# Research Papers — 2026-08 · bundle page 44 of 240 > Full-text markdown of papers #2151–2200 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/44 [← Previous bundle](https://aipod.dev/papers/archive/2026-08/page/43.md) [Next bundle →](https://aipod.dev/papers/archive/2026-08/page/45.md) ### Auditable CT Phenotyping Through Report-derived Radiological Observations Authors: Riga Wu, Walter Witschey, Yicheng Li, Felix Barajas Ordonez, Keno K. Bressem, Lisa C. Adams, Gary E. Weissman, Li Shen, Christos Davatzikos, Eduardo Barbosa, Daniel Truhn, Tianyu Han Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25948v1 Medical image foundation models can predict clinical phenotypes from computed tomography (CT), but strong performance leaves open whether they read disease-specific findings or shortcuts that correlate with the diagnosis. We tested this in 221 electronic-health-record (EHR) phenotypes using Auditable CT phenotyping (ACT), built on report-derived radiological observations. We trained ACT on 38,317 patients, mined 376,194 observations and evaluated it in 25,183 held-out patients. ACT exceeded five vision-language baselines on zero-shot annotation, and CT-CLIP across 221 phenotypes from unseen CT pulmonary angiography, both under zero-shot scoring (0.651 versus 0.572) and under linear probing (0.709 versus 0.662). Reading each probe exposes what accuracy conceals: only 97 observations occupy the 221 rank-1 positions, and one phrase describing aortic and coronary calcification ranks first for 20 phenotypes, including osteoporosis, urinary tract infection and major depressive disorder. Restricting the bank to clinician-specified evidence redirects those probes onto phenotype-related observations in 86 phenotypes at no accuracy cost (0.751 versus 0.741). Accurate CT-based EHR phenotyping can therefore rest on observations that are not valid evidence for the coded phenotype and that ACT can identify and intervene on. --- ### Unveiling Spectral Mechanisms in Training-Free LLM Text Detection Authors: Haitong Luo, Xuying Meng, Weiyao Zhang, Wenji Zou, Shengfeng Lou, Xuefeng Jiang, Chungang Lin, Yujun Zhang Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25944v2 The rapid advancement of Large Language Models (LLMs) makes it increasingly difficult to distinguish human writing from machine-generated text. Training-free detection offers a scalable solution, yet common confidence-based metrics mainly measure average token probabilities and often miss the signal fluctuations that characterize human writing, which we call "generative vitality". Spectral analysis offers a way to capture this vitality, but its mechanism and practical boundaries remain underexplored. In this paper, we analyze spectral detection from both theoretical and empirical perspectives. We connect spectral energy to variance in proxy log-probability trajectories and explain how broader human token choices create the fluctuations used by frequency-domain indicators. We further show that the strength of this signal depends on text length and sampling range: spectral evidence is clearest for long, continuous, constrained generation, while short, fragmented, mixed, and edited settings require complementary confidence and fluctuation views. These findings clarify when frequency-domain detection works and provide guidance for future multi-dimensional detector design. --- ### Unveiling Spectral Mechanisms in Training-Free LLM Text Detection Authors: Haitong Luo, Xuying Meng, Weiyao Zhang, Wenji Zou, Shengfeng Lou, Xuefeng Jiang, Chungang Lin, Yujun Zhang Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25944v1 The rapid advancement of Large Language Models (LLMs) makes it increasingly difficult to distinguish human writing from machine-generated text. Training-free detection offers a scalable solution, yet common confidence-based metrics mainly measure average token probabilities and often miss the signal fluctuations that characterize human writing, which we call "generative vitality". Spectral analysis offers a way to capture this vitality, but its mechanism and practical boundaries remain underexplored. In this paper, we analyze spectral detection from both theoretical and empirical perspectives. We connect spectral energy to variance in proxy log-probability trajectories and explain how broader human token choices create the fluctuations used by frequency-domain indicators. We further show that the strength of this signal depends on text length and sampling range: spectral evidence is clearest for long, continuous, constrained generation, while short, fragmented, mixed, and edited settings require complementary confidence and fluctuation views. These findings clarify when frequency-domain detection works and provide guidance for future multi-dimensional detector design. --- ### When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs Authors: Suchit Gupte, Xueru Zhang, Mohammad Mahdi Khalili Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25941v1 Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systematic study of how pruning affects SAE behavior and theoretically show that, for a fixed SAE, its impact is governed by perturbation energy, a covariance-weighted norm. This perspective exposes a key limitation of magnitude pruning: by ignoring activation geometry, it distorts the learned representation space and degrades SAE functionality. Activation-aware methods such as Wanda and SparseGPT, in contrast, implicitly control perturbation energy and are therefore substantially more robust at preserving SAE behavior. We further reveal a consistent structural vulnerability across all pruning methods: middle layers are significantly more sensitive to pruning than early or late layers. Guided by this insight, we propose a layer-wise sparsity allocation strategy, achieving lower perplexity under the same average pruning sparsity. Experiments across four model architectures validate our theoretical findings. Code is publicly available at https://github.com/osu-srml/sae-robustness-under-pruning/tree/main. --- ### A Statistical Audit of Physical AI Benchmark Redundancy Authors: Zaruhi Navasardyan, Hrant Davtyan Published: 2026-08-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.25940v2 Physical AI models are evaluated on suites of benchmarks that differ across model reports, leaving the model-by-benchmark matrix sparse and the relationship between benchmarks unmeasured. We construct a matrix of 51 models on 12 physical AI benchmarks, selected from a registry of 51 benchmarks and 152 models by reporting density, combining scores from model cards and benchmark papers with our own evaluation runs under each benchmark's official protocol. We measure how much information the benchmarks share and show quantitative evidence of Redundancy. Redundancy affects reported rankings: collapsing the two substitute pairs into single columns moves 22 of 51 models by three or more places under an equally weighted average. We then select benchmarks greedily under a utility combining score dispersion with variance not explained by the already-selected set, and obtain a four-benchmark subset retaining 78.5\% of the utility of all 12, on which we fit a Bradley--Terry ranking. The procedure requires only benchmark-level scores with sufficient overlap and is not specific to physical AI. --- ### A Statistical Audit of Physical AI Benchmark Redundancy Authors: Zaruhi Navasardyan, Hrant Davtyan Published: 2026-08-26 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2608.25940v1 Physical AI models are evaluated on suites of benchmarks that differ across model reports, leaving the model-by-benchmark matrix sparse and the relationship between benchmarks unmeasured. We construct a matrix of 51 models on 12 physical AI benchmarks, selected from a registry of 51 benchmarks and 152 models by reporting density, combining scores from model cards and benchmark papers with our own evaluation runs under each benchmark's official protocol. We measure how much information the benchmarks share and show quantitative evidence of Redundancy. Redundancy affects reported rankings: collapsing the two substitute pairs into single columns moves 22 of 51 models by three or more places under an equally weighted average. We then select benchmarks greedily under a utility combining score dispersion with variance not explained by the already-selected set, and obtain a four-benchmark subset retaining 78.5\% of the utility of all 12, on which we fit a Bradley--Terry ranking. The procedure requires only benchmark-level scores with sufficient overlap and is not specific to physical AI. --- ### Candidate supply and answer selection shape the value of LLM judging in multi-agent systems Authors: Jia-Hao Ji, Sijie Li, Jiabei Cheng, Zixi She, Jin-Tai Yu, Zhiyuan Yuan Published: 2026-08-26 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.25937v2 Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is difficult because generation, communication and final answer-selection rules usually change simultaneously. We conceptualize multi-agent reasoning as an evolutionary pipeline of candidate generation, peer communication and terminal selection, wherein consensus without quality control can exhibit patterns of memetic drift. We study two questions: (1) when an LLM judge provides effective selection pressure by supplying a signal of answer correctness for candidates generated in a multi-agent system, and (2) when using that signal improves the reported answer. To map judge reliability, we analysed 15,336 questions from MMLU-Pro, GPQA, MedXpertQA and MuSR, with Humanity's Last Exam analysed separately. To test these rules, we replayed 81,390 fixed candidate pools drawn from 16,278 questions across five benchmarks. We report three findings. (1) A correct answer is often already present among the generated candidates, but the system can still converge on and report a wrong answer. (2) Judge reliability is not a fixed trait of the model, but varies with the task, the generator and how rare the correct answer is. (3) Combining answer frequency with the judge's evaluation changed only the final answer-selection