探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-12 DOI: HASH:944153cf2348858c38e1083f871c6045

Design, Implementation, and Evaluation of a Shadowing Program for Medical Students in the Basic Sciences Phase

作者:

Omid↗Changiz↗ghasemi↗Khodadoustan↗Heshmat↗Arefan↗Fazel Harandi↗M. H↗Yousefi↗

Introduction Shadowing, as an educational method based on active observation, can foster a realistic understanding of professional roles and enhance the communication skills of medical students. This study aimed to design, implement, and evaluate a shadowing program for basic sciences medical students. Methods This development study was conducted based on the ADDIE model in five phases. The study population consisted of 799 medical students in semesters 2 to 5. The stages included Analysis (determining needs through literature review and expert panels), Design (specifying learning environments and evaluation methods), Development (preparing guides and educational tools), Implementation (within the Medical Ethics course), and Evaluation (using questionnaires and reflection forms). Findings This study aimed to design and evaluate an educational shadowing program based on the ADDIE model. In the Analysis phase, the profiles of 799 students and learning objectives were determined. In the Design phase, a structured program for four types of shadowing was designed. In the Development phase, all guides and educational tools were prepared. In the Implementation phase, the program was carried out with complete coverage and adherence to ethical considerations. Finally, the program evaluation showed that "Motivation to become a good physician" (3.75-3.95) and "Enhancing empathy" (3.50-3.94) received the highest scores, while "Increasing understanding of the basic science-clinical connection" (2.53-2.89) and "Willingness to attend on holidays" (1.87-2.31) received the lowest scores. Conclusion The findings indicate that implementing the shadowing program is an effective method for strengthening the professional attitudes and academic motivation of medical students. However, the program did not significantly improve students perception of the basic science-clinical connection, indicating a need for curricular refinement. The continuation and extension of this program to other levels and fields of medical sciences are recommended.

阅读与讨论 → 访问原文 →

02.

arXiv (math.PR) 2026-06-19 DOI: arXiv:2207.13180

Hermite trace polynomials and chaos decompositions for the Hermitian Brownian motion

作者:

Michael Anshelevich↗David Buzinski↗

arXiv:2207.13180v4 Announce Type: replace Abstract: For a non-zero parameter $q$, we define Hermite trace polynomials, which are multivariate polynomials indexed by permutations. We prove several combinatorial properties for them, such as expansions and product formulas. The linear functional determined by these trace polynomials is a state for $q = \frac{1}{N}$ for $N$ a non-zero integer. For such $q$, Hermite trace polynomials of different degrees are orthogonal. The product formulas extend to the closure with respect to the state. The state can be identified with the expectation induced by the $N \times N$ Hermitian Brownian motion. Hermite trace polynomials are martingales for this Brownian motion, while the elements in the closure can be interpreted as stochastic integrals with respect to it. Using the grading on the algebra, we prove several chaos decompositions for such integrals, as well as analyze corresponding creation and annihilation operators. In the univariate, pure trace polynomial case, trace Hermite polynomials can be identified with the Hermite polynomials of matrix argument.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18803

ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch

作者:

Tengfei Lyu↗Zirui Yuan↗Xu Liu↗Kai Wan↗Zihao Lu↗Li Ma↗Hao Liu↗

arXiv:2606.18803v1 Announce Type: new Abstract: Bringing Large Language Models (LLMs) into industrial ride-hailing dispatch as semantic feature extractors over platform-scale behavioral logs is a compelling but under-explored data systems problem. Production matching pipelines remain dominated by structured numerical features, yet decisive behavioral signals (e.g., a driver's habitual aversion to certain regions) are inherently contextual and naturally expressible as LLM-generated user profiles. However, scaling such profiling to a live, millisecond-latency dispatcher faces three intertwined constraints rarely addressed together: on a platform with millions of daily orders, logs exceed any LLM's context window by orders of magnitude; most users are long-tail, with too few interactions for per-user profiling; and surface-fluent profiles do not necessarily improve downstream prediction utility. We present ProfiLLM, an agentic LLM data pipeline that operationalizes utility-aligned user profiling for production matching systems through two modules. (1) Tool-Augmented Global Knowledge Mining equips an LLM agent with 27 analytical tools to mine platform-scale data, producing reusable global knowledge, adaptive user clustering rules, and region-level supply-demand priors. (2) Utility-Aligned Profile Exploration generates multiple candidate profiles per cluster, evaluates them via a lightweight downstream utility proxy, iteratively refines the best candidates and constructs preference pairs for DPO fine-tuning. Deployed on DiDi's production dispatcher, ProfiLLM achieves up to +6.14% relative AUC improvement in outcome prediction, up to +4.35% GMV gain in dispatching simulation, and consistent improvements in a 14-day online A/B test including +0.47% GMV, +0.33% Completion Rate, and -0.82% Cancel-Before-Accept rate.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13315

