMIT dataset. Our simple feedforward network reaches a classification accuracy of 99.77% on a spike-encoded Heidelberg Digits, overcoming the neuromorphic state of the art on this benchmark dataset. --- ### Camera trap classification with deep learning under ground truth uncertainty Authors: Leonard Hockerts, Peter S. Stewart, Sarthak Arora, Tiffany J. Vlaar Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30789v1 Supervised deep learning methods enable the rapid processing of ecological image data, but depend on a costly annotation process. Consequently, training labels are commonly derived from volunteer citizen science projects. However, disagreement among volunteers introduces uncertainty in the "ground truth" data that are assumed to be correct for model training and validation. Using two datasets containing camera trap images with associated volunteer and expert classifications, we investigated the effects of training under higher ground truth uncertainty. We observed improved overall test accuracy, particularly for images that were more difficult for volunteers. Species-level accuracy also generally improved, but generalisation to a different dataset did not. The benefits of ground truth uncertainty were enhanced by pre-training on ImageNet. Pre-training also reduced the number of training epochs required; further reductions in computational cost, but not gains in accuracy, resulted from additional pre-training on other camera trap images. With unbalanced training data, we still observed a clear benefit of increased ground truth uncertainty for overall accuracy, especially on difficult images. Class imbalance improved accuracy for common species, reduced rare species accuracy, and changed patterns of misclassification to more closely resemble mistakes made by volunteers. Our findings have implications for applying deep learning across ecological image types with multiple labels. Practitioners can improve accuracy, especially on difficult examples, by including moderate levels of label disagreement during training and using models pre-trained on general image data. In addition to improving the use of citizen science-derived labels in model training, our study suggests avenues for more effectively integrating human and deep learning classifications in combined workflows. (abridged) --- ### SkillZip Pro: Execution-Aware Dynamic Compression of Progressively Loaded Skills for Self-Evolving Agents Authors: Xiaofan Bai, Chao Liu, Hongqiang Lin, Di Wu, Mingli Song, Xuan Jin, Xipeng Cao, Yuhong Li Published: 2026-08-31 Categories: cs.AI arXiv: https://arxiv.org/abs/2608.30785v1 Production agent skills are directory bundles, not isolated prompts. The root is loaded at activation; references, schemas, scripts, assets, and nested subskills are loaded only when an execution path needs them. Compressing only the root misses most deployment cost and may move branch-specific details into the always-loaded context. Flattening instead destroys progressive-loading boundaries. We introduce \method, an evaluation-free compressor for complete, progressively loaded skill bundles. It leaves the agent harness unchanged and emits an ordinary directory. The method combines two safeguards. First, it compresses \emph{across files}, removing content from a reference or subskill when the root or a declared environment contract already provides it. Second, it preserves routing, so every required file and directly callable entry remains reachable after rewriting. Users can configure \method along two independent axes. \emph{One-Shot} mode rebuilds the full bundle; \emph{Continual} mode reuses state and applies Zip-on-Write after each evolution patch. \emph{Persistent} compression rewrites the shipped bundle to reduce storage and runtime context. \emph{Transient} compression keeps that bundle byte-identical and builds a task-specific view, reducing only per-run context after build cost. Entry contracts mark private, public, and conditional resources; a multi-entry audit preserves standalone public subskills. On a production content-moderation skill evaluated by our industrial multi-round harness, \method removes \hl{38\%} of skill bundle tokens and \hl{10.4\%} of end-to-end per-run tokens with no quality loss, while an unprotected 71\% configuration loses up to 26 accuracy points to one-sided false positives. On a multi-entry bundle, \method effeciently reduces token cost while near-perfectly preserving every route and public entry. --- ### PixelIR: Fidelity-Perception Decoupling via Pixel-Space Image-Residual Flow Matching for Efficient One-Step Real-World Super-Resolution Authors: Bingtian Qiao, Yue Shi, Yong Guo, Wenjun Zhang, Jiezhang Cao Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30782v1 Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realistic details. However, existing Real-ISR methods largely optimize fidelity and perceptual quality within a shared network, causing the two objectives to interfere throughout training and making their balance difficult to control. Recent one-step methods reduce sampling steps, yet often inherit both this coupled optimization behavior and the expensive high-resolution backbone of their multi-step predecessors. We argue that efficient Real-ISR requires not only a shorter sampling trajectory, but also specialized modeling of faithful