探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-18 DOI: HASH:42c939cd9d60e7324856eac14871b703

Expert in Ultrasound Skills: Feasibility of an IMU-video platform to describe technical profiles during focused cardiac ultrasound. Pilot study

作者:

morales↗f. r↗Gonzalez↗S. R↗Osses↗M. F. S↗Hernandez↗B. L↗Ramirez↗D. A↗

Background: Focused cardiac ultrasound (FoCUS) is operator dependent and requires coordinated probe manipulation, image interpretation and iterative visual feedback. Existing assessment approaches often emphasize final image quality or expert rating. We developed Expert in Ultrasound Skills (EXUS) , a platform that synchronizes transducer-mounted inertial measurement unit (IMU) data with ultrasound video, and evaluated its technical feasibility during FoCUS acquisition. Methods: This observational pilot study included 6 operators performing two repetitions of a four-view FoCUS protocol, yielding 12 analytical sessions and 48 planned acquisitions. Feasibility was defined by acquisition completion, video availability, start/stop events, fused IMU-video windows, temporal coverage, complete human label entries and IMU integrity. A 100-image Likert rating task was used to summarize pairwise inter-rater agreement for still-frame image quality assessment. Results: All 48 planned acquisitions were completed with video, start/stop events, fused windows and complete human label entries. Temporal coverage was at least 90% in 47/48 acquisitions. IMU integrity endpoints exceeded the 80% threshold: 43/48 acquisitions had no extreme IMU-derived artifact, 43/48 had no active-segment IMU restart and 44/48 had no complete motion flatline. Mean pairwise exact agreement for the Likert task was 38.9%, with mean quadratic-weighted Cohen's kappa of 0.564. Post hoc profiles varied across duration, visual quality, mechanical load and motor efficiency. Conclusions: EXUS was technically feasible for synchronized IMU-video capture during FoCUS. The pilot supports multimodal acquisition data as a way to describe technical profiles and generate formative feedback hypotheses, but the post hoc indices are not validated competency measures. Keywords: focused cardiac ultrasound; point-of-care ultrasound; inertial measurement unit; medical education; deliberate practice

阅读与讨论 → 访问原文 →

02.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.19266

Trade-offs in Medical LLM Adaptation: An Empirical Study in French QA

作者:

Ikram Belmadani↗Oumaima El Khettari↗Carlos Ramisch↗Frederic Bechet↗Richard Dufour↗Benoit Favre↗

The development of large language models (LLMs) has led to an increased focus on their adaptation to specialized domains and languages, yet the effectiveness of domain adaptation strategies remains unclear. We present a study of medical domain adaptation using French medical question-answering (QA) as a case study. We compare continual pretraining (CPT), supervised fine-tuning (SFT), and their combination across three model families, multiple sizes, and three initialization types, explicitly disentangling adaptation effects from base model choice. We evaluate both multiple-choice (MCQA) and open-ended QA (OEQA) under greedy and constrained decoding using automatic metrics and LLM-as-a-Judge evaluation. For MCQA, CPT+SFT most often achieves the best scores, but gains over SFT are small and frequently not statistically significant, making SFT a strong and cost-effective default. For OEQA, CPT consistently improves overlap-based metrics, while SFT often degrades generation quality; instruction tuning and CPT+SFT are preferred by LLM-based evaluation. Cross-lingual experiments further show effective transfer from French adaptation to English benchmarks. Overall, we provide practical guidelines for selecting adaptation strategies under computational constraints.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16759

Maximum Entropy Inverse Reinforcement Learning for Mean-Field Games with Average Reward

作者:

\c{S}evket Kaan Alk{\i}r↗Naci Sald{\i}↗Berkay Anahtarc{\i}↗Can Deha Kar{\i}ks{\i}z↗

arXiv:2606.16759v1 Announce Type: new Abstract: We study inverse reinforcement learning for discrete-time, infinite-horizon mean-field games (MFGs) under an average-reward criterion. Expert demonstrations are assumed to arise from a stationary mean-field equilibrium under an unknown reward, and the goal is to recover a policy explaining the observed behaviour via the maximum causal entropy principle. We formulate the inverse problem by enforcing consistency with the expert mean-field term and long-run feature expectations, treating two reward classes within a unified occupation-measure framework. For finite-dimensional linear rewards, we give a convex dual reformulation with an explicit log-partition objective, and prove smoothness and curvature properties justifying constant-step-size gradient descent. For infinite-dimensional RKHS rewards, we develop a Lagrangian relaxation whose inner-maximising policy is characterised by a soft Bellman equation. The main obstacle is the absence of a discount-factor contraction. We resolve this by introducing a minorisation-based sub-stochastic kernel that yields a strict contraction of the soft Bellman operator. We establish Fréchet differentiability and Lipschitz smoothness of the log-likelihood score, leading to a gradient ascent algorithm with convergence guarantees. Two numerical examples, a malware-spread MFG and an RKHS-based consumer-choice model, show that the recovered policies closely match expert behaviour.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12071