rule and raised accuracy from 63.82% to 70.82-70.95%, primarily by rescuing correct answers that were outnumbered by popular errors. In the systems studied here, the value of generating more candidates depends on whether those extra samples make correct answers present, frequent or recognisable. By isolating generation, recognition and selection, these findings establish a diagnostic basis for designing multi-agent architectures that protect generated correct answers from being lost. --- ### Candidate supply and answer selection shape the value of LLM judging in multi-agent systems Authors: Jia-Hao Ji, Sijie Li, Jiabei Cheng, Zixi She, Jin-Tai Yu, Zhiyuan Yuan Published: 2026-08-26 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2608.25937v1 Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is difficult because generation, communication and final answer-selection rules usually change simultaneously. We conceptualize multi-agent reasoning as an evolutionary pipeline of candidate generation, peer communication and terminal selection, wherein consensus without quality control can exhibit patterns of memetic drift. We study two questions: (1) when an LLM judge provides effective selection pressure by supplying a signal of answer correctness for candidates generated in a multi-agent system, and (2) when using that signal improves the reported answer. To map judge reliability, we analysed 15,336 questions from MMLU-Pro, GPQA, MedXpertQA and MuSR, with Humanity's Last Exam analysed separately. To test these rules, we replayed 81,390 fixed candidate pools drawn from 16,278 questions across five benchmarks. We report three findings. (1) A correct answer is often already present among the generated candidates, but the system can still converge on and report a wrong answer. (2) Judge reliability is not a fixed trait of the model, but varies with the task, the generator and how rare the correct answer is. (3) Combining answer frequency with the judge's evaluation changed only the final answer-selection rule and raised accuracy from 63.82% to 70.82-70.95%, primarily by rescuing correct answers that were outnumbered by popular errors. In the systems studied here, the value of generating more candidates depends on whether those extra samples make correct answers present, frequent or recognisable. By isolating generation, recognition and selection, these findings establish a diagnostic basis for designing multi-agent architectures that protect generated correct answers from being lost. --- ### One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation Authors: Justin Robert, Raheel Qader Published: 2026-08-26 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.25936v1 On-policy distillation trains a language model on its own generations while a teacher scores them token by token. It combines the dense supervision of imitation learning with the on-policy sampling of reinforcement learning. But it requires a second, larger model to act as teacher. On-Policy Self-Distillation (OPSD) removes that cost. The teacher is the model itself, conditioned on privileged information the student will not have at test time, such as a reference solution, a plan, or environment feedback. The teacher is no stronger than the student, only better informed. Early results were promising, with accuracy comparable to reinforcement learning at a fraction of the generated tokens. But the same asymmetry that produces the signal also biases it. One failure mode now dominates the field: collapse, the progressive narrowing of the set of reasoning paths the model can produce. Collapse is not specific to OPSD, though privileged information aggravates it. This review treats collapse as a symptom governed by three levers: (i) where the signal is applied, that is, how tokens are weighted; (ii) what the teacher is shown, that is, the nature of the privileged information; and (iii) when the signal changes, that is, the teacher's dynamics and the decay of guidance. We restrict our scope to mathematical reasoning, where the method originated and where its failure modes are best documented. We report no new experiments. The contribution is structural: a shared vocabulary for phenomena named differently across papers, and a clear line between what is settled and what is still disputed. --- ### TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding Authors: Yuqiang Lin, Yan Shi, Sam Lockyer, Harish Tayyar Madabushi, Adrian Evans, Wenbin Li, Yinhai Wang, Nic Zhang Published: 2026-08-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.25935v1 Traffic Anomaly Understanding (TAU) requires models and systems to detect, reason about, and explain anomalous events in transportation videos. To address this challenge, we propose TAU-Agent, an agentic retrieval-augmented framework for traffic anomaly understanding. Given a task query, a central retrieval agent orchestrates two visual perception tools, namely a Video Captioning Tool and an Open-Vocabulary Tracking Tool, to retrieve and select query-relevant evidence, including captions, temporal intervals, and object trajectories. The selected evidence, together with sampled video frames and the input query, is provided to a supervised fine-tuned vision-language model for final reasoning and answer generation. We evaluate TAU-Agent on both the in-domain and the out-of-domain benchmarks from the AI City Challenge 2026. TAU-Agent achieves scores of 0.6779 on Track 3, 0.3998 on Track 7, and 67.9275 on Track 8, ranking second, twelfth, and fifth, respectively. Code is available at: https://github.com/siri-rouser/TAU-Agent. --- ### How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark Evaluation Authors: Aida Usmanova, Zangir Iklassov, Markus Leippold, Ricardo Usbeck Published: 2026-08-26 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2608.25934v1 Automated fact-checking (AFC) systems retrieve evidence and predict claim veracity, yet evaluations omit simple baselines, systems are developed for a single benchmark and cannot be trusted to generalise across domains. No prior work cross-evaluates the full two-stage retrieve-then-verify pipeline across diverse datasets, complementing retrieval-only studies (Thakur et al., 2021) and single-stage benchmarking studies (Calamai et al., 2025). We benchmark nine models, ranging from random and sparse baselines to fine-tuned transformers, zero-shot LLMs, and the two highest-ranked systems from the AVeriTeC 2025 shared task, across four datasets spanning scientific, open-web, and climate domains. Three findings stand out: (1) on ClimateCheck claim-only and fine-tuned models outperform zero-shot LLM and top-performing AVeriTeC 2025 systems, highlighting that noisy evidence can degrade veracity prediction; (2) system rankings are strongly domain- and metric-dependent: the best model on SciFact (macro-F1 0.70) drops to 0.31 on ClimateCheck, while the AVeriTeC 2025 winner and runner-up swap rankings based on evaluation metrics and datasets; (3) replacing retrieved evidence with gold annotations improves veracity accuracy by 14-22 points across models, confirming retrieval remains primary bottleneck. We release code, pre-processed datasets, and all results to support reproducible AFC research. --- ### When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated Images Authors: Ruoqi Hu, Chulin Zhao, Jiashuo Chang, Ramon Ruiz-Dolz, Hanhe Lin Published: 2026-08-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2608.25933v1 *Chulin Zhao and Ruoqi Hu contributed equally to this work. State-of-the-art text-to-image (T2I) models exhibit pronounced and systematic defects when prompts involve intricate compositional factors such as multiple entities and multiple attributes. In this paper, we investigate how humans identify such defects. Specifically, we manually select 651 reference images from the four categories of people, hand, object, and scene that exhibit complex compositional characteristics, from which prompts emphasizing compositional factors are derived by manually editing ChatGPT-generated prompts. We then feed the prompts into three selected T2I models to generate AI images and conduct a comprehensive subjective study to identify their defects. For each image, 29 participants provide multi-label assessments specifying defect types and locations. The study yields the compositional AI-generated image defect (CO-AID) dataset, including reference images, prompts, AI-generated images, and information on defect locations and types. Experimental results show that training a deep model on CO-AID can both predict defects in AI-generated images and optimize AI image generation, demonstrating its usability and effectiveness. The database and supplementary materials are available at: https://github.com/Future-IQA/CO-AID . --- ### Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversion Authors: Jaehong Chung, Andrew Lockwood, Jef Caers Published: 2026-08-26 Categories: physics.geo-ph, cs.LG arXiv: https://arxiv.org/abs/2608.25932v1 Three-dimensional probabilistic inversion of time-domain airborne electromagnetic (AEM) data is limited by the cost of the forward solve. Even though one simulation takes only tens of seconds, a Bayesian inversion of a survey of millions of soundings requires of order $10^{10}$ forward evaluations. To address this, we develop a continually learning neural-operator surrogate of the three-dimensional AEM forward operator that replaces the solver inside the Bayesian inversion. We start from the point of view that regardless of what geological prior is specified, Maxwell's laws remain invariant. Secondly, we avoid the limitation of learning on a single prior by continual learning on consecutive priors, which means our surrogate becomes richer as it is applied in future case studies, either by the authors, or by the scientific community. We use a validity check built on ensemble disagreement to divert cases with measurements outside the training range to the solver. Driven by the surrogate, the identical Markov chain Monte Carlo sampler reproduces the full-solver posterior, and its credible intervals cover the truth within 2.6 percentage points. Applied