中 EN
登录 注册账户

Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达，利用大语言模型自动生成交叉领域文献分析简报。

登录 注册账户
01.
arXiv (math.PR) 2026-06-16

Geometry of critical discrete structures: long-range percolation on the hierarchical lattice and the discrete torus

作者:
Arghyadeep Chatterjee↗Sourish Maniyar↗Sanchayan Sen↗

arXiv:2509.09589v2 Announce Type: replace Abstract: Consider (a) balls $\Lambda_n$ of growing volumes in the $d$-dimensional hierarchical lattice, and (b) the $d$-dimensional discrete torus $\mathbb{T}_n^d$ on $n^d$ vertices. Place edges independently between each pair of vertices $x\neq y\in\Lambda_n$ or $\mathbb{T}_n^d$ with probability $1-\exp(-\beta J(x, y) )$ where $J(x, y) \asymp \| x-y \|^{-\alpha}$ for some $0

阅读与讨论 → 访问原文 →
02.
arXiv (CS.CV) 2026-06-17

ProCUA-SFT Technical Report

作者:
Jaehun Jung↗Ximing Lu↗Brandon Cui↗Muhammad Khalifa↗Shaokun Zhang↗Hao Zhang↗Jin Xu↗Amala Sanjay Deshmukh↗Karan Sapra↗Andrew Tao↗Yejin Choi↗Jan Kautz↗…

Training computer-use agents (CUAs) – models that interact with graphical desktops through screenshots and keyboard/mouse actions – requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content – 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs – and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld – an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

阅读与讨论 → 访问原文 →
03.
medRxiv (Medicine) 2026-06-16

Care Delivery Gap framework: a proof-of-concept patient-reported measure of guideline-referenced care-process omissions in sickle cell disease

作者:
Agbalalah↗Rowaiye↗

Abstract Background:Sickle cell disease (SCD) is concentrated in sub-Saharan Africa, where delivery of guideline-referenced care remains challenging. Current evaluation approaches rely largely on access indicators and clinical outcomes, which do not directly measure care delivery. We developed the Care Delivery Gap (CDG) framework, a patient-reported approach for identifying care-process omissions, and conducted a proof-of-concept study to assess feasibility and explore variation across income strata. Methods: We conducted a cross-sectional framework-development study involving a proof-of-concept sample of 52 individuals with SCD or caregivers recruited through clinics and moderated SCD communities across Africa, North America, and Europe between June 2025 and March 2026. The CDG framework assessed patient-reported omissions in specialist involvement, follow-up continuity, cardiovascular screening, and biochemical surveillance. Analyses were descriptive. Results: Substantial multi-domain care-process omissions were identified despite high reported healthcare engagement. Across geographic income strata, cardiovascular screening was reported by 4/35 (11%) LMIC versus 16/17 (94%) HIC participants, and regular follow-up within the preceding 12 months by 14/35 (40%) versus 16/17 (94%), respectively. High CDG scores, representing 1 omissions across three or four domains, occurred in 20/35 (57%) LMIC compared with 1/17 (6%) HIC participants. Similar disparities were observed across specialist review and vitamin B12 surveillance domains. Conclusion: A structured patient-reported framework identified multi-domain omissions in guideline-referenced SCD care, including among individuals reporting healthcare access. The divergence between access indicators and reported care delivery suggests that service contact alone may not reflect care quality. The framework provides a feasible foundation for future process-level quality measurement in high-burden settings.

阅读与讨论 → 访问原文 →
04.
arXiv (CS.CL) 2026-06-11

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

作者:
Peiqi Jia↗Haonan Jia↗Ziqi Miao↗Linkang Du↗Yuntao Wang↗Zhou Su↗

With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted.

阅读与讨论 → 访问原文 →
05.
arXiv (CS.AI) 2026-06-18

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 →
06.
arXiv (CS.AI) 2026-06-16

FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion

作者:
Zixin Rao↗Wentian Zhu↗Chan Aristella Lu↗Zhaorun Chen↗Wei Niu↗Le Guan↗Bo Li↗Zhen Xiang↗

