探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13468

Understanding the Rejection of Fixes Generated by Agentic Pull Requests – Insights from the AIDev Dataset

作者:

Mahmoud Abujadallah↗Ali Arabat↗Mohammed Sayagh↗

arXiv:2606.13468v1 Announce Type: cross Abstract: AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46.41\% of the fixes proposed by the agents Copilot, Devin, Cursor, and Claude are rejected. This represents a significant amount of wasted resources that require human reviews, verifications, and running tests and validations for fixes that are merely discarded. Our goal in this paper is to understand the failure modes of AI-agents, an understanding that is crucial for better integrating AI-agents as efficient teammates. In this paper, we conduct a qualitative study on a representative sample of 306 non-merged pull requests created or co-authored by the agents mentioned earlier, followed by a quantitative analysis of the reasons for rejection. Our qualitative findings identify 14 reasons divided into four high-level categories for rejecting AI-agent fixes. We observe that developers can reject fixes due to fixes whose implementation is incorrect (e.g., incomplete, wrong approach), fixes that do not pass the continuous integration (CI) pipelines and fail tests, fixes for which the agent is unable to perform the implementation (e.g., no code generated, sessions lost), and fixes whose priority is low. Our results shed light on the importance of better guiding the model at these levels: (1) proposing hints about the approach to follow for fixing an issue, (2) outlining constraints or limitations regarding the approaches that should not be taken, and (3) instructing the agent on how to validate the implementation through CI pipelines and without introducing a breaking change. Our results suggest the need for good prioritization of tasks so that generated fixes do not lead to wasted human review efforts or wasted agent resources (e.g., tokens, compute, or allowed number of requests).

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.15275

MamBOA: State-Space Architecture for Video Recognition

作者:

Mustafa Bora \c{C}elik↗

Fine-grained action recognition demands temporal reasoning that general-purpose architectures address through different cost-accuracy tradeoffs: 3D dense operators couple computation to the input volume, while difference-based methods approximate motion through rigid, hand-crafted subtraction of uncontextualized features - each reflecting a deliberate design choice with corresponding limitations in expressiveness or flexibility. We present MamBOA, a backbone-agnostic temporal framework built upon a novel interleaved scan structure that recasts the selective state-space recurrence (S6) as a native motion synthesizer. By interleaving consecutive feature representations extracted from a pretrained backbone into a single alternating sequence, the proposed scan structurally drives the recurrence to encode both temporal observations of each position within a shared hidden state, separated by only a single decay step - rendering the inter-frame transition an intrinsic component of the state dynamics rather than an externally computed quantity. A cascade of dedicated alignment and decoding operations then distills this joint encoding into an explicit motion representation, which a dual-path pooling mechanism adaptively aggregates by balancing attention-driven selection with uniform temporal coverage. The framework interfaces seamlessly with CNN, Transformer, and Mamba backbone families, adding only ~2.1 GFLOPs per feature pair. On Diving48, MamBOA achieves 85.02% Top-1 accuracy with an image-pretrained backbone and 86.24% with a video-pretrained backbone processing the entire video in a single forward pass - demonstrating that structurally induced state-space dynamics constitute a principled and general foundation for motion modeling.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.01730

Evidence-Gated LLM Priors for Multi-Objective Bayesian Optimization

作者:

Jiangyu Chen↗Ban Yi↗

arXiv:2606.01730v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used as heuristic advisors for black-box optimization, yet their suggestions and self-reported confidence are not necessarily calibrated to downstream objective values. This issue becomes more pronounced in multi-objective Bayesian optimization, where different objectives may require different expert knowledge and where an LLM expert can be useful for one objective but misleading for another. We study how to use LLM-generated expert priors in discrete multi-objective Bayesian optimization without blindly trusting them. We propose an objective-wise reputation-market mechanism that treats each expert-objective pair as a falsifiable prior source. Expert weights are updated online from observed objective feedback, discounted over time, and gated by market-level trust. We then introduce a decoupled counterfactual gate that can use the LLM prior without confidence, use it with confidence, or abstain from the LLM prior entirely. Across controlled synthetic stress tests and three molecule optimization benchmarks with \qwenflash{}-generated expert priors, we find that dynamic objective-wise calibration improves robustness over fixed LLM priors. However, raw LLM confidence is not reliably beneficial: on ESOL, confidence is positively correlated with prediction error; on FreeSolv, confidence can help; and on Lipophilicity, ignoring confidence remains strongest. Our fixed three-arm counterfactual gate improves over the first counterfactual variant on ESOL and FreeSolv, while an attempted margin portfolio exposes a useful negative result: margin selection should be acquisition-aware rather than based only on one-step prior error.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.18431