to the 2013 Capricorn TEMPEST survey in Western Australia, the surrogate inverts over two million soundings in seconds, a computation infeasible for the solver. Testing the geological prior against the entire survey costs minutes. The framework delivers uncertainty-quantified conductivity imaging at survey scale, which we believe is essential to perform near real-time mineral-systems targeting with geophysics. --- ### Controlling for Omitted Variable Bias in Deep Neural Networks Authors: Manuel Pfeuffer, Roshan Prakash Rane, Kerstin Ritter, Sonja Greven Published: 2026-08-26 Categories: stat.ME, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2608.25930v1 Control variables are widely used in statistical modelling to account for omitted variable bias of known confounders. However, they have largely been underexplored in deep learning. This is surprising, given that deep learning models encode image-inferable covariates, such as demographic variables, into their predictions when these covariates are correlated with the outcome---a form of omitted variable bias referred to as 'shortcut learning'. While many existing confound-control or fairness methods try to restrict the correlation of such covariates with model predictions, we show that this fails to correct for omitted variable bias. We therefore propose a control variable approach for deep learning models, based on generalised additive modelling of the effects of model inputs and covariates. As flexible additive models can suffer from concurvity, we introduce an estimation procedure that refits the final layer of a pre-trained network to include covariate effects, using cross-fitting with ridge penalisation. We show how these effects can be orthogonalised with respect to covariates to exclude their mediated effects and that model predictions can be marginalised over the covariate distribution to control for their effect. This yields unbiased, interpretable predictions and offers flexibility to model the desired effects depending on the scientific or fairness objective. We verify our approach using simulated images, and demonstrate consistent estimation of true effects. Existing methods either require more data or fail to recover the true effects. We apply our method to real neuroimaging data with experimentally induced confounding, where it recovers prediction performance to near the level of a model trained on unconfounded data. Code is available at https://github.com/mpff/cocodeel. --- ### Code World Model: Coding Agent as World Brain Authors: Yiwen Chen, Guosheng Lin, Chi Zhang Published: 2026-08-26 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2608.25927v1 World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics from visual observations, which reveal outcomes rather than the underlying knowledge, rules, and mechanisms governing world evolution. This makes it difficult to maintain persistent consequences and support coherent, open-ended evolution. We introduce Code World Model, a framework that separates world evolution from visual realization by combining the reasoning and coding capabilities of language models with the generative priors of video models. A coding agent serves as the world brain, reasoning about events and their consequences and generating executable code to maintain persistent world state and perform rule-consistent evolution. To connect executable state with visual generation, we introduce a proxy representation that encodes frame-wise spatiotemporal constraints and is compiled into a proxy video, which conditions a video model to render high-fidelity visual observations. We further develop data pipelines for constructing aligned proxy-observation pairs from gameplay and real-world videos. After fine-tuning on paired gameplay data, MiniMax-H3 follows proxy-based spatiotemporal specifications from simple interactive worlds built by the coding agent while preserving rich visual details and dynamics. These results demonstrate the potential of combining code for persistent world evolution with video models for flexible visual realization, providing a new path toward open-ended world models. --- ### Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational Procedures Authors: Roberto Luvini, Giacomo Longo, Alessandro Armando, Enrico Russo Published: 2026-08-26 Categories: cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2608.25926v1 Air traffic control procedures are executed through spoken exchanges between controllers and pilots. These interactions are essential to the safety of air transportation: failures in their execution can create severe operational hazards, as evidenced by past fatal accidents. Assessing whether an instruction has been followed requires relating what was said to the aircraft concerned, its state, and the obligations that pilots must meet. We present a runtime verification framework that monitors such procedures by checking controller-pilot exchanges, surveillance data, and onboard observations. The framework parses radio communications into events linked to the entities they concern and merges them with surveillance and onboard observations into a time-stamped trace. The ICAO-derived obligations as formalized as temporal formulas with explicit time bounds and evaluated over execution traces. Every violation is reported along with the breached obligations and the observations that support the verdict. With real traffic, the complete pipeline reaches an F1 of 0.85 against blind human-annotated violations; in 1,495 synthetic situations derived from two public corpora, the monitor logic returns the expected verdict in every case. In two historical accidents reconstructed from official investigation reports, the monitor identifies the same procedural deviations documented by the investigators. --- ### Visual General Intelligence: A White Paper Authors: Hirokatsu Kataoka, Yoshihiro Fukuhara, Yonglong Tian, Shangzhe Wu, Oishi Deb, Ryousuke Yamada, Christian Rupprecht, Jianyuan Wang, Kohsuke Ide, Koichi Namekata, Xianzheng Ma, Yiming Chen et al. Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25924v1 This paper reconsiders intelligence from a vision-centered perspective and examines whether intelligence emerging from visual experience and learning may provide a pathway toward AGI. In the language domain, beginning with the introduction of the Transformer architecture, the GPT series has demonstrated transfer to unseen tasks through autoregressive language modeling on web-scale text combined with aggressive scaling. This raises a natural question, namely, what capabilities and forms of intelligence can emerge from visual modalities such as images, videos, and geometry? In this paper, we discuss whether visual intelligence can serve as a pathway toward AGI, referred to in this paper as visual general intelligence (VGI), by bringing together contributors from diverse standpoints and affiliations. Our aim is not to offer a single definition of visual intelligence, but to clarify the principles that computer vision should pursue in the AGI era, the visual input modalities, the benchmarks, the learning paradigms, and the relationship between vision, when taken as the core, and other modalities such as language. --- ### Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation Authors: Pankaj Kumar, Subhankar Mishra Published: 2026-08-26 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.25922v2 GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness and the appropriate mitigation target. We ask which stage fails, and why, when the pipeline is subjected to adversarial perturbations on the input question. We introduce a stage-isolation protocol with two answer-preserving adversarial perturbations verified against the knowledge graph: Compositional Restructuring (CR) and Relation Synonym Swap (RS) target distinct stages while leaving entity seeds intact. Evaluated across ComplexWebQuestions and WebQSP, the results run counter to prevailing assumptions: the GNN reasoning stage retains near-baseline accuracy when the subgraph is intact, while subgraph construction accounts for over 99\% of the end-to-end collapse under CR, occurring even when the gold answer is present in 74\% of retrieved subgraphs. This exposes a fundamental distinction between answer presence and answer reachability that end-to-end metrics cannot detect, and places the mitigation target firmly at the subgraph construction stage rather than the reasoning model. Perturbed datasets and evaluation infrastructure are released at https://anonymous.4open.science/r/atkgrag-E85C . --- ### Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer Generation Authors: Pankaj Kumar, Subhankar Mishra Published: 2026-08-26 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2608.25922v1 GNN-based Knowledge Graph Question Answering (KGQA) pipelines process queries through four discrete stages: entity linking, subgraph retrieval, GNN reasoning, and answer generation. Standard robustness evaluations conflate stage-level failures into a single end-to-end metric, obscuring both the source of brittleness and the appropriate mitigation target. We ask which stage fails, and why, when the pipeline is subjected to adversarial perturbations on the input question. We introduce a stage-isolation protocol with two answer-preserving adversarial perturbations verified against the knowledge graph: Compositional Restructuring (CR) and Relation Synonym Swap (RS) target distinct stages while leaving entity seeds intact. Evaluated across ComplexWebQuestions and WebQSP, the results run counter to prevailing assumptions: the GNN reasoning stage retains near-baseline accuracy when the subgraph is intact, while subgraph construction accounts for over 99\% of the end-to-end collapse under CR, occurring even when the gold answer is present in 74\% of retrieved subgraphs. This exposes a fundamental distinction between answer presence and answer reachability that end-to-end metrics cannot detect, and places the mitigation target firmly at the subgraph construction stage rather than the reasoning model. Perturbed datasets and evaluation infrastructure are released at https://anonymous.4open.science/r/atkgrag-E85C . --- ### Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems Authors: Zhongwen Luan, Xiaoyu Zhang, Ming Hu, Yue Yang, Jiongchi Yu, Xiaohong Chen Published: 2026-08-26 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.25920v2 As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors. During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory, thereby enabling the reliable reproduction of MAS failures. We further construct the dataset SymFail, comprising 536 human-annotated failure trajectories with graph-linked locations, categories, and trace evidence. Based on these foundations, we conduct a large-scale empirical study across three mainstream MAS frameworks. Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates (only 67.97% and 6.90%, respectively). Building upon these findings, we further explore the effectiveness of a symptom-driven intervention method, which successfully repairs 20.15% of the failed cases (a 191.89% improvement to state-of-the-art repair methods). This study aims to provide actionable insights for MAS debugging and repair research, paving the way for the robust deployment of multi-agent systems. --- ### Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systems Authors: Zhongwen Luan, Xiaoyu Zhang, Ming Hu, Yue Yang, Jiongchi Yu, Xiaohong Chen Published: 2026-08-26 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2608.25920v1 As large language model (LLM)-based multi-agent systems (MASs) are increasingly applied to long-horizon complex tasks, their reliability has emerged as the core bottleneck hindering their real-world deployment. Existing MAS debugging and repair methods typically rely on rerunning and resampling the entire execution trajectory. However, a fundamental question remains to be answered: do these methods causally repair MAS failures or merely stochastically repair by leveraging the randomness of LLM sampling? To evaluate the effectiveness of MAS repair methods, we introduce SymTrace, a controlled evaluation framework that records the MAS execution trajectory and establishes intervention anchors. During replay, it effectively reconstructs the execution before the anchor using recorded logs and only regenerates the downstream trajectory, thereby enabling the reliable reproduction of MAS failures. We further construct the dataset SymFail, comprising 536 human-annotated failure trajectories with graph-linked locations, categories, and trace evidence. Based on these foundations, we conduct a large-scale empirical study across three mainstream MAS frameworks. Our findings reveal that existing unguided rerun methods are highly unreliable, exhibiting low failure reproduction and repair rates (only 67.97% and 6.90%, respectively). Building upon these findings, we further explore the effectiveness of a symptom-driven intervention method, which successfully repairs 20.15% of the failed cases (a 191.89% improvement to state-of-the-art repair methods). This study aims to provide actionable insights for MAS debugging and repair research, paving the way for the robust deployment of multi-agent systems. --- ### Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions Authors: Yueyuan Li, Rongcheng Nie, Weijie Xi, Mingyang Jiang, Songan Zhang, Hanyang Zhuang, Ming Yang Published: 2026-08-26 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2608.25917v1 Game-theoretic models provide principled frameworks for modeling vehicle interactions, but their underlying temporal assumptions have not been systematically examined against real-world driving behavior. In particular, it remains unclear how simultaneous, sequential, and asymmetric interaction structures can be measured from vehicle trajectories. This paper develops a trajectory-based interaction measurement framework to identify interaction events and quantify behavioral change onset, temporal organization, post-onset response dynamics, and ordering stability. The framework uses behavioral deviations to verify candidate interactions. We evaluate the framework on six real-world trajectory datasets, including INTERACTION, highD, inD, rounD, Waymo Open Motion, and nuPlan, covering diverse road geometries, traffic environments, and interaction types. The results show that concurrent and sequential behavioral changes both constitute substantial proportions of observed following, merging, and conflicting interactions. Among sequential interactions, stable ordering is more prevalent than alternating ordering, indicating that persistent asymmetric roles are a common interaction structure. Importantly, temporal precedence does not necessarily coincide with a measurable behavioral response, indicating that temporal ordering alone may not be sufficient to characterize behavioral dependence. These findings show that real-world interactions exhibit concurrent, sequential, and persistently ordered temporal structures. Different game-theoretic formulations are therefore better regarded as complementary modeling abstractions for different interaction regimes rather than as a universal structure governing all vehicle interactions. --- ### SAMpLE: A SystemC-AMS Machine LEarning-based Framework for Virtual Prototyping Authors: Andrei Mihai Albu, Sara Vinco Published: 2026-08-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.25910v1 Machine Learning (ML) is increasingly used in virtual prototypes of embedded systems to model behaviors that are difficult to capture analytically. However, integrating ML models into virtual platform simulation is still typically done through ad hoc solutions, which limits reuse, comparability, and reproducibility. This paper presents \textbf{\textit{SAMpLE}}, an open-source SystemC-AMS-based framework that integrates ML models as first-class Timed Dataflow (TDF) components through a standardized plug-and-play interface. SAMpLE provides two execution backends: a native C++ backend for online training of lightweight models, and an offline backend for executing externally developed models without requiring re-implementation in C++ or manual integration steps. The framework uses ONNX as a standard model exchange format to enable integration of externally trained ML models into SystemC-AMS simulations, and allows the evaluation of different ML-based solutions within the same testbench, dataset, and simulation workflow. The modular design and unified and reproducible environment will allow future extensions of SAMpLE to new models, without modifying the SystemC-AMS structure. --- ### Quantum-Inspired Modeling of Driving Behavior Authors: Mohammad Elayan, Omid Armantalab, Wissam Kontar Published: 2026-08-26 Categories: cs.LG, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2608.25907v1 Driver behavior is heterogeneous, context-dependent, and changes over time, and these properties shape the traffic phenomena we observe. Most models, however, fix in advance which behavioral variables interact and how. Behavior outside that form is absorbed as noise, while models flexible enough to capture it tend to lose interpretability. We introduce a quantum-inspired representation of driver behavior that combines properties usually treated separately or in part: it is continuous, probabilistic, context-dependent, history-dependent, and represents interactions among behavioral variables as learned from data. Each driver is encoded as an evolving density matrix, providing a unified representation of behavioral uncertainty, temporal evolution, and context-dependent behavioral variation. Trained without supervision on the I-24 MOTION dataset, the framework recovers three interpretable driving profiles representing three regimes: free flow, transition, and congestion. The profiles capture the behavioral range of the data and the smooth transitions drivers make between regimes as conditions change. The same representation also reproduces known macroscopic phenomena, aligning with the fundamental diagram and reproducing hysteresis loops. We also show how the representation supports practical use: it supplies context-dependent parameters to classical car-following models, and gives an autonomous vehicle a live behavioral read of the surrounding drivers with a short-horizon forecast of their motion. The framework points toward models of traffic that are interpretable and trustworthy by construction. We release an open-source toolkit on GitHub (https://github.com/mselayan/quantum-driver-representation) spanning data processing, training, inference, and analysis. --- ### One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography Authors: Muge Zhang, Aaron Jencks, Krishna Badikela, Yulia Tsvetkov, Sachin Kumar Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25904v3 Multilingual language models transfer knowledge across languages through shared subword vocabulary, a mechanism that breaks down when related languages use different writing systems. Prior work addresses this via script equalization (romanization or IPA transcription), but direct comparisons are rare; the focus has been on encoder-only models, with most work adapting existing pretrained models. We systematically compare different input representations in autoregressive multilingual pretraining, comparing orthographic text, IPA, and romanization in a controlled setup across three scales (467M, 709M, and 1.03B) on eight languages in four typologically motivated pairs. Across a wide range of downstream tasks on seen and unseen languages, romanized pretraining yields the strongest cross-lingual transfer, and the advantage over text widens with scale. IPA improves over text in most settings but trails romanization. Surprisingly, finetuning a text-pretrained model on romanized data hurts performance on languages already covered by the base model, only marginally helping when the model lacks script coverage. Our results indicate that for multilingual models spanning typologically diverse scripts, to obtain maximum benefits, romanization should be treated as a core design choice applied at pretraining rather than a post hoc fix. --- ### One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography Authors: Muge Zhang, Aaron