arXiv:2606.15609v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation. Meanwhile, emerging access-control mechanisms for LLM agents are being explored to block policy-violating requests and prevent misuse. We reveal a novel attack surface arising from agent memory operations: prohibited content that would trigger access control can be fragmented across interactions, stored in long-term memory in benign-appearing form, and later reconstructed through memory retrieval without appearing explicitly in the final user query. We propose FragFuse, the first attack that enables unprivileged users to bypass agent access control by exploiting this temporal channel introduced by long-term memory. FragFuse operates in three stages: (1) identifying rejection-responsive fragments via black-box adaptive querying with fragment masking; (2) injecting these fragments into memory using marker carrier queries; and (3) retrieving and fusing the stored fragments through a follow-up attack query. Although FragFuse can be instantiated manually for individual agents, we further develop a surrogate-based optimization scheme that tunes fusion instructions and marker designs, enabling automated attack generation without violating the attacker's threat-model assumptions. We evaluate FragFuse across four representative agent settings and task domains, covering three state-of-the-art agent access-control mechanisms. FragFuse achieves an average bypass success rate of 86.3% and an average end-to-end harmful task success rate of 41.1% across all settings, with only 4.4% average task-success degradation compared with configurations without access control. We also show that alternative defenses, including state-of-the-art prompt-injection detectors and perplexity detectors, do not effectively address this attack.

阅读与讨论 → 访问原文 →
07.
arXiv (CS.AI) 2026-06-16

Quantifying the Impact of Lossy Compression on Neural Generative Surrogate Modeling

作者:
Zhimin Li↗Harshitha Menon↗Charles Jekel↗Valerio Pascucci↗Peter Lindstrom↗

arXiv:2606.15959v1 Announce Type: cross Abstract: Neural networks are used as generative surrogate models for scientific discovery, which are trainable approximations of scientific simulations. These models enable users to replace time-consuming numerical simulations with learned alternatives, providing quick solutions. However, high-fidelity generative surrogate models require massive training datasets, which can create storage and I/O challenges. Lossy compression is a promising way to reduce this burden, but compression errors may affect the model quality in subtle ways, making it challenging to quantify their impact. In this work, we examine how lossy compression of training data impacts the quality of generative surrogate models. We begin by characterizing the uncertainty inherent in training neural networks, showing that identical training configurations can produce different models. By exploiting this variability, we propose a method to estimate how much compression-induced error a surrogate model can tolerate without affecting its accuracy. Evaluation of two application simulations demonstrates that our approach significantly reduces memory/storage requirements and speeds up training while producing high-quality surrogate models. These results show that lossy compression saves data storage up to 23.7x and 39x with negligible impact on the quality of the surrogate model. Meanwhile, reducing the size of the training data set also enhances the data loading speed and reduces the training time by up to 3x.

阅读与讨论 → 访问原文 →
08.
arXiv (CS.LG) 2026-06-18

Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction

作者:
Marc-Andre Schulz↗Kerstin Ritter↗

arXiv:2606.18420v1 Announce Type: new Abstract: On biomedical tabular data, flexible models such as deep networks, gradient-boosted trees, and kernel methods are repeatedly matched or beaten by linear and logistic regression given the same features. The usual reaction is to treat this as a model-side shortfall, to be fixed with more data, a better architecture, or tuning, on the assumption that the nonlinear structure is there and the model has failed to capture it. We argue that these fixes cannot help when the binding limit is the measurement rather than the model, as it frequently is in biomedicine. Additive noise blurs the population-optimal predictor, and because blurring removes a function's fine, rapidly varying detail before its broad shape, it erases nonlinear structure faster than linear structure. A degree-$k$ interaction is attenuated by the $k$-th power of feature reliability, while the linear part is attenuated only once. At the reliabilities typical of biomedical measurement, the nonlinear advantage can vanish even when the underlying biology is strongly nonlinear, and what the noise removes cannot be recovered by a larger cohort or a more flexible model, only by better measurement. The nonlinearity is hidden, not absent, and a tie between linear and flexible models is not by itself a verdict on the biology. These pieces are classical, drawn from measurement-error statistics, psychometrics, and Gaussian analysis, and we assemble them into an exact excess-risk identity. Measurement reliability is one of three conditions, alongside sample size and feature representation, that must align for a flexible model to help, and together they leave only a narrow window that most biomedical tasks fall outside. Across 140 UK Biobank tasks, the gap between flexible and linear models, where it exists, carries the predicted noise signature, and the three conditions can be separated by intervention but not by a benchmark alone.