Masked and Predictive Self-Supervised Foundation Models for 3D Brain MRI

作者:

Esra Erg\"un↗Hersh Chandarana↗Dan Sodickson↗G\"ozde \"Unal↗

Self-supervised foundation models have shown strong promise in medical imaging. However, existing MRI foundation-model studies have primarily emphasized segmentation and dense prediction tasks, while systematic investigation of self-supervised foundation models for MRI-based disease detection remains limited. In this work, we investigate two major self-supervised pretraining paradigms for MRI-based disease detection: reconstruction-based learning via Masked Autoencoders (MAE) and predictive representation learning via Joint Embedding Predictive Architectures (JEPA). We study the role of auxiliary objectives by introducing a novel spectral-domain reconstruction loss for MAE to enhance sensitivity to fine-grained anatomical structure, and by integrating variance–covariance regularization (VCR) within our JEPA framework to encourage decorrelated latent representations. Our models are pretrained on heterogeneous single-contrast MRI volumes in a contrast-agnostic setting, without modality concatenation. Across five downstream disease detection tasks, our results highlight the importance of self-supervised objective design for medical foundation model pretraining, demonstrating that the downstream benefit of each objective is determined by its relevance to the task's structure. Specifically, spectral regularization yields the largest improvements when the downstream discriminative signal is characterized by strong high-frequency anatomical structures, while covariance regularization is most beneficial when discriminative information spans multiple decorrelated feature dimensions. MAE with spectral-domain supervision consistently achieves superior downstream performance for MRI-based disease detection. These findings suggest that self-supervised objectives in medical imaging encode specific biases, and their downstream benefit is fundamentally conditioned on the task's structure.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.17024

ExpRL: Exploratory RL for LLM Mid-Training

作者:

Violet Xiang↗Amrith Setlur↗Chase Blagden↗Nick Haber↗Aviral Kumar↗

arXiv:2606.17024v1 Announce Type: new Abstract: Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through mid-training on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: RL-based mid-training using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as reward scaffolds: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13385

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

作者:

Zihao Wang↗Yiming Li↗Yutong Wu↗Zheyu Liu↗Kangjie Chen↗Fok Kar Wai↗Pin-Yu Chen↗Vrizlynn L. L. Thing↗Bo Li↗Dacheng Tao↗Tianwei Zhang↗

arXiv:2606.13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences. This makes them vulnerable to prompt-injection attacks, in which seemingly benign content embeds adversarial instructions that manipulate agent behaviour. Existing security benchmarks adopt an attack-centric perspective, focusing on the technical feasibility of injections while overlooking the nuanced distribution of resulting harms. In practice, however, prompt-injection risk is victim-dependent: a single exploit can produce asymmetric consequences for different stakeholders, and the same attack pattern may exhibit substantially different effectiveness depending on whom it targets. To capture these properties, we introduce \sysname, a stakeholder-centric benchmark to systematically categorize and attribute harm in real-world web agent systems. It distinguishes between affected entities (e.g., user, seller, platform), decomposes the attacks into concrete objectives, and evaluates each case with complementary outcome- and process-level metrics. Our results reveal substantial and heterogeneous vulnerabilities: not a single attack objective is reliably resisted by current agents, and failures distribute across qualitatively distinct modes ranging from stealthy parasitism (attack succeeds without disrupting the user's delegated task) to misaligned disruption (task disrupted without attack success) and compounded failure (both adversarial objective and task integrity simultaneously violated). These patterns are missed by conventional evaluation, highlighting the need for stakeholder-aware assessment of LLM-based agents in real-world deployments. Benchmark is available at https://github.com/StakeBench/SBC.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.12402

DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?