Beyond Prediction: Tail-Aware Scheduling for LLM Inference

作者:

Yueying Li↗Yuanfan Chen↗Jiayang Chen↗Esha Choukse↗Haoran Qiu↗G. Edward Suh↗Rodrigo Fonseca↗Ziv Scully↗Udit Gupta↗

arXiv:2606.18431v1 Announce Type: new Abstract: LLM serving exhibits extreme length variability, making size-based scheduling difficult in practice. Recent LLM schedulers approximate SJF/SRPT using predicted decode lengths or ranks and primarily report mean-centric metrics such as TTFT and TBT. We show that these prediction-driven policies can be fragile under distribution shifts, bursty arrivals, and GPU memory pressure, while offering limited control over the tail latency (P90-P99) that dominates user experience, even with perfect decode-length knowledge. We introduce a distribution-aware, prediction-free scheduling framework that replaces explicit length prediction with soft priority boosting driven by lightweight statistical signals. Our design co-optimizes scheduling and cache-aware preemption to account for memory-coupled decode dynamics across workload mixes. Evaluated on production and open-source traces, our method reduces P99 TTLT by up to 35-50% relative to SRPT with perfect length knowledge and reduces TTFT by 34-47% across workloads, including reasoning-heavy and chat-heavy tasks. These results demonstrate a robust alternative for optimizing tail latency in online LLM serving.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20210

Augmenting Game AI with Deep Reinforcement Learning

作者:

Alessandro Sestini↗Joakim Bergdahl↗Amir Baghi↗Jean-Philippe Barrette-LaPierre↗Florian Fuchs↗Linus Gissl\'en↗

arXiv:2606.20210v1 Announce Type: new Abstract: Immersion in video games depends not only on graphics, audio, and game mechanics, but also on the quality of in-game characters. Producing believable characters, or game AI, remains a significant challenge as behavioral complexity is hard to capture with hand-coded systems. Game AI is a source of immersion and engagement; however, the limitations stemming from the challenges of creating game AI often lead to frustration and the breaking of the illusion of realism within the game. The introduction of machine learning models opens the door to creating more believable, authentic, and relatable characters in games. The promise is that they either learn from interacting with the game, or from player data, to develop true human-like behavior. In this paper, we envision more applications of reinforcement learning for game AI in the future. For this to materialize, current research limitations are prohibitive to broad deployment across game genres. Therefore, we propose a framework for training reinforcement learning models with a set of requirements in mind that are suited towards game AI and game development. We present examples of games with reinforcement learning-augmented game AI and describe the practicalities of deploying player-facing machine learning agents in modern games. Furthermore, we identify bottlenecks and hard problems in these areas, which we believe offer promising research directions to accelerate the adoption of machine learning in game AI for the video game industry.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.16009

Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design

作者:

Claudio Fantinuoli↗

Machine interpreting (MI), the live, real-time branch of speech translation, has achieved remarkable progress on standard benchmarks, with some systems approaching human parity on textual fidelity. Yet the user experience remains far inferior to interpreter-mediated communication, revealing what we term the accuracy illusion: systems that appear accurate on paper but fail in practice to support smooth, goal-oriented interaction. This paper defines MI as a distinct subfield of speech translation, with its own characteristics and the need for evaluation methods grounded in communicative effectiveness rather than isolated fidelity metrics. Drawing on insights from interpreting studies, we identify critical dimensions of professional interpreting practice that are overlooked by current systems, and consolidate them into three interdependent design priorities for future MI: agency (context-sensitive initiative and repair), grounding (multimodal and discourse-level situational awareness), and experience (adaptive improvement through real interaction). Together, these priorities chart a path toward closing the usability gap and enabling systems that can sustain authentic multilingual communication in real time.

阅读与讨论 → 访问原文 →

07.

medRxiv (Medicine) 2026-06-22 DOI: HASH:79bfa8e43bebe84179d3aa5324c087d2

Symptom-based phenotype discovery in motor neuron disease using natural language processing of electronic health records

作者:

Abdulle↗Dinu↗Wu↗Kim↗Budhdeo↗Yao↗Tomlinson↗Al-Chalabi↗Dobson↗Iacoangeli↗

Background: Motor neuron disease (MND) is a fatal neurodegenerative condition with significant clinical heterogeneity that is incompletely captured by existing phenotype classifications based on onset site. Electronic health records (EHRs) contain detailed symptom documentation in clinical narratives that may enable data-driven discovery of clinically meaningful patient subgroups. Methods: We developed a natural language processing (NLP) pipeline using MedCAT to extract symptoms from clinical notes of 2,361 people with a confirmed diagnosis of MND at a tertiary neurology center. MND cohort confirmation used three complementary methods: clinic attendance records, text-based diagnosis detection, and NLP extraction with negation detection. Extracted symptoms were filtered to Unified Medical Language System semantic type T184 (Sign or Symptom) with removal of negated concepts. Patients were clustered using latent class analysis on binary symptom profiles. Survival differences were assessed using Kaplan-Meier analysis, log-rank tests, and Cox proportional hazards regression. Results: From the first clinical notes, we identified four clusters of symptoms among 872 patients and 76 symptoms: Motor-Bulbar (n=373), Motor-Tremor (n=154), Sensory-Pain (n=222), and Motor-Respiratory (n=123). When extended to all clinical notes (n=2,065; 184 symptoms), these reorganized into three clusters: Autonomic-Respiratory (n=472), Nocturnal-Respiratory (n=338), and Classic Motor (n=1,255). Survival differences were significant across all clusters in both the first notes and all notes analyses (log-rank p < 0.001). Conclusions: NLP-based symptom extraction from EHRs identifies clinically meaningful MND subgroups that extend beyond traditional onset-site classifications. Autonomic-respiratory symptom burden is associated with poorer survival while a newly identified Sensory-Pain subtype with a better prognosis. These data-driven phenotypes may improve prognostication and inform targeted supportive care.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2310.05753

Large-Scale OD Matrix Estimation with A Deep Learning Method

作者:

Zheli Xiong↗Defu Lian↗Enhong Chen↗Gang Chen↗Xiaomin Cheng↗

arXiv:2310.05753v2 Announce Type: replace Abstract: The estimation of origin-destination (OD) matrices is a crucial aspect of Intelligent Transport Systems (ITS). It involves adjusting an initial OD matrix by regressing the current observations like traffic counts of road sections (e.g., using least squares). However, the OD estimation problem lacks sufficient constraints and is mathematically underdetermined. To alleviate this problem, some researchers incorporate a prior OD matrix as a target in the regression to provide more structural constraints. However, this approach is highly dependent on the existing prior matrix, which may be outdated. Others add structural constraints through sensor data, such as vehicle trajectory and speed, which can reflect more current structural constraints in real-time. Our proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. This approach combines the advantages of both deep learning and numerical optimization algorithms. The neural network(NN) learns to infer structural constraints from probe traffic flows, eliminating dependence on prior information and providing real-time performance. Additionally, due to the generalization capability of NN, this method is economical in engineering. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset. Subsequently, we verified the stability of our method on real traffic data. Our experiments provided confirmation of the benefits of combining NN and numerical optimization.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12160

A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs

作者:

Ao Sun↗

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token. Our method extracts a compact set of features such as maximum, minimum, mean, standard deviation, and slope-from the token logits across all layers, enabling effective hallucination detection without overfitting. Experiments on TruthfulQA and MMLU datasets demonstrate that CHAIR significantly improves detection accuracy, particularly in zero-shot scenarios, showcasing its robustness and generalizability. Beyond hallucination detection, CHAIR highlights the potential of using internal representations for designing advanced decoding strategies. By leveraging patterns in logits, we suggest that more sophisticated models and adaptive decoding methods could further reduce hallucinations and enhance text completion quality. CHAIR not only offers a practical solution for detecting hallucinations but also lays the groundwork for exploring richer representations in LLMs to improve their factuality and coherence.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15735

EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries

作者:

Jiyoun Kim↗Muhan Yeo↗Eunhye Jang↗Jeewon Yang↗Hangyul Yoon↗Su Ji Lee↗Hee Jo Han↗Hee-Jae Jung↗Doyun Kwon↗Jun young Lee↗Jaehun Lee↗Jung-Oh Lee↗…

Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple summaries while verifying the evidence supporting each answer. Although large language models (LLMs) are increasingly explored for clinical question answering, existing benchmarks do not sufficiently reflect this setting: they often evaluate exam-style medical knowledge or focus on single-turn question answering with limited evidence-grounding evaluation. We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries. Built from de-identified MIMIC-IV discharge summaries, EHRNote-ChatQA contains 967 patient-level multi-turn samples spanning one to five notes and 16,072 medical-expert-verified QA pairs (8,036 content questions, each paired with an evidence-grounding question) across eight clinical categories. The benchmark is constructed through an expert-informed pipeline combining discharge-summary structuring schema, expert-curated multi-turn QA templates, and LLM-based generation, followed by review and revision of every single QA sample by 11 medical experts. Benchmarking 22 open- and closed-source LLMs reveals several challenges, including that LLMs struggle more with evidence grounding than content answering, multi-turn errors compound across turns, and single-turn clinical QA performance does not reliably transfer to this setting. These findings establish EHRNote-ChatQA as a rigorous and practical benchmark for evaluating clinical QA systems. The dataset will be made publicly available through PhysioNet credentialed access.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2509.10005