阅读与讨论 → 访问原文 →
09.
arXiv (CS.AI) 2026-06-18

Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction

作者:
Yongkyung Oh↗Lynn Talton↗Alex Bui↗

arXiv:2606.18548v1 Announce Type: cross Abstract: Adaptive AI ethics instruction in graduate research training benefits from intake measures that reflect differences in prior LLM experience. Prior coursework or workshop attendance is an obvious candidate, but it is not clear whether it is associated with pre-instruction ratings on key AI perception items. We compare three candidate intake features, self-reported usage frequency, self-rated LLM familiarity, and prior AI education, across five baseline perception outcomes in 93 bioscience graduate and postdoctoral trainees enrolled in a required research ethics course. Usage frequency shows Holm-corrected associations with all five outcomes, self-rated familiarity with three, and prior AI education with none. A threshold-like pattern at the lower end of the scale is most visible for training interest and accuracy trust rather than appearing as a uniform gradient across all five outcomes. In a short intake survey, reported LLM use is more consistently associated with these perceptions than prior coursework or workshops, with self-rated familiarity serving as a secondary indicator. These results suggest that simple pre-instruction behavioral signals can inform lightweight intake profiling for adaptive AI ethics education.

阅读与讨论 → 访问原文 →
10.
arXiv (CS.LG) 2026-06-18

Toward Simultaneously Optimal Regret in U-Calibration

作者:
Rafael Frongillo↗Haipeng Luo↗Nishant A. Mehta↗Jon Schneider↗

arXiv:2606.18527v1 Announce Type: cross Abstract: U-calibration studies online forecasting algorithms whose predictions can be consumed by any unknown downstream agent, guaranteeing sublinear regret simultaneously for all proper loss functions. Existing U-calibration algorithms achieve worst-case optimal $O(\sqrt{T})$ regret for every bounded proper loss, but they fail to adapt to easier losses: as we show, even for smooth losses such as squared loss, they incur $\Omega(\sqrt{T})$ regret instead of the optimal $O(\log T)$ regret. In this work, we show that this limitation is not inherent. Specifically, we design a single forecast algorithm that simultaneously achieves $\tilde O(\sqrt{T})$ regret for every bounded proper loss and $O(\log T)$ regret for every bounded smooth proper loss. More generally, our algorithm also attains logarithmic regret for losses that are smooth relative to the log-barrier, which include several non-Lipschitz examples. Our approach is based on a novel variant of Follow-the-Perturbed-Leader (FTPL) in which perturbations are applied directly in the prediction space using self-concordant noise. The resulting analysis also departs substantially from prior FTPL analyses due to the complex nature of this noise and may be of independent interest.

阅读与讨论 → 访问原文 →
11.
arXiv (CS.AI) 2026-06-11

Implicit Neural Representations of Individual Behavior

作者:
Andrew Kang↗Priya Narasimhan↗

arXiv:2606.12200v1 Announce Type: cross Abstract: We study policy representation learning from unlabeled multi-policy behavioral data. Each episode is generated by a fixed policy, but policy labels are unavailable. This setting appears in robotics play, demonstrations, games, racing, and other datasets where heterogeneous behaviors are mixed without annotations. We introduce Behavioral INR, a self-supervised generative model that adapts implicit neural representations (INRs) from vision to behavior. Instead of mapping coordinates to RGB values, Behavioral INR represents a policy as a state-action function mapping states to subsequent actions. An episode-level latent modulates this function through FiLM layers, yielding a generative prior over policies and allowing policy identity to be inferred without supervision. Because INRs treat each datapoint as samples from an underlying function, the same model naturally accommodates variable episode lengths and different sampling granularities, as in vision INRs with different image resolutions. We also define policy-level out-of-distribution (OOD) shifts along state-distribution and action-distribution axes, which arise when policies overlap in states or actions but are not captured by standard behavioral OOD settings based only on new agents or environments. We evaluate on synthetic Gaussian random field data, MuJoCo demonstrations with controlled OOD splits, and real-world chess, Formula 1 racing, robotics, and Seek-Avoid datasets. Behavioral INR most consistently improves policy identifiability in the hardest continuous state-action settings, especially when longer episodes, more policies, and OOD splits reduce the usefulness of marginal shortcuts; amortized history encoders remain competitive when policy identity can be recovered from symbolic repetition or low-dimensional action statistics. We release code and checkpoints.

阅读与讨论 → 访问原文 →
12.
arXiv (quant-ph) 2026-06-12

Quantized time in quantum walks under weak rank-K measurements

作者:
Klaus Ziegler↗

arXiv:2606.13552v1 Announce Type: new Abstract: Measurements can be used to monitor the evolution of quantum systems and may lead to a universally quantized time statistics. It is known that the mean return time is quantized for strong and indirect monitoring through the winding number of the return amplitude in a one-dimensional space. Here we discuss that under multi-channel strong or indirect monitoring, where the latter is achieved through ancilla coupling, the mean return time of a quantum walk in the projected subspace is also quantized. This reflects a universal time quantization for a higher dimensional evolution.