作者:

Jadelynn Dao↗Milan Ganai↗Yasmina Abukhadra↗Ajay Sridhar↗Mozhgan Nasr Azadani↗Katie Luo↗Clark Barrett↗Jiajun Wu↗Chelsea Finn↗Marco Pavone↗

Vision-Language Models (VLMs) are increasingly deployed as high-level planners for embodied agents, with an emerging strategy of scaling test-time compute to improve capability. However, we observe that doing so increases latency, token usage, and FLOPs while yielding uneven, often diminishing gains in downstream success, limiting where embodied agents can be deployed. We argue that choosing when and where to spend test-time compute is central to bringing frontier performance to the real world. We introduce DIRECT, a routing framework that uses multimodal scene context to allocate compute per prompt, improving the success–cost Pareto frontier over fixed model selection. Across three dominant scaling axes, namely chain-of-thought depth, model size, and memory history, our experiments on VLABench and RoboMME show that test-time compute is not a uniform lever: different axes yield qualitatively distinct capability gains. We validate these insights on a physical Franka arm in a DROID setup spanning zero-shot manipulation and long-horizon chaining, where our router matches or exceeds a stronger model's success rate at up to 65% lower average latency. Ultimately, our results show that naively scaling test-time compute is wasteful, and that DIRECT can provide frontier-level embodied planning in robotic systems at a fraction of the cost. Project page can be found at jadee-dao.github.io/direct/.

阅读与讨论 → 访问原文 →

08.

arXiv (math.PR) 2026-06-15 DOI: arXiv:2604.01632

Hierarchical symmetry selects log-Poisson cascades: classification, uniqueness, and stability

作者:

E. M. Freeburg↗

arXiv:2604.01632v2 Announce Type: replace Abstract: Within i.i.d. multiplicative cascades, a single axiom – the hierarchical symmetry, a linear contraction on incremental scaling exponents – is shown to be necessary and sufficient for the cascade multiplier to be log-Poisson. We prove: (1) a characterization theorem determining the log-Poisson law with explicit parameters, within the class of all multipliers with finite lattice moments; (2) a classification theorem locating the log-Poisson class inside the log-infinitely-divisible family and identifying the mechanism by which every rival sub-family fails the symmetry; (3) a stability theorem with sharp constants – $(1+\beta)^{1/2}$ when the limiting increment is known, $\sqrt{2}$ when it is fitted – and (4) an unconditional propagation theorem transferring the bound to the multiplier distribution at the sharp rate $\Theta(\sqrt{\varepsilon})$, with a matching lower bound. Beyond independence, the classification extends exactly at the level of asymptotic statistics (limiting cumulant generating function, large deviations, multifractal spectrum) and provably not at the level of laws: an explicit stationary ergodic Markov multiplier satisfies the symmetry exactly with a non-log-Poisson marginal, while exchangeable multipliers collapse to the i.i.d. log-Poisson cascade and finite-state Markov multipliers cannot satisfy the symmetry at all. In the continuous category of exactly scale-invariant log-infinitely-divisible multifractal random measures, no finite moment window of structure-function exponents identifies the cascade class, whereas at the level of the scale-invariance generator the symmetry selects exactly the Barral-Mandelbrot compound Poisson cascade, with scale-ratio-free stability constants. The proofs reduce to second-moment identities on [0,1] via the change of variables $u = e^{kx}$, boundedness of the multiplier, and multiplicative couplings.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2505.04671

Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards

作者:

Yuxin Zhang↗Meihao Fan↗Ju Fan↗Mingyang Yi↗Yuyu Luo↗Guoliang Li↗Bin Wu↗Wenchao Zhou↗