On the Limits of LLM-as-Judge for Scientific Novelty Assessment

作者:

Soumitra Sinhahajari↗Navonil Majumder↗Soujanya Poria↗

arXiv:2606.12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas. This makes novelty evaluation a central problem. Full idea evaluation is difficult because it often requires judging a method, its feasibility, and its empirical promise. We therefore study a cleaner upstream object: the research question (RQ). RQ generation is a prerequisite for scientific ideation, and RQs can be compared against questions pursued in real papers. We introduce RQ-Bench, a benchmark built from recent arXiv papers. For each paper, we reconstruct author-anchored RQs from its cited background, gaps, and contributions. These RQs are not the only valid questions for the same background. They are author-anchored reference points for testing novelty judgments. We evaluate model-generated RQs with standalone LLM judging, comparative LLM judging, and human expert evaluation. LLM judges consistently rate model-generated RQs as highly novel, producing a novelty mirage; in comparative evaluations, this preference becomes even stronger. Domain experts, however, reach the opposite conclusion and prefer the author-anchored reference questions. We further find that many generated RQs are narrow or source-bound, a dimension that LLM judges often miss unless explicitly tested. Overall, the contradictory novelty evaluations between LLM judges and human experts raise a serious concern about the reliability of using LLMs to assess the scientific novelty of research questions.

阅读与讨论 → 访问原文 →

05.

arXiv (quant-ph) 2026-06-15 DOI: arXiv:2606.14484

Quantum Horizon: An evaluation of quantum computing as a threat to Bitcoin and Ethereum

作者:

Iosif M. Gershteyn↗Jacob A. Alber↗

arXiv:2606.14484v1 Announce Type: new Abstract: Quantum computing poses a real, broad-based, but bounded and substantially mitigable threat to Bitcoin and Ethereum. We separate the two quantum algorithms that public discussion routinely conflates: Shor's algorithm breaks the elliptic-curve signatures (ECDSA over secp256k1, BLS over BLS12-381) that authorize spending, whereas Grover's algorithm does not meaningfully threaten proof-of-work mining, which is protected by a merely quadratic speedup, fault-tolerant per-operation costs, a square-root parallelization wall, and difficulty adjustment. Folding hardware scaling, the falling resource requirement, a fault-tolerance readiness lag, and expert surveys into a single Monte-Carlo forecast yields a wide, bimodal arrival distribution for a cryptographically relevant quantum computer: about a one-in-six chance by 2035, near 30% by 2040, and about 60% by 2050. Exposure is concentrated and mostly migratable: of Bitcoin's roughly six million quantum-exposed coins only about 2.3 million are irreducibly at risk, while 50 to 65% of Ether sits at key-revealed accounts that can adopt post-quantum signatures. A timely migration beats even an optimistic 2035 machine, so the binding constraint is governance, not technology. A survey of the top twenty cryptocurrencies finds none fully post-quantum. Reproducible models accompany every quantitative claim.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17645

Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns

作者:

Shiqi He↗Yue Cui↗Feijie Wu↗Xinyu Ma↗Jiaheng Lu↗Yaliang Li↗Bolin Ding↗Mosharaf Chowdhury↗

Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every action is a low-level primitive, horizons grow quickly and so do policy-facing LLM completions, dominating latency and cost on benchmarks such as Mind2Web and WebArena. Recent systems therefore wrap repeated interaction fragments as web skills: callable tools built from successful trajectories or induced programs, so one call can replace several primitives. However, prior skill libraries are still triggered mainly by instruction similarity or coarse site metadata, which yields low skill reuse on held-out sites and leaves much of the potential step and token reduction on the table. We present SkillMigrator, an agent that learns reusable web skills and transfers them across sites by matching layout structure rather than specific element references. Each induced skill is stored as a transferable interaction pattern (TIP): the skill paired with a structural sketch of the snapshot at induction time. At test time, SkillMigrator retrieves TIPs by layout similarity and grounds their references on the live page. The rest of the stack is standard: accessibility-snapshot observations with stable references, and fixed tool calling over primitives plus skill invocations. Compared with the state-of-the-art approaches, SkillMigrator reduces the average LLM-action count on successful trajectories by 8-10% across both WebArena and Mind2Web at matched success rate.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15822

TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AI

作者:

Qi Li↗Zhenhua Zou↗Shuo Li↗Mingwei Xu↗Zhuotao Liu↗

arXiv:2606.15822v1 Announce Type: new Abstract: AI agents increasingly access external models, tools, and services through Agentic Routing Infrastructure (ARI) to manage the overhead of heterogeneous interfaces and fragmented subscriptions. Yet, the architecture of ARI introduces fundamental trust risks: it obtains plaintext access to agent queries and service responses, while leaving agents unable to verify that their queries are routed to intended service providers or that requests and responses remain untampered. To address this problem, we present TrustedARI, the first trust-native agentic routing infrastructure for agentic AI. Architecturally, TrustedARI is built upon three core innovations: (i) an ARI-adapted three-party TLS handshake that enables the agent and ARI to jointly authenticate the service provider through role-specific distribution of TLS key materials; (ii) a privacy-preserving query-construction protocol that allows the agent and ARI to collaboratively construct well-formed queries without exposing their respective private inputs; and (iii) a verifiable billing protocol that supports fair usage-based settlement while preserving the integrity and confidentiality of service responses. We implemented and extensively evaluated a prototype of TrustedARI to validate its performance. Experiments confirm that TrustedARI is highly efficient: our ARI-adapted handshake protocol reduces communication overhead by 39.34% compared to the existing three-party TLS handshake. Furthermore, the privacy-preserving query-construction protocol imposes negligible overhead-averaging 0.19 seconds in computation time and 0.58 MB in communication costs-while the verifiable billing protocol speeds up proof generation by 28.20x. Crucially, TrustedARI is readily deployable without any modification to the service providers.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.12191

Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application

作者:

Jiachun Li↗Zhuoran Jin↗Tianyi Men↗Yupu Hao↗Kejian Zhu↗Lingshuai Wang↗Dongqi Huang↗Longxiang Wang↗Shengjia Hua↗Lu Wang↗Jinshan Gao↗Hongbang Yuan↗…

Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies current researches on agentic environments from the perspective of the environment engineering lifecycle, covering their modeling, synthesis, evaluation and application. Specifically, the paper first introduces representative environments from the perspectives of eight attributes and eight domains, providing detailed analyses of their development paths and highlighting their core capabilities. Second, for automated environment synthesis, two paradigms are introduced, such as symbolic synthesis and neural synthesis. This paper also shows different environment evaluation methods in each paradigm. Thirdly, the corresponding environment applications from the perspective of agent-environment co-evolution are discussed. In specific, the paper characterizes the primary pathways for agent evolution in dynamic environments from four complementary perspectives: memory-centric experience evolution, orchestration-centric workflow evolution, trajectory-centric offline evolution, and exploration-centric online evolution. And three paradigms of environment evolution are identified, namely neural-driven, difficulty-driven, and scaling-driven approaches. At last, several promising future directions are discussed, including Environment-as-a-Service, Multi-agent Environments, and Neural-Symbolic Environments.

阅读与讨论 → 访问原文 →

09.

bioRxiv (Bioinfo) 2026-06-16 DOI: HASH:c926e06690ab54a55efa7192a4baf091

OmicOS: A Comprehensive Omics Ecosystem Infrastructure and Agent System for the AI Era

作者:

Zeng↗Meng↗Hu↗Li↗Liu↗Shi↗Ma↗Gao↗Wang↗Luo↗Zheng↗Xian↗…

Biology has accumulated a vast ecosystem of omics methods, but much of this ecosystem remains built for expert humans rather than scientific agents. Methods are scattered across Python packages, R/Bioconductor and CRAN workflows, command-line tools, incompatible data containers and implicit object states, making even routine analyses difficult for an AI system to choose, execute and verify reliably. Here we introduce OmicOS, a comprehensive omics ecosystem infrastructure and agent system that turns OmicVerse V2, an open-source omics community, into an executable foundation for agentic biology. OmicVerse V2 provides the community substrate: scalable AnnDataOOM-compatible rust backends, agent-friendly Python algorithms for single-cell, spatial, bulk and multi-omics analysis, interfaces to single-cell foundation models, and Python-native reconstructions of historically R-centred Bioconductor/CRAN-style workflows. OmicOS makes this substrate actionable by registering analytical functions as state-aware capability contracts, allowing agents to inspect live data objects, select valid methods, execute controlled workflows and record provenance. The result is not a fixed pipeline, but a programmable omics environment in which agents compose real analyses from verified community methods rather than inventing tools. Across external and purpose-built benchmarks, OmicOS ranked first among the evaluated systems, reaching 81.2% on BiomniBench. Adding OmicVerse to a minimal agent improved task completion by up to 34.2 percentage points with qwen-3.6-35b, and controlled ablations showed that the gains came from registry-grounded execution rather than from larger models, documentation retrieval or unrestricted tool exposure. The same infrastructure scaled to atlas-sized data, reproduced R-centred workflows in Python and converted external pathology software into agent-usable skills. In a discovery task starting from a whole-body spatial map and the term Alzheimer disease, OmicOS composed a non-canonical workflow that integrated spatial expression, genetic association, eQTL and colocalization evidence to nominate a colon epithelial risk axis centred on PICALM, CD2AP and CR1. Together, OmicVerse and OmicOS define an open foundation for AI-era omics, showing how a community of biological methods can be transformed into a reliable, extensible and agent-operable system for discovery.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17013

Exploding and vanishing gradients in deep neural networks: the effect of residual connections

作者:

Vivek S Borkar↗

arXiv:2606.17013v1 Announce Type: cross Abstract: The well known phenomenon of exploding and vanishing gradients in deep neural networks is analyzed using multiplicative ergodic theory. The effect of adding a residual connection is explained in this context. Specifically, a characterization of Liapunov exponents due to Furstenberg and Kifer is exploited in order to make a precise statement about the Liapunov spectrum and the effect of residual connections on it.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16198

GRACE: Boosting Video MLLMs with Grounded Action-Centric Evidence for Viewer Sentiment Prediction

作者:

Ruoxuan Yang↗Tieyuan Chen↗Xiaofeng Huang↗Haibing Yin↗Jun Wang↗Xiping Chen↗Jun Yin↗Xuesong Gao↗Weiyao Lin↗

Viewer sentiment prediction in video advertisements aims to infer the latent affective response evoked in the audience. To bridge the gap between what is shown and what is felt, models must deduce hidden viewer emotions from explicit visual narratives, concrete character-object interactions, and visible textual cues. However, standard Multimodal Large Language Models (MLLMs) typically rely on holistic frame representations, which leave these fine-grained, affect-relevant events implicit and complicate precise emotional reasoning. To address this, we propose a grounded action-centric evidence augmentation framework that enhances video MLLMs' clue extraction and comprehension by introducing explicit event structure and localized visual evidence. Our method extracts temporally ordered subject-verb-object (SVO) triplets and auxiliary visible textual cues from action-centric video descriptions, grounds subject and object entities as visual entity crops, and then enables the MLLM to perform clue-enhanced emotional reasoning based on these extracted structured clues. In this way, action triplets specify "what happens", while grounded visual entity crops anchor "who or what participates in each event" to concrete visual evidence. Experiments on the Pitts dataset show consistent improvements over Qwen2.5-VL and Qwen3-VL baselines. Ablation studies, cross-dataset evaluation on AdsQA, and transfer experiments on an emotion-focused TVQA subset further support the effectiveness and generalization of our approach.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2309.15769

Benign overfitting beyond prediction: The ordinary least squares interpolator

作者:

Dennis Shen↗Dogyoon Song↗Peng Ding↗Jasjeet S. Sekhon↗

arXiv:2309.15769v3 Announce Type: replace-cross Abstract: Recent advances in deep learning have highlighted the phenomenon of benign overfitting in overparameterized statistical models, sparking significant interest in understanding its foundations. Owing to its simplicity and practical relevance, the ordinary least squares (OLS) interpolator has become a key object of study for gaining theoretical insight into this phenomenon. While the properties of OLS are well understood in classical underparameterized settings, its behavior in the overparameterized regime – unlike that of ridge regression or the lasso – remains comparatively less explored. We contribute to this growing literature by deriving new algebraic and statistical results for the minimum $\ell_2$-norm OLS interpolator. In contrast to much of the existing work, which focuses on prediction risk, we center our analysis on parameter estimation and inference, which are fundamental for many statistics and causal inference applications. Specifically, we establish overparameterized analogues of (i) the leave-$k$-out formulas, (ii) the omitted variable bias formula, and (iii) the Frisch-Waugh-Lovell theorem. Under the Gauss-Markov model, we further extend the Gauss-Markov theorem and analyze variance estimation under homoskedasticity in the overparameterized setting. Collectively, these results provide a systematic framework for studying parameter estimation and inference in overparameterized linear models, offering a novel perspective on benign overfitting beyond its implications for prediction.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14269

ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

作者:

Karamvir Singh↗Arvind Jain↗

Fixed-cardinality retrieval injects a constant top-K chunks into the generator regardless of query complexity, causing over-retrieval for narrow queries and under-retrieval for compositional ones. We describe ScoreGate, a lightweight score-space decision mechanism that controls retrieval cardinality at inference time using two scores already produced by the standard pipeline: bi-encoder similarity s_i and cross-encoder reranker score r_i, with no additional model inference calls required. Its core insight is that cross-encoder affirmation can rescue semantically relevant chunks that bi-encoder retrieval ranks poorly due to vocabulary mismatch – a failure mode unaddressed by fixed-K or single-score thresholding. On MS MARCO (200 dev queries), ScoreGate achieves MRR@10 = 0.401 with 35% fewer retained chunks than Standard Top-K. On an internal benchmark (n=300, Fleiss' kappa=0.87), ScoreGate observed zero false positives (95% CI [96.4%, 100%]) at 97.77-99.34% recall, with 34.8% fewer tokens per query and only 31ms added latency. Results on both MS MARCO and real-world production traffic suggest that adaptive retrieval cardinality can improve retrieval efficiency without degrading retrieval quality.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15917

Reinforcement Learning for LLM-based Event Forecasting

作者:

Amit Arnold Levy↗

arXiv:2606.15917v1 Announce Type: new Abstract: We use Group Relative Policy Optimization (GRPO), a recently devised sample and memory efficient reinforcement learning method, to finetune pretrained LLMs in the range of 1.5B to 14B parameters equipped with the ability to get current information through the use of a Wikipedia revisions tool, or news summaries, to forecast real events beyond the knowledge cutoff of the LLM, as well as problems made to simulate different aspects of the dynamics of that training. We use the results of these experiments to comment on the scaling capability of LLMs for forecasting, as well as classify how judgmental forecasting fits into the verifiable/unverifiable domain taxonomy, considering the impact of the inherent aleatoric uncertainty when forecasting future events (e.g. the roll of a die). As a result of the GRPO training, we manage to bring a 1.5B parameter transformer (Qwen 2.5 1.5B) to forecasting performance superior to Claude Sonnet 3.5 over the same dataset as measured by cross entropy from the market agreed probabilities. We also discuss various dead ends on the path to this result.

阅读与讨论 → 访问原文 →

15.

medRxiv (Medicine) 2026-06-15 DOI: HASH:62beacf0936bd25dad571a79178dcf96

Active commuting, anxiety symptoms and mental wellbeing: a dose-response study

作者:

Joensuu↗Jussila↗J. J↗Lanki↗Tiittanen↗Pasanen↗T. P↗Ekelund↗Halonen↗J. I↗

Climate change draws attention to the planetary health perspective in sport and exercise sciences, that is, to physical activity that supports both human wellbeing and environmental sustainability. Active commuting is a sustainable form of physical activity with well-established somatic health benefits. However, more knowledge is needed on its relationship with mental health. We examined dose-response associations between active commuting, anxiety symptoms, and mental wellbeing among Finnish adults, and whether green commuting environment moderates these relationships. We used data from the cross-sectional Environment and Health Survey collected in June-September 2023 in the ten largest cities in Finland. Employed participants with data on anxiety symptoms (Generalized Anxiety Disorder-7, GAD-7), mental wellbeing (World Health Organization-Five Well-Being Index, WHO-5), commuting profile over a year (mode, frequency, distance, and perceived greenness along the commute route), and sociodemographic and lifestyle factors were included (n=1,672; mean age 45.3 years; 53.8% women). Active commuting was defined as travelling the entire commute by walking or cycling (including e-biking) that was converted into approximated annual km/week and MET-h/week. We used linear and logistic regression with restricted cubic splines to evaluate dose-response associations, adjusted for key covariates. The role of perceived greenness was tested using an active commuting x commute greenness interaction term. We found no dose-response relationships between active commuting and anxiety symptoms or mental wellbeing in any of the models. No effect modification by commute greenness was observed. More research on how active commuting may support planetary health from a mental health perspective is needed.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2604.15173

Boundary-Centric Clip-Budgeted Active Learning for Temporal Action Segmentation

作者:

Halil Ismail Helvaci↗Sen-ching Samson Cheung↗

Temporal action segmentation (TAS) in untrimmed videos requires dense temporal supervision. However, most of the annotation cost is spent identifying action transitions where segmentation errors concentrate and small temporal shifts can disproportionately degrade segment-level metrics. We introduce B-ACT, a clip-budgeted active learning framework that explicitly allocates supervision to these error-prone boundary regions. B-ACT operates in a hierarchical two-stage loop: (i) it ranks and queries unlabeled videos using predictive uncertainty, and (ii) within each selected video, it detects candidate transitions from the current model predictions and selects the top-$K$ boundaries via a novel boundary score. The boundary score fuses neighborhood uncertainty, class ambiguity, and temporal prediction dynamics to reveal the underlying importance of each frame. Importantly, our annotation protocol requests labels only at the boundary frames while still training on boundary-centered clips to exploit temporal context through the model's receptive field. Extensive experiments on GTEA, 50Salads, and Breakfast demonstrate that boundary-centric supervision delivers strong label efficiency and consistently surpasses representative TAS active learning baselines and prior state of the art under sparse budgets. Gains are largest on datasets where performance is highly sensitive to boundary placement, as measured by edit and overlap-based F1 metrics.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.04525

GENEB: Why Genomic Models Are Hard to Compare

作者:

Daria Ledneva↗Mikhail Nuridinov↗Denis Kuznetsov↗

Progress in genomic foundation models is difficult to assess due to fragmented benchmarks, incompatible evaluation protocols, and task-specific reporting. As a result, claims of superiority or generality across models are often not directly comparable. We introduce GENEB, a large-scale diagnostic benchmark that evaluates frozen representations from 40 genomic foundation models across 100 tasks spanning 13 functional categories under a unified probing-based protocol, including few-shot regimes. GENEB enables controlled comparison across model scale, architecture, tokenization, and pretraining data while explicitly exposing task-level trade-offs. Our analysis shows that aggregate leaderboards are unstable: model rankings vary sharply across task categories, scale provides only modest and inconsistent gains, and architectural and pretraining alignment frequently outweigh parameter count. These results highlight limitations of current evaluation practices and position GENEB as a reference framework for principled comparison and category-aware model selection in genomic machine learning.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19919

ADaPT: Token-Level Decoupling for Efficient Large Reasoning Models

作者:

Tingyun Li↗Zishang Jiang↗Jinyi Han↗Xinyi Wang↗Sihang Jiang↗Han Xia↗Zhaoqian Dai↗Shuguang Ma↗Fei Yu↗Jiaqing Liang↗Yanghua Xiao↗

arXiv:2606.19919v1 Announce Type: new Abstract: Large reasoning models rely on long chain-of-thought to achieve strong performance, but applying such reasoning uniformly incurs high computational cost. Existing efficiency-oriented methods attempt to shorten or mix reasoning strategies, yet often degrade reasoning capability. We identify the root cause as sequence-level coupling between efficiency incentives and correctness optimization, which implicitly penalizes long but correct reasoning trajectories. To address this issue, we propose Adaptive Dual-Process Thinking (ADaPT), a token-level dual-process framework that explicitly decouples efficiency and correctness signals during training. ADaPT introduces a mode-selection token to control fast and slow reasoning, applying efficiency-related rewards exclusively to this token to avoid penalizing correct long reasoning while encouraging efficiency when appropriate. Moreover, ADaPT enables precise and continuous control over the efficiency-performance trade-off at inference time: by adjusting the generation probability of the mode-selection token, a single trained model can smoothly move along the efficiency-performance Pareto frontier. Extensive experiments demonstrate that ADaPT significantly reduces inference cost while maintaining strong reasoning performance across multiple benchmarks.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.01476

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

作者:

Yuhang Zhou↗Lizhu Zhang↗Yifan Wu↗Mingyi Wang↗Bo Peng↗Jiayi Liu↗Xiangjun Fan↗Zhuokai Zhao↗