reconstruction and perceptual detail synthesis. Based on this insight, we propose PixelIR, a fidelity-perception decoupling framework built upon pixel-space image-residual flow matching. PixelIR first learns an image flow that maps the degraded observation to a faithful reconstruction. Then, a residual flow synthesizes the missing perceptual details from noise without repeatedly relearning or overwriting the complete restoration solution. We further distill the teacher into a deployment-oriented one-step student within a coarse-to-fine pyramid architecture. Extensive experiments show that PixelIR achieves leading PSNR, SSIM, and LPIPS on both RealSR and DRealSR. The final model completes pixel-space restoration in a single evaluation with only 32.9M parameters, 89.7G MACs, and 8.5ms latency, demonstrating a strong practical fidelity-perception-efficiency balance. --- ### Reciprocity Separates Gradient Flow from Rotation in Conservative Physical Learning Authors: Ruiwu Niu, Xiaowen Bi, Michaël Antonie van Wyk Published: 2026-08-31 Categories: cs.LG, nlin.AO arXiv: https://arxiv.org/abs/2608.30778v1 Physical learning lets a trainable material or network use its own physical response to carry error signals, reducing the need for a separately programmed backward computation. We ask what determines whether such a system follows conventional gradient descent or evolves along a genuinely different learning trajectory. Our canonical model is a directed layered transport network in which every node redistributes a fixed amount of flow, so learning preserves positivity and total mass. In this model, conservation constrains only the allowable learning directions. Within the matched response class studied here, adjoint matching gives the physical output response a symmetric form. Non-negative mode-wise feedback then produces a reciprocal closed-loop response and a reweighted gradient flow. Adding an antisymmetric boundary component makes the closed-loop response rotational: the learning path can turn while the error driving that update still decreases at that moment. Turning is not automatically beneficial. Its finite-step effect is set by local curvature, and its accumulated effect also depends on step selection and on the new states visited along the path. Numerical consistency checks reproduce the exact response structure, predict the sign of the local effect across new network families, and show how trajectory drift can negate a local advantage. These results separate the roles of conservation, reciprocity, and nonreciprocity in physical learning. --- ### TrainSDC: Characterizing and Mitigating Silent Data Corruption in Large Language Model Training Authors: Zhipeng Xia, Haotian Xu, Siyu Yun, Liqi Lin, Hu Liu, Yu Li, Cheng Zhuo Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30769v1 LLM training is increasingly vulnerable to silent data corruption (SDC), yet existing protection methods largely treat Transformer computations uniformly because their vulnerability remains poorly understood. We present the first systematic characterization of SDC vulnerability across major computation interfaces in both the forward and backward passes of Transformer training. Our analysis reveals two distinct error propagation mechanisms: forward-pass vulnerability is highly location dependent, with faults on the Q/K path producing persistent training deviations, whereas backward-pass vulnerability is largely governed by gradient exponent distributions rather than computation locations. Motivated by these observations, we propose TrainSDC, a characterization-guided protection framework consisting of Q/K-path recomputation, residual-gain monitoring, and exponent-aware gradient scaling. Experiments on Llama 3.2-1B and Qwen3-0.6B show that TrainSDC maintains training behavior close to fault-free execution under both sparse and dense fault injection while introducing only 1.65%-6.76% runtime overhead. --- ### CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy Authors: Zekang Yang, Jiamin Li, Zhenghua Li, Jiaqi Fan, Zengcai Guo, Xiaolin Hu Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30768v1 Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved encouraging results on local image blocks, it remains unclear whether such progress translates to reconstruction that is both structurally accurate and scalable to the whole-brain scale. We present CORAL, the first benchmark for structure-aware evaluation of automatic neuron reconstruction from light microscopy images at both local and whole-brain scales. Built on a high-quality whole-brain fMOST dataset with carefully curated annotations, CORAL establishes two progressive tasks: block-level reconstruction, which evaluates reconstruction methods under limited spatial context, and brain-wide reconstruction, which assesses complete neuron reconstruction at the whole-brain scale. To account for topological correctness beyond geometric distance similarity, we introduce a structure-aware metric based on fiber prediction. To further achieve complete neuron reconstruction across the entire brain, we develop a brain-wide neuron tracing framework that extends arbitrary local reconstruction methods to the whole-brain scale through an iterative local-to-global process. Using this benchmark, we provide the first structure-aware comparison of mainstream