TUNI: Unifying Pre-training and Fine-tuning with Modality-Aware Mutual Learning and Rectification for RGB-T Semantic Segmentation

作者:

Xiaodong Guo↗Xianda Guo↗Tong Liu↗Zhihong Deng↗Yanlun Peng↗Xiang Li↗Wujie Zhou↗

RGB-thermal (RGB-T) semantic segmentation improves the environmental perception of autonomous platforms in challenging conditions. Prevailing RGB-T segmentation frameworks suffer from suboptimal multi-modal feature extraction and fusion, unbalanced modality dependency, and inadequate utilization of thermal information. To address these challenges, we propose TUNI, a unified pre-training and fine-tuning framework for efficient and real-time RGB-T semantic segmentation. It pre-trains an RGB-T encoder that incorporates an RGB-T local module that selectively emphasizes salient consistent and distinct local features across modalities, thereby integrating cross-modal feature extraction and fusion in a unified manner. To alleviate the modality bias issue during RGB-T pre-training, modality-inverted contrastive mutual learning is introduced to enable knowledge exchange between two RGB-dominated and thermal-dominated encoders. In the fine-tuning phase, modality rectification learning fully exploits residual thermal information by focusing on correct yet divergent prediction regions between two modality-specific decoders. We further develop three TUNI variants, covering lightweight, balanced, and high-performance requirements. Extensive experiments on five RGB-T semantic segmentation datasets demonstrate that TUNI achieves superior accuracy, generalization, and compactness compared with 15 state-of-the-art models. The code is available at https://github.com/xiaodonguo/TUNI-v2.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20076

Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers

作者:

Dong Hoon Lee↗Seunghoon Hong↗

arXiv:2606.20076v1 Announce Type: cross Abstract: Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Variable-length tokenizers (VLTs) promise adaptive compression by varying token counts, allowing diffusion models to flexibly balance quality and compute. However, conventional VLTs modulate length by truncating ordered token sequences, which makes token semantics depend on token position and breaks representational alignment across lengths. This leads to a cross-length shift in the latent distribution that hinders a single variable-length diffusion model from operating effectively. To address this, we propose a novel variable-length tokenizer that modulates length by merging tokens. We show that encouraging similar tokens to merge enables direct cross-length representation alignment when the diffusion transformer operates according to the merging pattern. Since conventional merging methods are data-dependent, making the merging pattern inaccessible during generation, we introduce learnable global merging, which is data-independent, to ensure compatibility with diffusion transformers. On ImageNet 256$\times$256 generation, our merging-based variable-length tokenizer integrated with a diffusion transformer achieves a superior gFID-compute trade-off compared to prior VLT methods. Code is available at [this https URL](https://github.com/movinghoon/lgm)

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2602.00593

Pix2Fact: When Vision Is Not Enough – Benchmarking Fine-Grained VQA with Web Verification on High-Resolution Real-World Scenes

作者:

Yifan Jiang↗Cong Zhang↗Bofei Zhang↗Qiaofeng Zheng↗Yifan Yang↗Bingzhang Wang↗Yew-Soon Ong↗

Despite progress on general tasks, vision-language models (VLMs) still struggle with challenges that demand both fine-grained visual grounding and external knowledge, a synergy overlooked by existing benchmarks that evaluate these abilities in isolation. To fill this void, we introduce Pix2Fact, a visual question-answering benchmark designed to assess expert-level visual perception and knowledge search. Pix2Fact comprises 1,000 high-resolution (4K+) images spanning eight scenarios. Its questions and answers are meticulously crafted by PhD-holding annotators from top global universities across diverse disciplines. Each question requires detailed visual grounding and the integration of external knowledge. Evaluating ten state-of-the-art VLMs, including proprietary models such as Gemini-3.1-Pro and GPT-5.4, we find that Pix2Fact poses a formidable challenge: the most advanced model (Gemini-3.1-Pro) achieves only 51.7% average accuracy, even with access to visual ground truth and search tools. Our analysis attributes this low accuracy to three factors, frequent visual grounding errors even with visual ground truth, shallow search harnessing, and VLM's inability to retrieve long-tail, unstructured local information. This striking gap exposes the limitations of current models in assisting humans with real-world scenarios that demand overwhelming visual comprehension. We believe Pix2Fact will serve as a critical benchmark to drive the next generation of language-vision agents that seamlessly integrate fine-grained perception with robust knowledge search.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14555

Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner

作者:

Aray Karjauv↗

Modern image classifiers widely adopt global average pooling (GAP) followed by a linear classification head. This linearity ensures that the image-level logits equal the average of logits obtained by applying the classification head pointwise to the feature grid prior to GAP. Consequently, standard classifiers may inherently retain spatial class evidence that remains recoverable even when the image-level prediction is incorrect. This structure naturally suggests a multiple-instance learning (MIL) interpretation, where an image is viewed as a bag of spatial instances. Within this formulation, we demonstrate that standard classifiers trained with a single label per image can still learn the intended classification task in multi-object scenes. We further exploit this property to decompose image-level logits into a prediction grid, providing a post-hoc diagnostic to extract spatial class evidence that GAP otherwise obscures. Our systematic evaluation reveals that off-the-shelf models consistently recover the ground-truth class within foreground regions. The MIL interpretation further suggests that common classifier failures reflect known limitations of mean aggregation.

阅读与讨论 → 访问原文 →

15.

medRxiv (Medicine) 2026-06-17 DOI: HASH:78c2a7dab257abe9176b09b85e7085e5

Womens intentions and motivations towards health behaviour change before pregnancy: a cross-sectional survey of pregnant women in Australia

作者:

Steel↗Schoenaker↗McIntyre↗Rogers↗Hall↗Adams↗

Introduction: The preconception period (i.e. the weeks and months before pregnancy) is a critical window during which parental health behaviours can influence pregnancy outcomes and the childs long-term health. Modifiable factors such as nutrition, physical activity, substance use, and environmental exposures play a key role, yet womens ability to adopt and sustain healthy behaviours is shaped by complex psychological, social and environmental influences. This study applies the Theory of Planned Behaviour to identify the beliefs underpinning womens preconception behaviours, with the aim of informing support for effective and sustained health behaviour change. Methods: An Australian national retrospective cross-sectional survey of pregnant women (18-49 years), recruited through social media platforms. The 92-item survey captured respondent socio-demographics, pregnancy status and health conditions, health behaviours, and beliefs regarding preconception health behaviours. Respondents level of pregnancy planning was categorised using the London Measure of Unplanned Pregnancy (LMUP). Items regarding preconception beliefs were structured in accordance with the Theory of Planned Behaviour, with a focus on regular exercise, healthy diet, and alcohol avoidance. These beliefs variables were analysed using structured equation modelling to identify paths between latent variables and the items used to estimate each concept. Results: The study was completed by 430 pregnant women of whom 72.7% had a planned pregnancy. Most had a partner, were university educated and in good health. Structural equation modelling showed intention strongly predicted exercise ({beta}=0.65), healthy diet ({beta}=0.54) and alcohol avoidance ({beta}=0.64). Perceived control and partner norms influenced intentions, whereas health professional norms had limited effect. Positive beliefs were associated with folate supplement use and smoking cessation. Conclusion: These findings highlight intention as a key driver of preconception health behaviours, with perceived control and partner influences playing a more significant role than individual beliefs or health professional input. Effective interventions should therefore address structural barriers and actively involve partners, while respecting womens autonomy. Overall, couples-focused, multi-level strategies are likely essential to support meaningful and sustained preconception health behaviour change.

阅读与讨论 → 访问原文 →

16.

bioRxiv (Bioinfo) 2026-06-17 DOI: HASH:dc3385c7abbb1b7ce9089f1f710e72a9

Posterior-calibrated multimodal motor states reveal longitudinal and imaging-associated heterogeneity in Parkinson's disease

作者:

Tirhekar↗H. M↗Yadav↗Bajaj↗C. l↗

Parkinson's disease (PD) motor heterogeneity is commonly summarized by hard subtype labels, although clinical states vary longitudinally, severity can dominate unsupervised structure, and model uncertainty is rarely calibrated. We developed a posterior and refit-stability calibrated multimodal motor state framework that assigns probabilistic MDS-UPDRS-III motor states, aggregates them at the patient level, separates global burden from residual tremor-axial profile, and tests whether imaging can recover the resulting posterior distribution. In 29,366 aligned PPMI motor-posterior visits spanning 4,773 participant identifiers, patient-level state families were stable on average (modal-family fraction 0.925; 95% CI 0.921 - 0.930), but 25.5% of patients transitioned state over follow-up (95% CI 24.1 - 26.7%). PD-only cohort definitions produced smaller denominators and are reported as sensitivity cohorts with rerun calibration and imaging-posterior checks. Severity and covariates explained substantial motor-domain variance, especially bradykinesia (rsecond=0.850), but residual profile modeling retained five active components across total-severity, principal-component, leave-one-domain, non-target-burden, and clinical-only severity axes. Refit-stability calibration with 250 patient-blocked bootstrap refits showed high nominal posterior confidence (0.989) but lower empirical label consistency (0.849), quantifying overconfidence rather than hiding it. Patient-held-out temporal modeling predicted future axial burden (best XGBoost rsecond=0.605) and future state transition (XGBoost AUC=0.830; 95% CI 0.822 - 0.837). DaTSCAN plus FreeSurfer ROI features predicted patient-level soft motor posterior vectors (RF jsd=0.209; 95% CI 0.199 - 0.220; macro-AUROC=0.692), while severity/demographic-adjusted imaging features further improved soft posterior recovery (jsd=0.188). BioFIND transfer reproduced clinically meaningful endpoint gradients after state assignment in 225 external patients, supporting external face validity rather than definitive transportability. These results support PD motor phenotypic states as calibrated, dynamic, clinically interpretable profiles with convergent imaging associations, not as definitive biological subtypes.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13657

Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation

作者:

Guo Yu↗Wenlin Liu↗Yulan Hu↗Hao-Xuan Ma↗Jun-Peng Jiang↗Han-Jia Ye↗

arXiv:2606.13657v1 Announce Type: new Abstract: On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe as it combines two desirable ingredients: on-policy student trajectories and dense teacher supervision, yet how this hybrid changes a model's parameters remains unclear. Across several language and vision-language model pairs and use cases, our analysis yields two main findings. On sparsity, \textsc{OPD}-style updates are small and coordinate-sparse. They are distributed across layers and are usually FFN-heavy. This sparse structure is operationally useful: training only the discovered subnetwork recovers nearly the same performance as full \textsc{OPD}. However, the sparsity-inducing SGD optimizer underperforms AdamW in our optimizer ablation, likely because dense teacher supervision preserves heterogeneous coordinate-wise gradient scales where AdamW's adaptive scaling remains useful. On geometry, the updates are numerically full-rank but spectrally concentrated; they lie mostly away from the principal singular subspaces of the source weights and fall disproportionately on coordinates where the source weights are close to zero. These findings suggest that dense teacher supervision does not turn \textsc{OPD} into ordinary dense parameter rewriting; instead, \textsc{OPD} retains important geometric signatures of on-policy post-training.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19883

Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning

作者:

Ananya Kunisetty↗Avishek Ghosh↗

arXiv:2606.19883v1 Announce Type: new Abstract: We study a multi-agent multi-armed bandit problem in the competitive setup with two-sided matching markets under a human centric decision making model. To capture human preferences, we use cumulative prospect theory (CPT) that weighs the actions of the agent in a nonlinear fashion using a ($\alpha$-Hölder continuous) weight function. CPT has been widely used in behavioral economics and risk sensitive machine learning to emulate human preferences. We analyze the state-of-the-art learning algorithm with CPT weight distorted rewards and obtain a player optimal regret of $\mathcal{O}(K\log T \left(\frac{1}{\Delta}\right)^{2/\alpha})$, where $K$ denotes the number of arms, $T$ is the learning horizon, and $\Delta$ represents (suitably defined) players' minimum preference gap. Noticing the dependence on $\Delta$ to be sub-optimal, we further improve this regret by judiciously selecting the active set of arms during exploration, which removes the dependence on $K$ in the dominant term and achieves an improved (optimal) regret guarantees in the setting where the number of arms $K$ is significantly larger than the number of players $N$. In addition, we consider adversarial markets where the observed rewards of the agents may be corrupted. We propose and analyze algorithms for robust markets with CPT as risk sensitive measure in both settings where the total corruption budget is known and where it is unknown, and establish logarithmic player-optimal regret guarantees in both cases.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2605.07821

Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis

作者:

Boyang Dai↗Chaoqi Chen↗Yizhou Yu↗

arXiv:2605.07821v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is crucial for ensuring the reliability of deep learning models. Existing methods mostly focus on regular entangled representations to discriminate in-distribution (ID) and OOD data, neglecting the rich contextual information within images. This issue is particularly challenging for detecting near-OOD, as models with simplicity bias struggle to learn discriminative features in disentangled representations. The human visual system can use the co-occurrence of objects in the natural environment to facilitate scene understanding. Inspired by this, we propose an Object-Centric OOD detection framework that learns to capture Object CO-occurrence (OCO) patterns within images. The proposed method introduces a new OOD detection paradigm that understands object co-occurrence within an image by predicting disentangled representations for the test sample, then adaptively divides patterns into three scenarios based on object co-occurrence patterns observed in ID training data, and finally performs OOD detection in a divide-and-conquer manner. By doing so, OCO can distinguish near-OOD by considering the semantic contextual relationships present in their images, avoiding the tendency to focus solely on simple, easily learnable regions. We evaluate OCO through experiments across challenging and full-spectrum OOD settings, demonstrating competitive results and confirming its ability to address both semantic and covariate shifts. Code is released at https://github.com/Michael-McQueen/OCO.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19782

AgentFinVQA: A Deployable Multi-Agent Pipeline for Auditable Financial Chart QA

作者:

Aravind Narayanan↗Shaina Raza↗

Financial chart question answering in regulated settings demands more than accuracy: practitioners must know which answers to trust before acting on them, and many institutions cannot send client data to external model providers. Yet existing chart-QA agents are accuracy-focused and opaque, and most assume proprietary API access; to our knowledge, none combines auditability with on-premise deployability without significant accuracy compromise. We present AgentFinVQA, a multi-agent pipeline that decomposes each query into planning, OCR, legend grounding, visual inspection, and verification, recording every step in a traceable Model Evaluation Packet (MEP) per sample. On FinMME, AgentFinVQA improves $+7.68$ pp over a primary-backbone matched zero-shot baseline with a proprietary backbone (Gemini-3 Flash; 71.24% vs. 63.56%, McNemar $p \approx 1.1 \times 10^{-16}$), and $+4.84$ pp with open-weights Qwen3.6-27B-FP8 served locally. The verifier's verdict also serves as a useful confidence signal (68.2% vs. 55.6% exact accuracy on confirmed vs. revised answers), enabling human-in-the-loop review routing. Error analysis shows that question misunderstanding, legend confusion and extraction error account for nearly two-thirds of failures and are the categories least detected by the verifier, identifying clear directions for future work. Together these results show that auditable, on-premise financial chart QA is practical and that the open-weights system keeps most of the accuracy gains while enabling full data residency. We release our code to support reproducible evaluation.

阅读与讨论 → 访问原文 →

21.

medRxiv (Medicine) 2026-06-12 DOI: HASH:5a9a743a2ac5f8e6bf0ef4d6c10175de

Room-Specialized Mixture-of-Experts for In-Home ADL Recognition with Ambient Sensors

作者:

Addepalli↗V. r↗Rao↗Kiselica↗Kummerfeld↗Abdalnabi↗Lee↗

Monitoring activities of daily living (ADLs) in the home is a promising approach for tracking dementia progression in older adults. While ambient sensor-based ADL systems are well-studied, most existing ADL recognition systems rely on globally trained models that ignore the spatial organization of in-home activities. In real deployments, where training data are sparse and highly home-specific, global transformer models may fail to capture room-dependent behavioral structure. We propose a deterministic Mixture of Experts (MoE) architecture for in-home ADL recognition, in which each expert is a compact transformer specialized to one room of the home (bedroom, kitchen, bathroom, living area). Input segments are routed using a deterministic gating strategy based on room-level motion activity and time-of-day priors for sleep-related behaviors. Unlike learned routing networks, the proposed gate encodes domain knowledge about where ADLs are likely to occur, reducing model complexity under limited per-home training data. By decomposing ADL recognition into room-specific activity spaces, the proposed architecture reduces competition between dominant and low-frequency activities under highly imbalanced residential data. We evaluated the system on data collected via low-cost ambient sensors (motion, light, temperature, humidity) and Raspberry Pi edge devices across five homes, with ground-truth ADL labels provided by participants and caregivers. Across the five homes, the proposed MoE consistently outperformed global transformer, 1D CNN, and Random Forest baselines, achieving macro-F1 scores ranging from 0.60 to 0.88, highlighting the importance of home-specific modeling in real-world deployments. These findings suggest that room-aware expert specialization may provide a practical and interpretable strategy for low-data ADL recognition in real-world residential environments.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13370

A Quantitative Experimental Repeated Measures Study of Training Dynamics in a Small Llama Style Language Model Under a Compute-Aware Token Budget