Jencks, Krishna Badikela, Yulia Tsvetkov, Sachin Kumar Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25904v1 Multilingual language models transfer knowledge across languages through shared subword vocabulary, a mechanism that breaks down when related languages use different writing systems. Prior work addresses this via script equalization (romanization or IPA transcription), but direct comparisons are rare; the focus has been on encoder-only models, with most work adapting existing pretrained models. We systematically compare different input representations in autoregressive multilingual pretraining, comparing orthographic text, IPA, and romanization in a controlled setup across three scales (467M, 709M, and 1.03B) on eight languages in four typologically motivated pairs. Across a wide range of downstream tasks on seen and unseen languages, romanized pretraining yields the strongest cross-lingual transfer, and the advantage over text widens with scale. IPA improves over text in most settings but trails romanization. Surprisingly, finetuning a text-pretrained model on romanized data hurts performance on languages already covered by the base model, only marginally helping when the model lacks script coverage. Our results indicate that for multilingual models spanning typologically diverse scripts, to obtain maximum benefits, romanization should be treated as a core design choice applied at pretraining rather than a post hoc fix. --- ### MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath Selection Authors: Fahim Shahriar Khan, Ashraf Aboulnaga Published: 2026-08-26 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2608.25903v1 Relational Deep Learning (RDL) is an effective approach to machine learning over multi-table relational databases. In RDL, a database is modeled as a graph in which each row is a node and each foreign-key relation is an edge, and a graph neural network (GNN) is trained on this graph. Training a GNN requires sampling a subgraph around every seed node in the training set, and the cost of training is largely determined by the size of these subgraphs. This paper aims to reduce subgraph size by leveraging the join and aggregation capabilities of relational database systems. We observe that sampled subgraphs are obtained by following metapaths composed of foreign-key links, and that many of these metapaths can be pruned without loss of accuracy. We present MetaSieve, a metapath selection layer that determines which metapaths to retain and which to prune. For each candidate metapath extension, MetaSieve computes statistics via SQL join and aggregation queries and evaluates the extension based on a novel scoring function that prefers lightweight but informative candidates. Metapaths whose scores fall below a threshold are deemed uninformative and pruned. Metapath selection in MetaSieve is lightweight since it relies only on database statistics and task labels, and it is independent of GNN parameters, so it integrates with diverse GNN architectures for classification and regression. Our evaluation on the RelBench benchmark with multiple GNN backbones shows that MetaSieve consistently reduces per-epoch training time by large margins while maintaining and often improving accuracy. --- ### Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic Dynamics Authors: Pavel Prochazka Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25898v1 Forecasting a stochastic dynamical system rarely means a single number: one wants several observables---future state, threshold event, regime label---each with its own likelihood. Standard multi-task recipes balance per-task losses, tuned or learned. We instead compose the observables' likelihoods in per-task free-routed last-layer beliefs on a shared backbone; this absorbs unit-dependent loss scaling into likelihood parameters learned in the same gradient pass. Stochastic dynamics supply what static benchmarks cannot: computable ground truth for the predictive variance. Results land where theory puts them: on the well-specified, homoscedastic Ornstein--Uhlenbeck process the learned predictive law recovers the analytic kernel and correctly specified baselines tie. On heteroscedastic systems (stochastic Lorenz-63, real air-quality data) the belief's input-dependent variance separates: best single-run NLL on the state and regime tasks, calibration matched only by arms whose NLL it beats, at a fraction of the tuned grids' cost. On the real series the state margin holds across five rolling origins. --- ### Towards A Unified Information Bottleneck Framework for Time Series Explanations Authors: Xu Zheng, Zichuan Liu, Zhuomin Chen, Mayur Akewar, Janki Bhimani, Jason Liu, Mo Sha, Jingchao Ni, Wei Cheng, Dongsheng Luo Published: 2026-08-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.25897v1 Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations. --- ### From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations Authors: Ping Wang, Xiangguo Sun, Bingbing Xu, Guocong Li, Xiaofeng Meng Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25894v1 Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input. Existing approaches to hallucination mitigation typically assume reliable user inputs, overlooking how such factual errors can actively mislead model reasoning. To address this vulnerability, we propose DEDUCE, a three-stage framework that transforms LLMs from passive responders into proactive error correctors. DEDUCE operates in three stages: (1) detect errors through fine-grained fact extraction and verification; (2) devise correction strategies via multi perspective deliberation; and (3) correct misconceptions while delivering reliable answers. We also present MisFactQA, a dataset containing factual errors of varying degrees, and propose new metrics for evaluating model robustness. Experiments on TruthfulQA, FalseQA, and our MisFactQA benchmark demonstrate that DEDUCE significantly improves both accuracy and error correction capability. Consistent gains across Qwen, LLaMA, and Gemma families confirm its effectiveness and scalability. --- ### A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory Tasks Authors: Yikun Han, Yi Wang, Neil Mankodi, Stephen Yang, Ambuj Tewari Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25893v1 Foundation models have transformed molecular property prediction, yet it remains unclear whether a molecular foundation model, fine-tuned on a single canonical olfactory prediction task, can learn representations that transfer across diverse machine olfaction problems. We investigate this question by fine-tuning Uni-Mol2 on the GS-LF benchmark for multi-label odor descriptor prediction and evaluating the resulting model, without additional deep-learning training, on four complementary downstream settings: cross-dataset odor descriptor prediction, odorous-versus-odorless classification, enantiomer evaluation, and odor mixture discriminability. The fine-tuned model matches or exceeds the performance of the state-of-the-art olfaction-specific baseline on the primary GS-LF benchmark and consistently transfers across these downstream evaluations. The enantiomer analysis further shows that three-dimensional molecular representations distinguish mirror-image molecules in a way that two-dimensional graph models fundamentally cannot, although accurately predicting the perceptual consequences of stereochemistry remains an open challenge. Together, these results support a train-once, transfer-across-tasks paradigm for machine olfaction and suggest that chemically pretrained molecular representations provide a strong foundation for transferable olfactory prediction. --- ### Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancing Authors: Matvey Moisseyev, Huijing Du, Dandan Zheng, Chi Zhang, Hongfeng Yu Published: 2026-08-26 Categories: cs.DC, cs.CE, cs.LG, math.OC arXiv: https://arxiv.org/abs/2608.25890v1 Detailed multicellular growth simulations based on subcellular element models (SEMs) can capture complex tissue development, but their element-level interactions impose substantial computational cost. This work presents a scalable multi-GPU framework for 3D multicellular growth simulation that combines GPU acceleration, spatial binning, domain decomposition, and workload-aware partitioning. Cell movement, growth, and division continuously reshape the spatial workload distribution, causing initially balanced partitions to become inefficient over time. To address this, we introduce an RNN-based load-balancing controller that observes recent per-rank execution times and partition states and learns residual corrections to a reactive boundary-adjustment rule. The controller is trained offline in a differentiable surrogate of the load-balancing loop with randomized workload dynamics, requiring no measured execution traces for training. We evaluate the framework in terms of single-GPU acceleration, multi-GPU computation scaling, controller-level load-balancing behavior, and end-to-end simulation performance, with comparisons against static partitioning, reactive load balancing, and conventional time-series prediction baselines. A representative embryonic epidermal development use case further demonstrates the type of spatially and temporally evolving workload targeted by the framework. In our evaluation, GPU acceleration with spatial binning accelerates the interaction computation by roughly three orders of magnitude over a serial CPU baseline. RNN-guided load balancing reduces the mean global imbalance from 11.3% under static partitioning to 3.5%, lowers end-to-end runtime by 9.0% relative to static partitioning, and reduces slice migration by 7.7x compared with the reactive baseline, showing that history-aware control can improve workload balance while avoiding unnecessary repartitioning. --- ### Embedding NDRE Trajectories into Contrastive Learning for Label-Free, Physiology-Aware Crop-Stress Staging and DSS Outputs Authors: Shafqaat Ahmad Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25888v1 Timely detection of crop stress is critical for sustaining yields under increasing drought frequency, yet conventional vegetation