methods for local neuron reconstruction and further evaluate their performance in brain-wide reconstruction. Our results underscore the importance of structure-aware evaluation and the need for more robust methods for complete neuron reconstruction. --- ### T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler Authors: Yuanqiang Yu, Tianpei Yang, Yongliang Lv, Yan Zheng, Jianye Hao Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30765v1 Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to solve different tasks by sharing parameters across various tasks. However, these methods are faced with inter-task interference since what parameters should be shared across tasks is not addressed, dramatically reducing learning efficiency. To solve these problems, we propose a novel MTRL framework called Task-Specific feature Selector and Scheduler (T3S), which consists of two components: a feature selector and a task scheduler. Specifically, the feature selectors employ hypernetworks to construct task-specific soft masks, which can be applied by globally shared representation to construct task-specific features. The task scheduler selects tasks for learning through two metrics, where the selection probability is inversely proportional to task progress (e.g., success rate) and task learning speed. Experimental results show that T3S consistently outperforms the state-of-the-art MTRL algorithms on various robotics manipulation tasks. --- ### ChessQueries: Toward Better Chess Board Recognition Authors: Joël Seytre Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30762v1 Chess board recognition is the task of mapping the image of a chess board to the information of which piece is on which square. So far this task has two established benchmarks: ChessCog is synthetic, and ChessReD comes from smartphone pictures of a single chess board setup. We introduce ChessQueries, a new method combining a ViT encoder with a DETR-style decoder, which outperforms existing methods. On the ChessReD benchmark, we improve the state of the art from 15.3% to 99.2%, and demonstrate strong capabilities on out-of-distribution datasets. Our method saturates the task on the two datasets, with an average 0.01 wrong squares per board (vs. SotA: 3.4 / 0.15 respectively). We also share a new, harder public dataset, parsed from broadcasted top-level chess tournaments. Code, model weights and the SLCC data will be released. --- ### PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents Authors: Ziyi Bai, Siqi Li, Tinglei Huang, Börje F. Karlsson Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30760v1 Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual observations into executable plans. However, building agents that can continually improve through interaction and rapidly adapt to their environments remains challenging. Summing up experience from past interaction trajectories provides a promising solution, but existing experience-based methods often rely on manually designed prompting workflows to extract and update skills. Such fixed procedures may struggle to learn updated skills from new and diverse experiences. We introduce PRACTICE, which trains a skill learner to discover and maintain a persistent skill library from past interaction trajectories while keeping the task executor frozen. Given the historical accumulated skills and incoming trajectories, the skill learner produces structured batch-edits that add, refine, merge, or remove skills, and then hierarchical consolidate all collected edits into a consistent updated skill library. We train the learner with a two-stage curriculum. First, it learns basic skill generation and library maintenance from oracle trajectories. Then, by contrasting successful and failed trajectories from heterogeneous executors on the same tasks, it learn to identify invalid action patterns and recovery strategies. Finally, we apply online skill-edit distillation to align the skill learner with a stronger teacher on its current edit distribution to further improves the policy. Experiments demonstrate that a compact skill learner delivers consistent performance improvements across successive library-update rounds for multiple frozen executors. On EB-ALFRED and EB-Habitat, PRACTICE further outperforms the strongest experience-based baselines. Project resources are publicly available at: https://baai-agents.github.io/PRACTICE --- ### CheXGround: Anatomical Region Tokens for Grounded Longitudinal Chest X-ray Interpretation Authors: Adonay Demewez Gebremedhin, Wessam Shehieb, Sara Alansari, Mohamad Alansari, Muzammal Naseer, Sajid Javed, Naoufel Werghi Published: 2026-08-31 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.30758v1 Recent radiology multi-modal language models have made substantial progress in chest X-ray report generation, visual question answering, and temporal reasoning. While longitudinal chest X-ray interpretation compares sequential examinations to describe change, visual grounding aims to connect clinical language with localized image evidence. Although longitudinal modeling and visual grounding have each advanced radiology language models, how localized visual evidence can support longitudinal interpretation remains under-explored. We introduce CheXGround, a region-grounded longitudinal chest X-ray language model that represents paired