作者:

Joe Dwyer↗

arXiv:2606.13370v1 Announce Type: new Abstract: This study examines training dynamics in a small Llama-style language model trained under a fixed, compute-constrained token budget. Rather than evaluating efficiency solely through endpoint performance, the study uses a quantitative experimental repeated measures design to analyze how validation loss, validation perplexity, rolling volatility, backslide behavior, spike behavior, and between-seed variability change across token-based training intervals. Six independent training runs were conducted on a 4.26-million-parameter model using the TinyStories corpus, CPU-based full-precision training, and a target budget of approximately 20 million cumulative training tokens. Metrics were collected across 21 intervals, producing 126 seed-by-interval observations. Repeated measures ANOVA showed statistically significant interval effects for validation loss, validation perplexity, and rolling volatility. Descriptive trajectories revealed rapid early improvement followed by non-monotonic degradation during later training intervals. Mean validation loss decreased from 8.3552 at initialization to 2.7996 near 4 million tokens, but increased to 3.9010 by the final checkpoint. Validation perplexity followed the same pattern, falling sharply early in training before rising later. Derived telemetry further showed recurrent validation-loss backslides and no interval-summary evidence of a stable phase under the predefined criteria. These findings suggest that compute-aware language model evaluation should examine training trajectories rather than endpoint metrics alone. In constrained compute settings, additional token exposure may increase computational cost without producing proportional generalization gains, and interval-level telemetry can reveal instability, regression, and diminishing returns that final metrics may obscure.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2507.05019

Meta-Learning Transformers to Improve In-Context Generalization

作者:

Lorenzo Braccaioli↗Anna Vettoruzzo↗Prabhant Singh↗Joaquin Vanschoren↗Mohamed-Rafik Bouguelia↗Nicola Conci↗

arXiv:2507.05019v2 Announce Type: replace-cross Abstract: In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are costly to store, difficult to evaluate for quality and balance, and pose privacy and ethical concerns due to the inclusion of sensitive information. Motivated by these limitations and risks, we propose an alternative training strategy where we leverage a collection of multiple, small-scale, and domain-specific datasets. We empirically demonstrate that the increased quality and diversity of such data improve the generalization abilities of in-context learners beyond their training domain, while achieving comparable performance with models trained on a single large-scale dataset. We investigate this paradigm by leveraging meta-learning to train an in-context learner on the Meta-Album collection under several settings. Firstly, we show the performance in a controlled environment, where the test domain is completely excluded from the training knowledge. Secondly, we explore the robustness of these models to forgetting in a continual scenario where the information is accessible for a limited time. Finally, we explore the more challenging unsupervised scenario. Our findings demonstrate that transformers still generalize for in-context prediction when trained on a curated dataset collection while offering advantages in modularity and replaceability.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2512.03503

Understanding LLM Reasoning for Abstractive Summarization

作者:

Haohan Yuan↗Haopeng Zhang↗

Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, evaluating both summary quality and factual faithfulness. Our results show that reasoning is not a universal solution and its effectiveness depends strongly on the strategy and the summarization setting. In particular, we find a trade-off between summary quality and factual faithfulness. Explicit reasoning strategies often improve reference-based quality, but may weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. We further find that increasing an LRM's internal reasoning budget does not reliably improve summarization and can even reduce factual consistency. These findings suggest that, for summarization, more reasoning is not always better. Effective reasoning should preserve faithful compression rather than induce over-elaboration. Our source code is publicly available.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2505.16077

Ensembling Sparse Autoencoders

作者:

Soham Gadgil↗Chris Lin↗Su-In Lee↗

arXiv:2505.16077v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that a single SAE captures only a limited subset of features that can be extracted from the activation space. Motivated by this limitation, we introduce and formalize SAE ensembles. Furthermore, we propose to ensemble multiple SAEs through naive bagging and boosting. In naive bagging, SAEs trained with different weight initializations are ensembled, whereas in boosting SAEs sequentially trained to minimize the residual error are ensembled. Theoretically, naive bagging and boosting are justified as approaches to reduce reconstruction error. Empirically, we evaluate our ensemble approaches with three settings of language models and SAE architectures. Our empirical results demonstrate that, compared to an expanded SAE that matches the number of features in the ensemble, ensembling SAEs improves the reconstruction of language model activations along with SAE stability. Additionally, on downstream tasks such as concept detection and spurious correlation removal, SAE ensembles achieve better performance, showing improved practical utility.

阅读与讨论 → 访问原文 →