On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy distribution shift of Supervised Fine-Tuning (SFT) and the sparse credit assignment of Reinforcement Learning (RL). However, standard OPD faces two coupled limitations. First, it requires direct access to the teacher's token-level logits, excluding a broad class of capable proprietary models from serving as teachers. Second, the token-level logit signal itself is brittle, depending on a narrow overlap of plausible next tokens between teacher and student, and prone to amplifying degenerate patterns such as repetition loops. In this paper, we introduce OmniOPD, a novel framework that addresses both limitations through a logit-free, chunk-level supervision signal. OmniOPD replaces deterministic logit matching with Monte Carlo rollouts that approximate the teacher's local preferences through a continuous semantic similarity metric over multi-token chunks, and concentrates this supervision via a peak-entropy scheduler that audits the student only at its high-uncertainty reasoning forks. A Dirichlet-Multinomial Bayesian prior and a base-model KL anchor further bound the variance of discrete sampling and prevent policy collapse across unaudited tokens. Across competitive benchmarks, OmniOPD surpasses the standard OPD approach by up to +28.64% on math, confirming that chunk-level semantic verification extracts a more reliable learning signal than token-level logit matching, whose high information density is offset by significant noise and brittleness. Furthermore, when paired with stronger black-box teachers such as Claude-4.5-Haiku and Gemini-2.5-Flash, OmniOPD achieves an additional +9.54% relative on math over its open-weight teacher counterpart, advancing the student past the performance of self-exploratory RL.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.13105

Disparate Impact in Synthetic Data Generation

作者:

Paul Andrey↗Micha\"el Perrot↗Batiste Le Bars↗Marc Tommasi↗

arXiv:2606.13105v1 Announce Type: new Abstract: We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is the same across sensitive groups. Our approach departs from existing work on fair SDG, that address the problem of correcting for undue biases in the observed distribution, hence redefining SDG as learning a distribution that is not that of the real data. By contrast, non-disparate impact is notably achieved when the synthetic and real distributions are the same. We expose reasons why SDG may fail to reach that solution and discuss why approximation and estimation errors occur and can be disparate across groups. We notably look into the expressive power of SDG methods relative to distribution complexity, sampling errors due to group proportions, and estimation errors induced by differential privacy mechanisms. We illustrate cases of disparate impact on both artificial and real-world data, focusing on SDG methods that rely on probabilistic graphical models. We also introduce a strategy of learning group-wise SDG models and illustrate how it can improve both the overall utility and its parity in many settings.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.12251

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

作者:

Xinhai Zou↗Chang Zhao↗Alireza Aghabagherloo↗Dave Singel\'ee↗Robin Degraeve↗Bart Preneel↗

arXiv:2606.12251v1 Announce Type: cross Abstract: Gradient-based adversarial attacks remain a dominant threat to deep neural networks (DNNs), as they exploit gradient information to efficiently optimize adversarial perturbations. To address this, we investigate whether reinforcement learning (RL) training can disrupt the gradient structure used by attackers by training image classifiers with policy-gradient objectives and epsilon-greedy exploration. Through systematic experiments across CIFAR-10, CIFAR-100, and ImageNet-100 with multiple architectures, we find that RL-trained classifiers significantly disrupt gradient-based adversarial optimization. To explain this, we conduct a comprehensive mechanism analysis using loss landscape visualization, static and dynamic gradient indicators, and predictive entropy. Our analysis reveals that RL acts as an implicit regularizer, producing models with highly unstable gradient directions and smaller gradient magnitudes. This combination makes each PGD step both unreliable in direction and limited in magnitude, causing gradient-based attacks to fail within practical iteration budgets. We further show that combining RL with adversarial training (RL-adv) provides a dual-layer defense operating at two complementary levels: RL degrades gradient information available to attackers (gradient-level defense), while adversarial training strengthens decision boundaries (boundary-level defense). RL-adv achieves the highest robustness across all major attack types evaluated, including gradient-based (PGD, AutoAttack), transfer-based, and query-based attacks, outperforming SL-adv by a significant margin. These findings identify RL-induced gradient disruption as a complementary robustness mechanism and motivate future research on hybrid SL-RL training schedules that combine SL's efficiency with RL's gradient-regularization properties.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2505.10496

CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs

作者:

Raman Dutt↗Pedro Sanchez↗Yongchen Yao↗Steven McDonagh↗Sotirios A. Tsaftaris↗Timothy Hospedales↗

Structured benchmarks have advanced text-conditional image generation for real-world imagery, however, no such benchmark exists for synthetic radiograph generation. Despite being a highly active area of research, existing studies continue adopting inconsistent evaluation protocols and lack a unified assessment of the three most critical criteria: generative fidelity, privacy risk, and downstream utility. To address these limitations, we introduce CheXGenBench, the first unified evaluation framework for synthetic chest radiograph generation that simultaneously assesses fidelity, privacy risks, and downstream utility across frontier text-to-image (T2I) generative models. Our evaluation protocol, comprising over 20 quantitative metrics, covers 11 leading T2I architectures with plug-and-play integration for newer models. Through a rigorous and fair evaluation protocol, we establish comprehensive baseline state-of-the-art (SoTA) performances across all dimensions to guide future research. Furthermore, our results uncover several limitations of current generative models, which include first, even SoTA models struggle with long-tailed medical distributions; second, models pose high privacy risks regardless of fidelity quality; and third, while synthetic data already benefits downstream classification, it is of limited utility for downstream multimodal tasks. Drawing from these results, we propose concrete research directions to advance the field. The code is available at https://github.com/Raman1121/CheXGenBench