Recent advances in large language models (LLMs) trained with reinforcement learning (RL) have improved Text-to-SQL performance. However, RL-based approaches still struggle with complex queries due to two key limitations: insufficient stepwise execution-aware reasoning grounded in database feedback, and the lack of process-level rewards for guiding reasoning optimization. To address these issues, we propose CoCTE, a divide-and-conquer and execution-aware reasoning framework that progressively composes SQL queries through intermediate view validation and structured Common Table Expressions (CTEs), improving both accuracy and interpretability. To realize a CoCTE reasoning process, we develop Reward-SQL, a unified approach with three stages: (1) model initialization, which equips LLMs with structured CoCTE reasoning capabilities; (2) process reward design, which delivers fine-grained, execution-aware supervision; and (3) process-supervised RL and inference, which integrates process rewards into training and guides the inference stage by process rewards. This paper addresses the core challenges in Reward-SQL and makes the following contributions. We introduce a process reward model (PRM) that combines execution-aware trajectory scoring with entropy-based step weighting, providing dense and interpretable supervision across reasoning steps. We integrate PRM into both RL training and inference stages, stabilizing optimization and improving trajectory exploration with process-level signals. Experiments show that Reward-SQL significantly outperforms baselines with comparable model sizes, and exhibits strong cross-domain generalization.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2603.14867

Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning

作者:

Mikoto Kudo↗Takumi Tanabe↗Akifumi Wachi↗Youhei Akimoto↗

arXiv:2603.14867v4 Announce Type: replace-cross Abstract: Many strategic decision-making problems, such as environment design for warehouse robots, can be naturally formulated as bi-level reinforcement learning (RL), where a leader agent optimizes its objective while a follower solves a Markov decision process (MDP) conditioned on the leader's decisions. In many situations, a fundamental challenge arises when the leader cannot intervene in the follower's optimization process; it can only observe the optimization outcome. We address this decentralized setting by deriving the hypergradient of the leader's objective, i.e., the gradient of the leader's strategy that accounts for changes in the follower's optimal policy. Unlike prior hypergradient-based methods that require extensive data for repeated state visits or rely on gradient estimators whose complexity can increase substantially with the high-dimensional leader's decision space, we leverage the Boltzmann covariance trick to derive an alternative hypergradient formulation. This enables efficient hypergradient estimation solely from interaction samples, even when the leader's decision space is high-dimensional. Additionally, to our knowledge, this is the first method that enables hypergradient-based optimization for 2-player Markov games in decentralized settings. Experiments highlight the impact of hypergradient updates and demonstrate our method's effectiveness in both discrete and continuous state tasks.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.17006

TuneJury: An Open Metric for Improving Music Generation Preference Alignment

作者:

Yonghyun Kim↗Junwon Lee↗Haiwen Xia↗Yinghao Ma↗Junghyun Koo↗Koichi Saito↗Yuki Mitsufuji↗Chris Donahue↗

arXiv:2606.17006v1 Announce Type: cross Abstract: We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preference score from a text prompt and an audio clip. The released checkpoint is trained on publicly available human-preference labels covering arena-style (A vs. B) votes, metric-alignment preference pairs, crowdsourced pairwise comparisons, and expert aesthetic ratings. The predicted score margin between two clips is well calibrated on our held-out test split, supporting data filtering via a simple score threshold. TuneJury generalizes to both held-out test pairs and out-of-distribution benchmarks, remaining competitive with prior baselines on the latter. For generators released after training, we introduce anchor calibration, a post-hoc, per-system Bradley-Terry calibration that recovers agreement at substantially better data efficiency than from-scratch retraining. The same frozen reward drives consistent reward-axis gains across three downstream applications: inference-time best-of-N selection, DITTO-style latent optimization, and expert-iteration post-training. TuneJury is available at https://github.com/yonghyunk1m/TuneJury.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2603.02230

Generalized Discrete Diffusion with Self-Correction

作者:

Linxuan Wang↗Ziyi Wang↗Yikun Bai↗Wei Deng↗Guang Lin↗Qifan Song↗

arXiv:2603.02230v2 Announce Type: replace-cross Abstract: Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correction at inference time or during post-training; however, such approaches often suffer from limited generalization and may impair reasoning performance. GIDD pioneers pretraining-based self-correction via a multi-step BERT-style uniform-absorbing objective. However, GIDD relies on a continuous interpolation-based pipeline with opaque interactions between uniform transitions and absorbing masks, which complicates hyperparameter tuning and hinders practical performance. In this work, we propose a Self-Correcting Discrete Diffusion (SCDD) model to reformulate pretrained self-correction with explicit state transitions and learn directly in discrete time. Our framework also simplifies the training noise schedule, eliminates a redundant remasking step, and relies exclusively on uniform transitions to learn self-correction. Experiments at the GPT-2 scale demonstrate that our method enables more efficient parallel decoding while preserving generation quality.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2508.04266

ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents

作者:

Jiangyuan Wang↗Kejun Xiao↗Qi Sun↗Huaipeng Zhao↗Tao Luo↗Jian Dong Zhang↗Xiaoyi Zeng↗

Existing benchmarks in e-commerce primarily focus on basic user intents, such as finding or purchasing products. However, real-world users often pursue more complex goals, such as applying vouchers, managing budgets, and finding multi-products seller. To bridge this gap, we propose ShoppingBench, a novel end-to-end shopping benchmark designed to encompass increasingly challenging levels of grounded intent. Specifically, we propose a scalable framework to simulate user instructions based on various intents derived from sampled real-world products. To facilitate consistent and reliable evaluations, we provide a large-scale shopping sandbox that serves as an interactive simulated environment, incorporating over 2.5 million real-world products. Experimental results demonstrate that even state-of-the-art language agents (such as GPT-4.1) achieve absolute success rates under 50% on our benchmark tasks, highlighting the significant challenges posed by our ShoppingBench. In addition, we propose a trajectory distillation strategy and leverage supervised fine-tuning, along with reinforcement learning on synthetic trajectories, to distill the capabilities of a large language agent into a smaller one. As a result, our trained agent achieves competitive performance compared to GPT-4.1.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.12925

Multi-Label Test-Time Adaptation with Bayesian Conditional Priors

作者:

Qiru Li↗Ao Zhou↗Zhiwei Jiang↗Zifeng Cheng↗Cong Wang↗Yafeng Yin↗Qing Gu↗

Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone. BCP views zero-shot logits as a proxy for marginal posteriors under a fixed image-text likelihood and attributes shift-induced errors mainly to a mismatched label prior. For each test image, it selects a high-confidence anchor label and applies an anchor-conditioned Bayesian refinement. This update is closed-form in logit space and admits a pointwise mutual information (PMI) interpretation, explicitly promoting compatible labels and suppressing incompatible ones. BCP operates without target annotations by estimating anchor-conditioned priors online from the unlabeled test stream via lightweight second-order co-occurrence statistics, adding negligible overhead beyond a single forward pass. Across standard multi-label benchmarks and multiple CLIP backbones, BCP consistently outperforms strong TTA baselines, e.g., improving RN50 average mAP from 57.31 to 69.22 and ViT-B/16 from 62.61 to 71.79.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19958

SketchKeyAnime: Reference-anchored Sparse Key-Sketch Animation Synthesis

作者:

Meixi Li↗Xianlin Zhang↗Yue Zhang↗Xueming Li↗

Traditional animation production relies heavily on manual drawing and iterative refinement, particularly for key-pose design, in-betweening, and character coloring. While existing animation and video generation methods have made notable progress, they typically depend on RGB boundary frames, dense frame-wise conditions, or complete sketch sequences, limiting their applicability under low-cost input conditions. We present SketchKeyAnime, a video diffusion framework for generating structurally controllable, appearance-consistent, and temporally coherent animations from sparse key-sketch inputs. Given a single reference RGB image and a few temporally indexed key sketches, SketchKeyAnime introduces a dual-branch conditioning mechanism to encode local geometric constraints alongside semantic-temporal context. It leverages Sketch Cross Attention to fuse reference image and sketch conditions with learnable gating, and incorporates an Adaptive Weighted Loss to strengthen supervision on key-sketch frames and line-art regions. Experimental results on the Aesthetic subset of Sakuga-42M show that our approach consistently outperforms representative animation interpolation and sketch-guided generation baselines. Compared to the best-performing baseline, SketchKeyAnime reduces EDMD by 31.9\% and FVD by 9.5\%, demonstrating superior sketch fidelity and temporal coherence, while achieving the best overall performance across most quantitative metrics. These results validate the proposed framework and highlight its potential for low-cost, highly controllable animation creation.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16003