studies through corresponding anatomical regions. CheXGround extracts anatomical regions from current and prior radiographs, encodes them as temporally enhanced Region-of-Interest (ROI) tokens, and combines them with global temporal image context during generation. To connect these region tokens with clinical text, we propose Temporal Region--Phrase Alignment, a pretraining objective that aligns temporal anatomical representations with localized report phrases. We evaluate CheXGround on single-study and longitudinal Visual Question Answering (VQA), longitudinal findings generation, temporal grounded VQA, and anatomical grounding. Across these tasks, CheXGround improves clinical language quality, temporal reasoning, and localization accuracy over recent baselines. Our results suggest that organizing longitudinal evidence at the anatomical level is a strong representation for grounded radiology language modeling. Project page: https://adonaydem.github.io/chexground-website --- ### Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts Authors: Thomson D. Nguy Published: 2026-08-31 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2608.30757v1 Before an intelligent system can decide whether an action is allowed, it must first know which rules the action has approached. A single proposed action can implicate several policy regimes at once. Their requirements may stack, overlap, or qualify one another, yet many remain written in natural language while the action itself arrives as an incomplete description of intent. The first problem is not judgment. It is attention. Policy-centroid routing creates a layer before adjudication. It compresses expressions within each policy regime into one or more representative centroids, places the proposed action in the same semantic space, applies a declared measure, and routes every regime crossing a declared threshold to authoritative review. Several regimes may trigger at once. The output is a review agenda, not permission, prohibition, legality, breach, compliance, certification, or enforcement. The paper develops six falsifiable propositions and seven follow-on studies comparing the hypothesis with structured workflows, lexical and semantic retrieval, hierarchical and direct classification, and selective prediction under matched review burden. The studies are designed to identify where policy geometry recovers applicable regimes, where compression loses rare or overlapping obligations, and where the mechanism should abstain. The paper includes a synthetic worked example and reports no empirical efficacy result. --- ### On the Prospects of Dynamic LLM Conversations in Software Development Authors: Annemarie Wittig, Alina Mailach, Janet Siegmund, Norbert Siegmund Published: 2026-08-31 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2608.30756v1 Large language models (LLMs) have become an essential tool for assisting developers, yet we still lack knowledge on ways to effectively support their interactions during development activities. That is, the quality of interactions with a chat-based LLM still strongly depends on how developers phrase prompts and which information they include. Our goal is to evaluate whether interventions into these interactions with LLMs have an effect on software developers---be it harmful or beneficial. To this end, we conducted a four-month longitudinal study with third-semester computer science students working on a full-stack Web development project using chat-based LLMs under three conditions: (1) a \emph{context}-aware group received intent-based conversation augmentation, (2) a \emph{proactive} group received follow-up suggestions and tailored advice, and (3) a \emph{control} group without intervention. Our augmentations are minimal: (i) to reduce confounding factors and (ii) to isolate treatment effects. Analyzing interaction logs and user surveys revealed no major differences in interaction patterns, indicating no detectable harmful effects in the measured outcomes when intervening in interactions. Moreover, we observed trends of increased satisfaction with the \emph{proactive} treatment. The results indicate that even with minimal interventions, dynamic guidance mechanisms for developer-LLM interactions show observable effects, such that more severe augmentations may have the potential to substantially improve developer satisfaction. --- ### CLIN: an Objective Framework for Evaluating Creativity in Short Persian Literary Text Authors: Mohammad Reza Modarres, Armin Tourajmehr, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30754v1 Evaluating creativity in large language model (LLM) outputs remains challenging because creativity is multidimensional and human-centered. We examine how reliably LLMs evaluate short literary text in Persian, a low-resource language, across multiple evaluation strategies and prompt formulations. We find that LLM-human agreement varies substantially across dimensions: alignment is stronger for structured TTCT-derived properties such as Originality, Fluency, and Elaboration, but considerably weaker for more subjective dimensions, particularly Emotion and Attractiveness. Judgments are also sensitive to prompt formulation, while few-shot prompting, ensembling, and multi-agent debate provide no consistent improvement. Motivated by this dimension-dependent behavior, we