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11204

Benchmarking Large Language Models for Safety Data Extraction

作者:

Jonas Grill↗Thomas Bayer↗S\"oren Berlinger↗

Accurate extraction of structured information from Safety Data Sheets (SDS) remains challenging in industrial safety due to heterogeneous document formats and the limitations of traditional rule-based methods. This study benchmarks state-of-the-art Large Language Models (LLMs) for automated SDS data extraction, comparing text-based and multimodal processing pipelines. We systematically evaluate four models: Gemini 1.5 Pro, GPT-4o, Claude 3.7 Sonnet, and Llama 3.1-70B, across three prompting strategies: zero-shot, few-shot, and chain-of-thought. The evaluation framework assessed accuracy, latency, and cost across more than 50,000 extracted data fields. Results show that text-based extraction consistently outperforms multimodal processing across all metrics. Gemini 1.5 Pro combined with a Chain-of-Thought prompt achieved the highest accuracy (84%), outperforming GPT-4o (81%) and Claude 3.7 Sonnet (79%). However, no model surpassed the 90% accuracy threshold commonly required for reliable real-world deployment. These findings indicate that general-purpose LLMs are not yet robust enough for unsupervised industrial use, though performance suggests strong potential with task-specific fine-tuning. Future research should focus on domain-adapted training, model calibration, and the integration of Human-in-the-Loop verification to ensure safety-critical reliability.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13033

SAM-Deep-EIoU: Selective Mask Propagation for Multi-Object Tracking

作者:

Alexander Holmberg↗

Multi-object tracking has a heavy-tailed difficulty distribution: most frames are easy for a lightweight base tracker, while a small fraction are intrinsically hard. Video object segmentation (VOS) models can often preserve identity through the hard frames where the base tracker fails, but they are much more expensive in compute and memory. We propose selective mask propagation, a tracking algorithm that dispatches from a base tracker to a VOS model only on windows where an assignment-uncertainty signal fires. The base tracker's output is modified only when the VOS model makes a confident prediction that contradicts the base tracker's identity assignment; weak or inconclusive predictions preserve the base output. The method is training-free, treats both the base tracker and the VOS model as black boxes, and can benefit from replacing the VOS component with a more capable model. On DanceTrack, selective mask propagation improves three different base trackers. On SportsMOT, where identity preservation is central to sports analytics, SAM3-Deep-EIoU with global track association achieves state-of-the-art performance on the benchmark with 86.8 HOTA.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2605.18848

Exact Linear Attention

作者:

Weinuo Ou↗

arXiv:2605.18848v4 Announce Type: replace-cross Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error. We identify and address two key limitations of prior linear attention – gradient explosion and token attention dilution – by imposing kernel constraints that ensure non-negativity, discriminability, and geometric interpretability. Several kernel functions are proposed, including the Hadamard Exp Kernel, Summation Squared Euclidean Distance Kernel, and Subtraction Squared Euclidean Distance Kernel, each tailored for specific attention behaviors. Beyond the core attention formulation, the paper presents three engineering innovations: (1) a Hyper-Link structure that replaces traditional residual connections to mitigate gradient degradation; (2) a Memory Lobe module based on bidirectional linear attention, which captures "transformation flow" across layers to implement qualitative memory and an implicit reinforcement learning paradigm; and (3) a routing-score-based bias mechanism for Mixture-of-Experts (MoE) to improve interpretability and semantic alignment. Experimental results demonstrate that ELA achieves up to 6x faster decoding speed and 75% reduction in KV cache memory usage compared to full attention, while maintaining comparable or superior training performance. The proposed memory module accelerates convergence and enhances generalization. Furthermore, we extend the linear attention principle to vision models, yielding YOLO-LAT, which attains up to 4.3x GPU inference speedup and 7.9x parameter reduction with competitive detection accuracy. These results underline the broad applicability of exact linear attention for scaling Transformer models to ultra-long sequences and efficient visual tasks.

阅读与讨论 → 访问原文 →