index thresholds or image-based clustering often fail to capture stress progression, limiting their value for farm decision-making. To address this gap, we present EigenCL, a physiology-guided contrastive learning framework that stages crop stress from Sentinel-2 NDRE trajectories, with the goal of providing interpretable and transferable stress diagnostics for decision support systems (DSS). EigenCL was trained on 10,000 maize NDRE patches from drought-affected Iowa fields in 2020 and tested on Nebraska fields in 2023 without retraining, with validation incorporating soil-moisture records, U.S. Drought Monitor maps, and county-level yield statistics. The model produced four physiologically coherent stress clusters (Healthy, Mild, Moderate, Severe), significantly outperforming baselines including K-Means, SimCLR, ProtoCLR, and an ablation model (Silhouette = 0.748, DBI = 0.35, CHI = 49,624). Clusters aligned with maize growth stages, with severe stress peaking around tasseling-silking (VT-R1), a stage known to drive yield loss; moreover, EigenCL clusters correlated with soil moisture at 0-14-day lags (rho up to 0.72) and matched yield anomalies in drought-affected counties. By embedding NDRE trajectory dynamics into contrastive learning, EigenCL enables early stress alerts and interpretable DSS outputs (e.g., heatmaps, scouting priorities, regional risk indices), extending beyond single-date NDRE thresholds and supporting scalable monitoring for climate-smart agronomy. --- ### Efficient Estimation of High Information Projections using Nearest Neighbours Authors: David P. Hofmeyr Published: 2026-08-26 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2608.25887v1 An intuitive method for dimensionality reduction is proposed, which is highly effective for finding interesting projections of multivariate data. Following similar intuitive motivation to a number of existing techniques, the proposed method is based on enhancing the nearest neighbour relationships in the data. The proposed projection arises from the spectral decomposition of a matrix designed to encode the local covariance structure in the data, where the local covariance at a point is captured by pairs of its nearest neighbours. We show that under standard regularity conditions this matrix is a consistent estimator of the so-called ``Density Information Matrix'' (DIM); a non-parametric analogue of the Fisher Information Matrix. Spectral decompositions of DIMs have been shown to be connected with the important problems of Independent Components Analysis and, in the supervised context, Sufficient Dimension Reduction. However, existing estimators of the DIM are computationally expensive to compute and only target the DIM of a surrogate density, which is proportional to the square of the true underlying density. In addition, we go on to explore the practical utility of our method in aiding the downstream tasks of cluster analysis and outlier detection. --- ### Loss-Based Active Learning for Neural Abstractive Summarization Authors: Michail Ioannou, Tatiana Passali, George Michalopoulos, Grigorios Tsoumakas Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25881v1 Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to create accurate summaries. Active learning mitigates this issue by selecting only the most informative instances for annotation, allowing models to achieve competitive results with significantly fewer labels. However, the application of active learning to summarization remains under-explored, and existing studies often suffer from instability and significant computational bottlenecks. To overcome these challenges, we propose LOBSTER (LOss-BaSed acTivE leaRning), a novel active learning framework designed specifically for abstractive summarization. LOBSTER improves performance by prioritizing unlabeled instances semantically similar to the model's current high-loss training examples, enabling the model to explicitly correct its specific weaknesses. Our empirical evaluation across three benchmark datasets and two summarization backbone models demonstrates that LOBSTER consistently matches or outperforms current state-of-the-art approaches while achieving a query selection speedup of up to 665x. --- ### Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces Authors: Luca Bux, Thiago Rios, Ingo Scholtes, Stefan Menzel, Bernhard Sendhoff Published: 2026-08-26 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2608.25876v2 Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as "more elegant" or "more minimalist," typically encoded by a vision-language model (VLM). A practical question is whether state-of-the-art VLMs represent objects consistently in terms of the same concept. We audit 6 VLMs by ranking untextured 3D objects along Kansei adjective pairs, where Kansei describes affective impressions of product form, with each axis defined as the difference between the text representations of its two poles. Geometric pairs serve as positive controls, and pairs of unrelated adjectives establish an empirical null. Across 10 categories of ShapeNet database, affective axes converge above the null (mean pairwise rank correlation 0.36 vs. 0.14) but below the geometric ceiling (0.44). The agreement between models is partial and highly uneven: on the three axes shared by all categories, mean convergence ranges from 0.21 for bookshelves to 0.51 for jars. Convergence depends primarily on whether a category's representational variation aligns with the semantic direction being evaluated, rather than simply on how much the objects vary in shape overall. Cross-model convergence does not imply agreement with human judgments. Based on our findings, we implement a UI prototype that shows how the audit can inform which Kansei descriptors to expose as controls for a given object class and which to withhold. --- ### Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design Interfaces Authors: Luca Bux, Thiago Rios, Ingo Scholtes, Stefan Menzel Published: 2026-08-26 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2608.25876v1 Generative design interfaces increasingly expose semantic controls that let users steer output with concepts such as "more elegant" or "more minimalist," typically encoded by a vision-language model (VLM). A practical question is whether state-of-the-art VLMs represent objects consistently in terms of the same concept. We audit 6 VLMs by ranking untextured 3D objects along Kansei adjective pairs, where Kansei describes affective impressions of product form, with each axis defined as the difference between the text representations of its two poles. Geometric pairs serve as positive controls, and pairs of unrelated adjectives establish an empirical null. Across 10 categories of ShapeNet database, affective axes converge above the null (mean pairwise rank correlation 0.36 vs. 0.14) but below the geometric ceiling (0.44). The agreement between models is partial and highly uneven: on the three axes shared by all categories, mean convergence ranges from 0.21 for bookshelves to 0.51 for jars. Convergence depends primarily on whether a category's representational variation aligns with the semantic direction being evaluated, rather than simply on how much the objects vary in shape overall. Cross-model convergence does not imply agreement with human judgments. Based on our findings, we implement a UI prototype that shows how the audit can inform which Kansei descriptors to expose as controls for a given object class and which to withhold. --- ### How Edge of Stability Hinders SCAFFOLD in Federated Optimization Authors: Anant Khandelwal, Michael Crawshaw, Mingrui Liu Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25873v1 In federated learning, it is well known that heterogeneous data can (in theory) slow down optimization, and much effort has been directed at designing optimization algorithms that are unaffected by data heterogeneity, such as the SCAFFOLD algorithm. Yet, despite strong theoretical guarantees, SCAFFOLD does not usually outperform the much simpler FedAvg in practice. In this work, we propose that this gap is due to the presence of Edge of Stability (EoS) and progressive sharpening in federated optimization, supported by extensive empirical probing. First, we find that EoS-like dynamics occur with both FedAvg and SCAFFOLD under a variety of architectures and hyperparameters. We observe that the equilibrium value of the sharpness is inversely proportional to the learning rate (as in GD), and interestingly, the degree of data heterogeneity (but not the number of local steps) also affects the equilibrium value. Most importantly, we observe that SCAFFOLD's ability to estimate the gradient of the global objective is severely degraded at the EoS, as measured by the correlation between sharpness and SCAFFOLD's error in estimating the global gradient along the optimization trajectory. This suggests a mechanism for SCAFFOLD's lackluster performance in deep learning: with high sharpness at the EoS, SCAFFOLD cannot reliably estimate the global gradient. --- ### CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition Authors: Junjie Meng, Ranxu Zhang, Zi-an Zhang, Shujun Liu, Xiaoning Qi, Xiaozhou Xu, Yanyong Zhang, Hui Xiong, Chao Wang Published: 2026-08-26 Categories: cs.LG arXiv: https://arxiv.org/abs/2608.25871v1 Forecasting in large-scale e-commerce marketplaces is increasingly required to support planning: merchants need to evaluate sales outcomes under future action sequences such as budget schedules, rather than passively predicting what happens next. However, most existing time series forecasting (TSF) approaches remain inherently passive. Even when incorporating operational decisions as auxiliary covariates, they typically optimize for correlation-based extrapolation under historical policies. This design suffers from autoregressive inertia and conflates endogenous market evolution with decision-induced transitions, leading to policy-insensitive rollouts and unreliable counterfactual analysis. To bridge this gap, we propose CEDAR (Controlled and Event-Driven Demand forecasting via Action-aware Residual decomposition), a