investigate whether structured creativity dimensions can instead be approximated using simple, interpretable proxy metrics. We introduce CLIN, which evaluates three TTCT-derived dimensions separately using topic-aware novelty for Originality, contextual lexical clustering for Fluency, and lexical diversity for Elaboration. These proxies achieve human alignment comparable to or better than the strongest zero-shot LLM judge in our setting while requiring substantially lower evaluation cost. --- ### Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval Authors: Shaowei Wei, Chong Huang, Songtao Fang, Jin Zhang, Zhuojun Wang, Chengfu Huo Published: 2026-08-31 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2608.30753v1 In large-scale e-commerce retrieval, dual-encoder retrievers are op- timized for contrastive similarity, whereas downstream rerankers capture finer-grained relevance preferences; this objective mis- match limits end-to-end retrieval quality. Reinforcement Learning offers a way to use reward-model feedback for retriever adaptation, but we observe that standard policy-gradient updates can degrade embedding geometry, especially when the document index must remain frozen due to industrial constraints. To address this, we propose PAO (Positive-Advantage-Only), a selective RL optimization method. Our analysis reveals that in- discriminate penalization of negative samples (pushing away) in a frozen high-dimensional space disrupts pre-trained semantic man- ifolds. PAO selectively applies gradient updates only to retrieved items with positive advantages, effectively pulling query embed- dings toward high-reward regions while preserving global topo- logical stability. Experiments on both a massive industrial dataset and public benchmarks demonstrate that PAO significantly outper- forms standard RL and distillation baselines. --- ### Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models Authors: Ashwin Nedungadi, Stefan Oehmcke, Stefan Lüdtke Published: 2026-08-31 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2608.30751v2 Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translate spatial descriptions into code. We introduce Autoregressive Mosaics (AM-Bench), a benchmark that separates these factors: First, a translation task gives a model a fully specified geometry of a picture in words as a prompt and asks for the code that produces it. Second, a layout task requires the model to compose an image from an underspecified prompt. Across eight open-weight text-and-code-only models, all models reliably translate specified geometry into code, but their open-ended layout performance differs substantially, indicating that these differences are not explained by code-generation ability alone. An output-medium ablation further shows that the interface or medium of expression that the model uses matters: replacing procedural code with raw SVG improves layout scores across all models. Finally, probing model activations shows that a coarse layout plan is present before generation, but reflects only the layout implied by the prompt. During generation, models track the evolving geometric state instead of executing an initially fixed plan. Overall, these results show that 2D spatial performance in text-only LLMs depends on both the model and the output medium, and is not explained by code-generation ability alone. --- ### Do VLMs Share Safety Neurons Across Modalities? Authors: Jiaxuan Li, Jiahao Zhang, Duc Minh Vo, Huy H. Nguyen, Pride Kavumba, Koki Wataoka Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30750v1 Vision-language models (VLMs) can comply with harmful requests delivered through images, even when their LLM backbones would refuse the same content in text. While prior work characterizes these jailbreaks empirically or at the representation level, how visual inputs perturb safety pathways at the neuron level remains uncharted. We close this gap with a causal, neuron-level analysis of safety mechanisms in 10 VLMs. We propose a two-stage detection pipeline with iterative ablation that accounts for self-repair, and introduce two modality-isolated benchmarks, ViSafe-Detect and ViSafe-Eval, which decouple visual and textual safety signals. Our analysis reveals: (i) Text safety in VLMs is localizable: $\sim$88 neurons ($<$0.01%) whose targeted ablation substantially reduces refusal. (ii) Text safety neurons constitute the dominant refusal pathway: ablating them is the only intervention that consistently and substantially reduces refusal across all models. (iii) Visual safety is high-dimensional and diffuse at the single-neuron level: text safety concentrates in $\sim$5 subspace directions while visual safety requires $\geq$50. This gap holds across architectures, explaining why current alignment has not closed the visual safety gap. Project page is at: https://jiaxuan-li.github.io/vlm-safety-neuron/ Warning: this paper may include examples of harmful content. --- ### The Fragility of Jailbreak Robustness Across Operational States Authors: Yuna Park, Hwang Youn Kim, Yujin Kim, Won Woo Ro, Suhyun Kim, Jae-In Hwang Published: 2026-08-31 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2608.30748v1 Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the vanilla state). However, user-LLM interactions can induce diverse operational states beyond