SciText2Eq: Assessing LLMs for Explainable Equation Generation for Scientific Creativity

作者:

Yifan Mo↗Xiao Fu↗Yue Su↗Qingyu Meng↗Koen Hindriks↗Qingzhi Liu↗Jiahuan Pei↗

arXiv:2606.16003v1 Announce Type: new Abstract: This work investigates the ability of large language models (LLMs) to generate mathematical equations from scientific texts. Prior work faces challenges in unstructured grounding, multi-equation dependency, and humanaligned evaluation. To this end, we construct a dataset of AI research papers, pairing contextual passages with ground-truth equations and variable descriptions. We develop an explainable equation generation workflow and evaluate it across diverse open- and closed-source LLM backbones. We introduce an evaluation protocol combining automatic metrics, LLM-based rubrics, and human judgments to assess accuracy, explainability, and human-LLM alignment. Results indicate that LLMs perform moderately on lexical- and syntactic-based similarity, while struggling with semantic accuracy. Comparisons between LLM-based evaluations and human judgments reveal limited alignment, highlighting challenges in using LLMs to assess equation quality. These findings offer insights for improving equation generation models and developing more reliable evaluation methods for scientific text. We provide code and data for reproducibility.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2601.00215

Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design

作者:

Omar Sharif↗Eftekhar Hossain↗Nikhil Singh↗Patrick Ng↗

Reinforcement learning with verifiable rewards has driven major gains in LLM reasoning, and it is intuitive to assume this recipe will transfer well to multimodal models. However, multimodal models do two things: first, perceive what is in an image, then reason about what it implies. Because these stages are graded jointly, it is hard to tell how much room reasoning alone has to grow. We study this on algorithmic visual puzzles, where both components are necessary and show that perception, not reasoning, is the binding constraint. Replacing images with simple textual descriptions raises performance by over 20 points on average for Claude models. We then evaluate six reward designs aimed at inducing visual grounding during reasoning without chain-of-thought supervision. Training Qwen-2.5-VL-7B with GRPO, reward design induces long, structured reasoning with self-reflection and visual references, yielding a 5.56-point gain over the base model. These gains are, however, uneven; no single reward improves all categories, and rewards with verifiable accuracy signals trade out-of-domain transfer for in-domain accuracy. These results point to perception-aware reward design as a path forward, so that signals correct perception at its source rather than the reasoning that inherits its errors.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.13795

Diffusion Policy Optimization without Drifting Apart

作者:

Haozhe Jiang↗Haiwen Feng↗Pieter Abbeel↗Jiantao Jiao↗Angjoo Kanazawa↗Nika Haghtalab↗

arXiv:2606.13795v1 Announce Type: new Abstract: RL post-training has become increasingly pivotal for improving diffusion policies, but existing diffusion policy-gradient methods are often unstable and cannot achieve reliable policy improvement. We identify the cause as the double-drift phenomenon: optimizing a variational surrogate can let the ELBO separate from the true log-likelihood, which then makes the resulting proxy policy gradient misaligned with the true policy gradient of expected return. We propose DiPOD, a diffusion policy optimization framework that maintains tight-bound behavior throughout training by interleaving self-distillation with policy-improving gradient updates. This leads to a simple and practical algorithm: augmenting each diffusion policy-gradient update with an on-policy ELBO regularizer. Across diffusion language model post-training and continuous-control diffusion policies, DiPOD substantially stabilizes training and reaches higher rewards than previous methods.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18557

DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models

作者:

Patrick Cooper↗Alvaro Velasquez↗

arXiv:2606.18557v1 Announce Type: new Abstract: A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface renderings). We introduce DeFAb (Defeasible Abduction Benchmark), a dataset and generation pipeline that converts four decades of publicly funded knowledge bases into formally grounded instances for defeasible abduction: constructing hypotheses that explain anomalies by overriding defaults while preserving unrelated expectations. Because every hypothesis must pass polynomial-time checks for valid derivation, conservativity, and minimality, DeFAb makes logical rigor the instrument for measuring creativity and theoretical reasoning, scoring the disciplined construction of theory revisions rather than fluent but theory-destroying prose. The pipeline pairs taxonomic hierarchies (OpenCyc, YAGO, Wikidata) with behavioral property graphs (ConceptNet, UMLS) to produce 372,648+ instances across 33.75M materialized rules from 18 sources, in three levels with polynomial-time verifiable gold standards. Four frontier models do not reliably internalize defeasible reasoning: rendering-robust Level 2 accuracy is 7.8-23.5%; chain-of-thought variance (~36 pp) exceeds any inter-model gap; and a matched contamination control isolates a +19.4 pp Level 3 gap. We further release DeFAb-Hard (a 235-instance Level 3 difficulty variant; best model 53.3% vs 100% symbolic) and CONJURE (a kernel-verified transformative-creativity variant of 560 Lean 4/Mathlib instances whose gold answers are definitions the proof kernel did not previously contain, judge-free verifier; a pilot finds zero novel concepts). The same verifier doubles as an exact reward for preference optimization (DPO, RLVR/GRPO). Released under MIT at https://huggingface.co/datasets/PatrickAllenCooper/DeFAb.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.19808

Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning

作者:

Sajib Acharjee Dip↗Dawei Zhou↗Liqing Zhang↗

Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes. We study this as a deployment allocation problem rather than a new-verifier problem. We introduce \sevra, Selective Verification for Reasoning Allocation, a serving-layer controller that decides whether to preserve a frozen solver's initial answer or invoke active verification. Using a frozen Qwen3-4B solver, we log intervention outcomes and train recoverability-aware gates from serving-visible attempt state. On \mathfive, selective verification reaches 76.3\% accuracy, compared with 75.5\% for always verifying, while reducing post-generation tokens by 26.8\% and harmful flips from 2.2\% to 1.0\%. However, an 8,192-token initial solve reaches 76.0\% accuracy with 28\% fewer total model tokens, showing that selective recovery is useful but not the best tested cost frontier. In frozen transfer to \gsm, the selective policy verifies only 3.0\% of examples, improves accuracy from 93.4\% to 94.5\%, and reduces verification tokens by 91.2\% relative to always verifying; again, a longer initial solve matches its accuracy with fewer realized tokens. On CommonsenseQA, always-on verification hurts, while Self-Consistency@5 improves accuracy at about five times the realized token cost. The resulting deployment rule is: tune the initial budget first, then use selective recovery when explicit checks, bounded retries, auditability, or regression-risk control matter.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2602.02028

Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories

作者:

Ya Gao↗Kalle Kujanp\"a\"a↗Pekka Marttinen↗Harri Valpola↗Alexander Ilin↗

arXiv:2602.02028v2 Announce Type: replace Abstract: Enabling artificial intelligence systems, particularly large language models, to update knowledge and flexibly apply it during reasoning remains a central challenge. Existing knowledge editing approaches emphasize atomic facts, improving factual recall but often failing to integrate updated information into a coherent framework usable across contexts. In this work, we argue that knowledge update is fundamentally a reasoning problem rather than a memorization problem. Consequently, a model should be trained in situations where the new information is instrumental to solving a task, combined with pre-existing knowledge, and exercised through multi-step reasoning. Based on this insight, we propose a training strategy based on three principles. First, new knowledge is introduced as a coherent background story that contextualizes novel facts and explains their relation to existing knowledge. Second, models are trained using self-generated multi-hop questions that require multi-step reasoning involving the new information. Third, training is done using knowledge distillation, forcing a student model to internalize the teacher's reasoning behavior without access to the novel information. Experiments show that models trained with this strategy effectively leverage newly acquired knowledge during reasoning and achieve remarkable performance on challenging questions that require combining multiple new facts.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2606.18634

EffiNav: Fusing Depth and Vision-Language for Efficient Object Goal Navigation

作者:

Zecheng Yin↗Benedict Jun Ma↗

arXiv:2606.18634v1 Announce Type: cross Abstract: To locate a target object while exploring the unknown environment is a fundamental capability for autonomous agents, with applications ranging from search-and-rescue to field robots. A simplified version of such task is Object Goal Navigation (ObjNav). In ObjNav, successful arrival at the target object provides a basic measure of performance; however, the efficiency of the navigation trajectory is equally important, as it indicates how intelligently the agent explores and how much time remains for subsequent tasks. In unknown environments, the key to efficient navigation lies in deciding where to explore next. While many prior works aim to address this core challenge and achieved promising performance in certain settings, recent training-based models and non-training frameworks still suffer from generalization and efficiency issues respectively, which in the worst cases can lead to excessive exploration of already-visited areas or redundant back-and-forth motion. We evaluate EffiNav on two widely used simulation benchmarks Habitat Matterport 3D (HM3D) and Open-Vocabulary Object goal Navigation (OVON), and further validate its effectiveness on physical robots in real-world settings. We conduct failure analysis on massive simulation episodes. With minimal modification, we also extend EffiNav to a memory-augmented ObjNav task on the GOAT-BENCH dataset, demonstrating its adaptability beyond standard ObjNav settings. Across two standard metrics–Success Rate (SR) and Success weighted by Path Length (SPL), EffiNav matches or outperforms recent baselines, reflecting its efficiency, robustness, and practical applicability. Recognizing the different emphases of the two datasets, the performances reveals this framework is more balanced and generalizable for efficient ObjNav.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17820

Improving low-resource ASR using bilingual fine-tuning with language identification: a cross-linguistic evaluation

作者:

Reihaneh Amooie↗Yun Hao↗Wietse de Vries↗Jelske Dijkstra↗Matt Coler↗Martijn Wieling↗

This study explores how bilingual fine-tuning affects automatic speech recognition (ASR) in low-resource languages. We evaluate this method across nine linguistically and geographically diverse language pairs, covering a range of language families and writing systems. To distinguish the two languages, during training, we pre-pend each input text with a language identification token. At inference, the model jointly predicts both the language and transcription from the speech input alone. As texts for which the language is incorrectly determined show low ASR performance, we also conduct a follow-up experiment in which the language identification token is provided both during training and inference. Our results show that bilingual fine-tuning can be beneficial when language identification accuracy is high, and that in cases where language identification performance is low, including the language identification token at inference helps to improve ASR performance.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.AI) 2026-06-18 DOI: arXiv:2603.15988

Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech

作者:

Jaesung Bae↗Xiuwen Zheng↗Minje Kim↗Chang D. Yoo↗Mark Hasegawa-Johnson↗

arXiv:2603.15988v3 Announce Type: replace-cross Abstract: Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evaluation is costly and difficult to scale, and the scarcity of labeled data limits robust objective modeling. To address this, we propose a three-stage framework that leverages unlabeled dysarthric speech and large-scale typical speech datasets to scale training. A teacher model first generates pseudo-labels for unlabeled samples, followed by weakly supervised pretraining using a label-aware contrastive learning strategy that exposes the model to diverse speakers and acoustic conditions. The pretrained model is then fine-tuned for the downstream DSQA task. Experiments on five unseen datasets spanning multiple etiologies and languages demonstrate the robustness of our approach. Our Whisper-based baseline significantly outperforms SOTA DSQA predictors such as SpICE, and the full framework achieves an average SRCC of 0.761 across unseen test datasets.

阅读与讨论 → 访问原文 →

25.

arXiv (quant-ph) 2026-06-17 DOI: arXiv:2605.27841

Coherent Dark State Formation of a Lead-Vacancy Spin Qubit in Diamond

作者:

Yiyang Chen↗Koyo Hirai↗Tzyy Zheng Neo↗Eiki Ota↗Takashi Taniguchi↗Masashi Miyakawa↗Shinobu Onoda↗Toshiharu Makino↗Mutsuko Hatano↗Takayuki Iwasaki↗

arXiv:2605.27841v2 Announce Type: replace Abstract: A lead-vacancy (PbV) center in diamond exhibits coherent emission above the liquid helium temperature, making it highly attractive for quantum network applications. Here, we report the magneto-optical and spin properties of PbV centers in diamond. We record a spin lifetime of 12 ms at 7.5 K under large off-axis magnetic field. Furthermore, we observe formation of the coherent dark state by coherent population trapping and estimate a spin dephasing time of 177 ns at 6.5 K. This work demonstrates the outstanding thermal robustness of the PbV spin compared to other group-IV centers above 4 K.

阅读与讨论 → 访问原文 →