two-stage framework for robust decision-conditioned simulation. In Stage I, an Action-Interleaved Transformer learns controllable action-conditioned state transitions for rollout under planned interventions. In Stage II, a Residual Correction Module leverages external event signals and LLM-assisted text representations to align noisy event descriptions with product context and correct event-driven deviations. Our study is enabled by a large-scale real-world dataset from Alibaba 1688, comprising approximately 32 million product trajectories with paired state-action sequences and aligned event signals. Extensive offline experiments and online controlled experiments in production demonstrate that CEDAR consistently improves simulation accuracy over strong TSF baselines and delivers practical gains for real-world budget planning. --- ### Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence Authors: Ante Kapetanovic, Kemal Altwlkany, Andro Mercep, Tomislav Duricic, Emanuel Lacic Published: 2026-08-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2608.25869v1 Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter content, and gate iterative refinement in production pipelines, where each judgment is often assumed to be independent of earlier evaluations. We test this assumption using three prompt conditions: no metadata, revision framing, and anchored metadata containing revision, attempt, and prior-score fields. We show that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values. Across 192,000 attempted evaluations (185,271 successful), seven out of the eight evaluated models have 95% task-stratified bootstrap intervals below zero for the total anchored-metadata effect on 20 fixed texts. Cohen's $d$, a standardized measure of the difference between score distributions, reaches an absolute value of 0.71. Token-level analysis of selected model-task probes suggests a threshold-like response pattern: introducing anchored metadata produces a marked redistribution of output-score probabilities, while changing the anchor value within the tested below-threshold range produces comparatively little additional variation. On categorical industry data with human-labeled ground truth, anchored metadata blocks 48% of error corrections and flips 10.18% of correct judgments toward an assigned wrong label, demonstrating the bias extends beyond numerical scoring to categorical decisions. Neither Chain-of-Thought nor a metadata-disregard warning reduces the total effect, although the warning improves the paired accuracy effect relative to baseline in the industry experiment. Reliable LLM evaluation demands careful context engineering rather than an assumption of impartiality. Effective mitigation must be validated for the intended model and task or domain. --- ### LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue Segmentation Authors: Karen Sanchez, Carlos Hinojosa, Albert A. Ávila, Andrea C. Riano-Rojas, Diego H. Romero, Jenny C. Páez, Martina Llinás, Bernard Ghanem Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25866v1 Quantifying wound tissue composition is essential for monitoring chronic ulcer progression and guiding treatment decisions. However, pixel-level annotations are costly, and multi-tissue wound datasets remain scarce, particularly for neglected diseases such as leprosy. We introduce LUTSeg, a longitudinal chronic ulcer dataset comprising 141 images from 39 patients with wound masks and five tissue categories annotated by five expert clinicians, including a multi-expert gold-standard subset for inter-rater agreement analysis. To establish an initial benchmark for LUTSeg, we further propose TiSage, a semi-supervised tissue segmentation framework that integrates multi-scale semantic priors from a frozen medical vision-language model within a teacher-student architecture. We evaluate TiSage on LUTSeg and DFUTissue, showing improvements over supervised and semi-supervised baselines in most low-label settings. Code & data: https://github.com/carlosh93/TiSage --- ### Learning Late, Guiding Early: Timestep-Decoupled Semantic Guidance for Fair Face Generation Authors: Subir Kumar Parida, Rajbabu Velmurugan, Ketan Kotwal, R. S. Sengar, Swati Hiremath Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25862v2 Demographic imbalance in synthetic face generation can propagate to downstream face recognition systems, making fairness an important consideration when diffusion models are used for data generation. Existing fairness-aware generation approaches often require model retraining, architectural modifications, or repeated guidance throughout the reverse diffusion process. In this work, we introduce Semantic Boundary Predictor (SBP), an inference-time framework that performs demographic guidance through a one-shot intervention during reverse denoising. Our approach is motivated by the observation that latent representations at different diffusion timesteps play distinct semantic roles: late-stage latents provide stronger demographic separability, whereas early-stage latents offer greater flexibility for semantic intervention. SBP leverages this timestep decoupling by learning linear semantic boundaries from late-stage latent representations while applying them only once at the initial noisy latent, allowing the remainder of the reverse denoising process to proceed unchanged. The method requires neither retraining nor fine-tuning of the underlying Latent Diffusion Model and operates without external balanced datasets. Experiments on CelebA-HQ demonstrate substantial improvements in demographic fairness, reducing fairness disparity by 98% for gender, 95% for binary race, and 15% for four-class race, while maintaining perceptual image quality across demographic groups. Owing to its one-shot inference strategy and model-agnostic design, SBP introduces only a small computational overhead and can be readily integrated with existing pre-trained latent diffusion models. --- ### Learning Late, Guiding Early: Timestep-Decoupled Semantic Guidance for Fair Face Generation Authors: Subir Kumar Parida, Rajbabu Velmurugan, Ketan Kotwal, R. S. Sengar, Swati Hiremath Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25862v1 Demographic imbalance in synthetic face generation can propagate to downstream face recognition systems, making fairness an important consideration when diffusion models are used for data generation. Existing fairness-aware generation approaches often require model retraining, architectural modifications, or repeated guidance throughout the reverse diffusion process. In this work, we introduce Semantic Boundary Predictor (SBP), an inference-time framework that performs demographic guidance through a one-shot intervention during reverse denoising. Our approach is motivated by the observation that latent representations at different diffusion timesteps play distinct semantic roles: late-stage latents provide stronger demographic separability, whereas early-stage latents offer greater flexibility for semantic intervention. SBP leverages this timestep decoupling by learning linear semantic boundaries from late-stage latent representations while applying them only once at the initial noisy latent, allowing the remainder of the reverse denoising process to proceed unchanged. The method requires neither retraining nor fine-tuning of the underlying Latent Diffusion Model and operates without external balanced datasets. Experiments on CelebA-HQ demonstrate substantial improvements in demographic fairness, reducing fairness disparity by 98% for gender, 95% for binary race, and 15% for four-class race, while maintaining perceptual image quality across demographic groups. Owing to its one-shot inference strategy and model-agnostic design, SBP introduces only a small computational overhead and can be readily integrated with existing pre-trained latent diffusion models. --- ### Precipitation Downscaling Using Foundation Model-Conditioned Diffusion Authors: Victor Nascimento Ribeiro, Jorge Guevara, Jorge Sebastian Moraga, Chris Lucas, Natalie Lord, Andrew Taylor, Edward Lockhart, Will Trojak, Johannes Schmude, Anne Jones Published: 2026-08-26 Categories: cs.CV, cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2608.25858v1 High-resolution precipitation fields are essential for hydrological impact assessment, yet global climate model outputs are too coarse and biased for direct use. AI-based statistical downscaling with diffusion models offers a promising approach, but the mechanism by which large-scale atmospheric predictors condition generation remains largely unexplored. We investigate three conditioning strategies for a denoising diffusion probabilistic model applied to daily precipitation downscaling: channel concatenation of upsampled coarse predictors, cross-attention conditioning with a learned convolutional encoder, and cross-attention conditioning with the frozen encoder of the pretrained Prithvi WxC weather foundation model. All strategies are evaluated against an unconditioned baseline under identical conditions using probabilistic, distributional, spectral, and extreme-event metrics for the Colorado River Basin. Concatenation conditioning achieves the lowest point-wise CRPS and MSE, but tends to produce over-smoothed fields that suppress high-intensity events. In contrast, cross-attention conditioning provides substantially better distributional realism and modest improvements in spectral fidelity. Improvements are greatest for extremes: the Prithvi-WxC conditioned model retains over half of >100mm/day events, although estimates are uncertain due to limited samples. When trained on the full dataset, the learned convolutional model performs similarly to the foundation model-conditioned approach while requiring lower computational resources. However, the Prithvi-WxC-conditioned model achieves comparable performance with only five years of training data. These results indicate that cross-attention conditioning offers advantages over simple concatenation for probabilistic precipitation downscaling, and that pre-trained foundation model representations may offer benefits in data-limited settings. --- ### Unlocking