the vanilla state. In this work, we find that jailbreak robustness is highly fragile to operational-state variation: even when the attack remains fixed, changing only an ordinary system prompt not designed to affect safety can dramatically alter attack success rates. We systematically investigate this phenomenon across seven aligned models and three representative jailbreak attacks, observing substantial differences in ASR between vanilla and non-vanilla operational states. In one case, ASR increases by up to 56 percentage points (2% to 58%) solely due to a change in operational state. Remarkably, these increases occur even for attacks originally designed and optimized under vanilla-state evaluation. We further show that state-dependent robustness variation is systematically associated with differences in hidden representations along a refusal-related axis, and that projections onto this axis strongly predict jailbreak outcomes. Our results show that a single vanilla-state evaluation may not fully characterize jailbreak robustness, motivating evaluations that also examine how robustness changes across non-vanilla operational states. --- ### TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification Authors: Ze Chen, Qiming Yu, Zijia Song, Guozheng Yang, Wei Yan Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30745v2 The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitoring. In existing dataset-driven training and testing studies, limitations such as shortcut learning induced by spurious feature correlations and sample imbalance caused by the long-tail distribution of real-world traffic result in weak generalization of traffic identification performance to real-world network traffic. To address these limitations, we propose TDDM-Melatt, a disentangled memory-based traffic classification framework with diffusion-based data augmentation. First, we design Melatt, a memory-decoupled traffic representation model, which employs Competitive Gating Long Short-Term Memory (CG-LSTM) to construct the encoder and decoder. We design a spurious-correlation-free pre-training and inference paradigm, employing strict topology anonymization and a frozen pre-trained encoder strategy to cut off the model's learning pathways for spurious features. During inference, classification is performed efficiently by a downstream classifier on the frozen representations. Second, we propose a Traffic Denoising Diffusion Model (TDDM) tailored to the characteristics of traffic data. Extensive experiments are conducted on 4 representative public benchmark datasets. Under strict flow-level splitting and anonymization, TDDM-Melatt outperforms 6 basic classification models and 6 SOTA representation learning models. The proposed method provides a new and effective technical pathway for encrypted traffic classification in real-world network environments. --- ### Functional Degeneracy in Neural Networks: Measurement and Pruning Authors: Maria Matveev, Pascal Esser, Ayush Bharadwaj, Lucius Bushnaq, Gitta Kutyniok Published: 2026-08-31 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.30741v1 A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to deploy it. To study this, we quantify functional degeneracy through the behavioral recovery rank, defined as the number of leading behavioral-Hessian eigendirections required to recover a trained model's performance. Using the behavioral recovery rank as a geometric benchmark for compression, we find that structural and magnitude pruning retain more degrees of freedom, even after the task is saturated. This gap suggests that functional redundancy is distributed across parameter directions and is not exposed by individual weights or neurons. --- ### Not All Fallbacks Are Failures: Understanding and Recovering from Fallbacks in Mobile Voice Assistants Authors: Phillip Schneider, Alexandre Mercier, Joshua Oehms, Kristiina Jokinen, Florian Matthes Published: 2026-08-31 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.30738v1 Robust understanding of user input is a core requirement for voice assistants deployed in real-world environments. In practice, these systems encounter heterogeneous fallback situations caused by noisy audio input, transcription errors, ambiguous requests, incomplete utterances, or unintended activations. Existing systems typically respond with generic fallback messages, which do not resolve the underlying interaction failure and can degrade user experience. We study fallback handling in a deployed smartwatch-based voice assistant for general health support in everyday environments. Our analysis is based on six months of real-world usage data from more than 500 users, yielding a dataset of 3,030 anonymized, naturally occurring fallback-triggering utterances. We contribute (1) an operational taxonomy and the annotated VoxFallbacks dataset of these interactions, (2) a comparative evaluation of different models within a classification pipeline under practical deployment constraints, and (3) practical lessons for designing robust and cost-efficient fallback mechanisms. Results show that lightweight embedding-based classifiers outperform larger generative models on most classification tasks while requiring substantially fewer computational resources. --- ### Calibrating Small Language Models for Claim Check-Worthiness Detection Authors: Pratuat Amatya, V Venktesh, Vinay Setty Published: 2026-08-31 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2608.30731v2 Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challenge at an early-stage startup: running large language models (LLMs) over every incoming claim is cost- and latency-prohibitive, yet smaller models sacrifice accuracy. We propose NN-PPI, a pointwise extension of Prediction-Powered Inference (PPI) that calibrates model predictions at inference time as a lightweight post-hoc layer, without re-training the underlying model. NN-PPI achieves weighted F1 gains ranging from 12% to 33.80% depending on the size and performance of the baseline model, bringing SLMs on par with larger LLMs. Beyond few-shot SLMs, NN-PPI further improves a production-deployed fine-tuned model, demonstrating that residual calibration is complementary to supervised fine-tuning. By recovering LLM-level accuracy from models that are an order of magnitude cheaper to serve, it makes accurate check-worthiness detection substantially cheaper to operate at scale. Our code and data can be found at https://anonymous.4open.science/r/arr-claim-worthiness-F237. --- ### E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation Authors: Wei Fan, Xinjie Shen, Xudong Guo, Jianhong Tu, Yang Su, Yinger Zhang, Lianghao Deng, Fengyu Wang, Baohua Dong, Yangqiu Song, Dayiheng Liu Published: 2026-08-31 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2608.30730v1 Long-horizon agentic tasks go beyond chaining short tasks over more interaction turns. Their evolving dynamic environments and long-range dependencies require Large Language Models (LLMs) to continually explore, learn from experience, and adapt their policies over thousands of steps. We introduce E-Commerce Bench, the first open-source benchmark that integrates multi-round counterpart negotiation and dynamic events into a year-long business operation. Over a 365-day year, an LLM agent concurrently runs multiple online stores, researching the market, negotiating with suppliers to source inventory, optimizing sales strategies, fulfilling orders, handling returns, and managing cash flow to maximize its end-of-year total assets. To construct a realistic merchant-side operating environment, the product and supplier data are derived from a real e-commerce platform, while a year-long calendar of promotions, natural disasters, and supply-chain shocks continually reshapes demand. For reproducibility, both sides of the market are deterministic: customer purchases and returns follow a fixed demand model, while a negotiation kernel determines supplier pricing, concessions, and decisions, with an LLM used only to verbalize them. We evaluate 18 frontier models across seven dimensions, including year-end assets, and find that no single model dominates. GPT-5.6 Sol earns the most, growing the 100,000 opening stake into 1,431,425, yet it ranks 16th of 18 on fraud avoidance and trails Fable5 in operational efficiency. Among open-weight models, Qwen3.8-Max-Preview leads with 416,252, 38% above GLM 5.2 (high), and achieves the strongest learning over the horizon, progressively bargaining down prices across repeated orders. Our code is available at https://github.com/QwenLM/E-CommerceBench. --- ### RailGen: Improving Railway Intrusion Detection via Agent-Guided Small-Scale Foreign Object Generation Authors: Quan Hao, Ziyang Tao, Chenxi Zhang, Yudong Wang, Rui Shi, Liguo Zhang Published: 2026-08-31 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.30727v1 Small-object detection under long-tailed data distributions is a fundamental yet challenging problem in multimedia. Railway Foreign Object Detection (RFOD) epitomizes this challenge with easily confused small intrusions and scarce samples. To address these issues, we propose a generative-augmented detection paradigm that leverages multimodal image generation to enrich the feature space of rare and small objects. We first construct RailGen, a multimodal image generation agent based on large models. Under semantic constraints, RailGen automatically invokes tools to generate railway scenes, calibrate intrusion positions, extract foreign objects, and fuse them into realistic intrusion effects. This process produces high-quality synthetic samples that effectively densify the feature representations of tail classes and complete the small-object feature space. Within this paradigm, we further propose FocalDEIM, a detection framework designed to enhance training with generated data. FocalDEIM improves dense matching with Focal Modulation for better small-object discrimination and adopts Focal Loss to emphasize hard samples, thereby alleviating blurred inter-class boundaries in complex railway scenes. Experimental results demonstrate that RailGen can generate high-quality small-scale foreign objects, reducing the object pixel area by up to 58x and 13.85x on average. Equipped with these challenging samples, our paradigm surpasses the baseline DEIM by 5.6% and 7.5% in mAP@50 and mAP@(50-95), respectively, and outperforms existing state-of-the-art methods. Ablation studies verify RailGen's feature-space enrichment and FocalDEIM's boundary discrimination. The paradigm provides an effective multimodal generative solution for long-tailed small-object detection in safety-critical applications. ---