Multimodal Protein Language Models at Inference Time Authors: Yi Zhou, Qipeng Wang, Yunqing Liu, Jun Xia, Qing Li, Wenqi Fan Published: 2026-08-26 Categories: cs.CE, cs.AI arXiv: https://arxiv.org/abs/2608.25855v1 Multimodal protein language models (pLMs) learn joint protein sequence-structure distributions, and their generation performance should also depend critically on inference-time sampling strategies. Yet prior work has focused more on model training than on how inference-time strategies behave. In this paper, we establish a three-stage investigation framework to empirically study the inference design space of multimodal pLMs across three representative pLMs and four fundamental tasks. We evaluate vanilla sampling, task-specific classifier-free guidance, and reward-guided beam search on multimodal pLMs, corresponding to controls over sampling distributions, per-step logits, and parallel trajectories. Throughout the complementary advancements centered on exploration-exploitation trade-off, we (1) reveal the suboptimality of default inference protocols and identify task-oriented sampling preferences; (2) observe substantial quantitative gains across tasks, consistently boosting the upper bound performance of multimodal pLMs without updating model parameters; (3) derive conclusions about base models that differ from prior consensus. --- ### Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware Benchmark Authors: Zhiqiang Shi, Oana Cocarascu Published: 2026-08-26 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2608.25854v1 Key Point Analysis (KPA) aims to identify a concise set of key points that summarize a collection of arguments together with their prevalence. We argue that KPA is fundamentally a structured prediction problem that requires recovering semantic groupings, generating representative key points, ensuring coverage, and estimating prevalence. Under this formulation, we show that existing KPA benchmarks suffer from limitations in grouping quality, redundancy, coverage, and argument-key point mappings, causing ceiling violation and selection failure in reference-based evaluation. To support future research on true KPA, we introduce a structure-aware, distribution-sensitive benchmark built via a human-in-the-loop re-annotation. Human and LLM evaluations consistently show that the resulting structures yield more coherent groupings, higher-quality key points, better coverage, and more reliable prevalence estimates than existing annotations. We further release several annotation resources to support research on KPA evaluation, argument-key point matching, explainable KPA, and LLM-as-a-judge methodologies, and outline a research agenda for true KPA. --- ### DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative Priors Authors: Tuo Chen, Jie Gui, Minjing Dong, Lanting Fang, Ju Jia, Benlei Cui, Jian Liu Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25851v1 Self-supervised learning (SSL) encoders are vulnerable to backdoor attacks, posing threats to both visual SSL encoders and vision-language encoders. Existing defenses are typically designed for only one of these paradigms and rely on restrictive assumptions such as access to uninfected in-distribution data or precomputed pseudo-labels, which are difficult to satisfy in practice. To address these limitations, we propose DEFUSE, a generalizable backdoor detection framework for SSL encoders. Inspired by Bayesian posterior inference, we reformulate backdoor detection as a representation-conditioned image likelihood estimation problem parameterized by a conditional diffusion generative model. Uninfected representations tend to yield semantically consistent reconstructions, whereas backdoored ones are more likely to be mapped to the attacker's target class or semantically meaningless images, deviating from the original semantics and thereby exposing the backdoor. However, we find that the exact likelihood is intractable, because highly abstracted representations discard the low-level information necessary for pixel-faithful reconstruction. We therefore relax the objective to semantic reconstruction and evaluate it in a well-separated representation space provided by a reference encoder. Rather than training from scratch, we fine-tune a pretrained diffusion model, leveraging its generative prior to map data onto the natural image manifold while preserving semantic content. Extensive experiments demonstrate that DEFUSE substantially outperforms existing detectors across diverse attack settings, generalizing to both visual SSL and vision-language encoders. Notably, our method greatly reduces the reliance on prior knowledge about the victim encoder or the attack strategy. The source code is available at https://github.com/jsrdcht/DEFUSE . --- ### Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening Authors: Wensi Zhang, Tomas Teijeiro, Jérôme Thevenot, David Atienza Published: 2026-08-26 Categories: eess.AS, cs.AI, cs.LG, cs.SD, eess.SP arXiv: https://arxiv.org/abs/2608.25846v1 Cough acoustics are promising for non-invasive tuberculosis (TB) screening, yet whether machine learning (ML) models capture disease-related acoustics or artifacts of data collection remains unresolved. We evaluated the cross-dataset generalizability of classical ML and deep learning (DL) cough-based TB classifiers across three independent datasets. Despite moderate within-dataset performance (ROC-AUC up to $0.755 \pm 0.056$), both pipelines fail to generalize, with external performance frequently below 0.6, indicating a possible limitation of the data. We further observed audio representations are organized by recording device and dataset rather than TB status, predicted TB probability tracks country-level prevalence in CODA, and device mismatch degrades transfer while device-diverse training improves it. Additionally, a clinical-variable baseline generalizes more consistently (ROC-AUC $0.655 - 0.711$), indicating acquisition-specific variability is a stronger driver of poor generalizability than population shift. High within-dataset performance is not enough. External validation is essential before cough-based TB models are clinically ready. --- ### THA-Flow Generative Model: Prosthesis Geometry Prediction from Preoperative CT Authors: Yiping Wang, Jie Li, Jingyu Shen, Liao Wang Published: 2026-08-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2608.25845v1 Preoperative planning for total hip arthroplasty (THA) is commonly framed as selecting a single prosthesis configuration and placement for a patient's osseous anatomy. In practice, however, the same anatomy may admit several clinically reasonable solutions, making planning inherently a one-to-many problem that is better represented by a conditional probability distribution. We present THA-Flow, a conditional flow-matching model that generates three-dimensional prosthesis geometry directly from preoperative CT. Separate AutoencoderKL models compress preoperative bone anatomy and prosthesis geometry, while a three-dimensional UNet learns a rectified flow from Gaussian noise to the prosthesis latent space under spatial bone conditioning and optional structured prosthesis parameters. The retrospective cohort comprised 1,355 hips from 1,149 patients undergoing primary THA. Following rigid registration of postoperative CT to preoperative CT, the actual postoperative prostheses were transformed independently according to the pelvic and femoral registrations and represented as a dual-channel truncated signed distance field. The prosthesis autoencoder achieved a peak signal-to-noise ratio of 47.11 dB and a structural similarity index of 0.9964 on the validation set. Complete acetabular and femoral geometries were generated across seven major stem models representing 93.4% of the cohort. Repeated bone-conditioned sampling preserved component position, alignment, and the principal bone-prosthesis interfaces while allowing limited local geometric variation. To our knowledge, THA-Flow represents the first application of generative AI to three-dimensional surgical planning for THA. --- ### VINCENT: Validated Interaction Network for Cross-drug Explanation of Therapeutics Authors: Fan-Sheng Chuang, Xuchen Li, Yujing Bian, Kaixiong Zhou Published: 2026-08-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2608.25841v1 Drug synergy prediction estimates whether two drugs produce a stronger joint effect than expected from their individual activities. For drug combination discovery, a single synergy score is often not enough: researchers also need to know which molecular regions jointly drive the prediction. We study motif-pair synergy explanation, which identifies pairs of chemically coherent regions, one from each drug, that jointly contribute to predicted synergy. Existing interpretable synergy models expose atom- or substructure-level signals, but their explanations are built into the predictor architecture, and none validates cross-drug region scores under repeated perturbations or feeds that evidence back to refine the explanation. A reliable motif-pair explanation should instead be chemically coherent, perturbation-stable, and aligned with predictor behavior. We introduce VINCENT (Validated Interaction Network for Cross-drug Explanation of Therapeutics), a post-training framework for a fixed interaction-aware synergy predictor. VINCENT extracts atom-pair evidence from attention and gradient signals, groups atoms into chemically coherent motifs, and validates candidate motif pairs through repeated local perturbations. The validated evidence is fed back to refine motif assignments, yielding explanations that satisfy these three criteria. On a 25-pair literature-annotated subset, VINCENT achieves a mean motif recall of 0.826 (95% CI: 0.78-0.87), compared with 0.49-0.66 for baselines. Across all 71 test pairs, its validated interaction scores yield a TP/TN separation of 3.36. These results show that closed-loop perturbation validation recovers literature-supported molecular regions more accurately than existing alternatives while producing cross-drug interaction scores that better reflect predictor behavior. ---