阅读与讨论 → 访问原文 →
13.
arXiv (CS.AI) 2026-06-11

Autoregressive Direct Preference Optimization

作者:
Masanari Oi↗Mahiro Ukai↗Masahiro Kaneko↗Naoaki Okazaki↗Nakamasa Inoue↗

arXiv:2602.09533v2 Announce Type: replace Abstract: Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the response-level Bradley-Terry (BT) model may limit its full potential, as the reference and learnable models are assumed to be autoregressive only after deriving the objective function. Motivated by this limitation, we revisit the theoretical foundations of DPO and propose a novel formulation that explicitly introduces the autoregressive assumption prior to applying the BT model. By reformulating and extending DPO, we derive a novel variant, termed Autoregressive DPO (ADPO), that explicitly integrates autoregressive modeling into the preference optimization framework. Without violating the theoretical foundations, the derived loss takes an elegant form: it shifts the summation operation in the DPO objective outside the log-sigmoid function. Furthermore, through theoretical analysis of ADPO, we show that there exist two length measures to be considered when designing DPO-based algorithms: the token length $\mu$ and the feedback length $\mu'$. To the best of our knowledge, we are the first to explicitly distinguish these two measures and analyze their implications for preference optimization in LLMs.

阅读与讨论 → 访问原文 →
14.
arXiv (CS.AI) 2026-06-11

GPO: Learning from Critical Steps to Improve LLM Reasoning

作者:
Jiahao Yu↗Zelei Cheng↗Xian Wu↗Xinyu Xing↗

arXiv:2509.16456v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in various domains, showing impressive potential on different tasks. Recently, reasoning LLMs have been proposed to improve the reasoning or thinking capabilities of LLMs to solve complex problems. Despite the promising results of reasoning LLMs, enhancing the multi-step reasoning capabilities of LLMs still remains a significant challenge. While existing optimization methods have advanced the LLM reasoning capabilities, they often treat reasoning trajectories as a whole, without considering the underlying critical steps within the trajectory. In this paper, we introduce Guided Pivotal Optimization (GPO), a novel fine-tuning strategy that dives into the reasoning process to enable more effective improvements. GPO first identifies the `critical step' within a reasoning trajectory - a point that the model must carefully proceed to succeed at the problem. We locate the critical step by estimating the advantage function. GPO then resets the policy to the critical step, samples the new rollout and prioritizes the learning process on those rollouts. This focus allows the model to learn more effectively from pivotal moments within the reasoning process to improve the reasoning performance. We demonstrate that GPO is a general strategy that can be integrated with various optimization methods to improve reasoning performance. Besides theoretical analysis, our experiments across challenging reasoning benchmarks show that GPO can consistently and significantly enhance the performance of existing optimization methods, showcasing its effectiveness and generalizability in improving LLM reasoning by concentrating on pivotal moments within the generation process.

阅读与讨论 → 访问原文 →
15.
Nature (Science) 2026-06-17

Probing picometre-scale interlayer deformations via hyperbolic polaritons

作者:
Shu Zhang↗

The resilience of van der Waals (vdW) materials to large strain fields makes them an ideal platform for tuning electronic, optical and magnetic properties1–4. Although in-plane strain is readily mapped, non-invasive and quantitative characterization of out-of-plane strain remains a formidable challenge, particularly for picometre-scale deformations buried at interfaces. Here we demonstrate a polaritonic optical method that uses the mid-infrared out-of-plane hyperbolic polaritons (oHPs) mode to detect interlayer deformations in prototypical vdW polar insulator–hexagonal boron nitride (hBN). This method uses the softening mechanism of out-of-plane transverse optical (oTO) phonons induced by interlayer strain, enabling highly sensitive detection of picometre-scale deformations. Although these oTO phonon modes are typically spectroscopically ‘dark’, their strain response is activated through the oHPs, achieving an atomic displacement sensitivity of about 10 pm (about 8 × 10−7 times the probing wavelength), enabling ultradeep-subwavelength mechanical interlayer deformation detection. This is experimentally validated in both planar hBN and at the buried interface of quantum dot–hBN nanotube heterostructures. This polariton-based picometrology bridges nanomechanics and photonics, providing a non-destructive lens to visualize hidden stress landscapes with atomic precision. A new polaritonic optical method that uses the mid-infrared out-of-plane hyperbolic polaritons mode is described and experimentally validated to allow the examination of picometre-scale interlayer deformations, providing a bridge between nanomechanics and photonics.

阅读与讨论 → 访问原文 →
16.
arXiv (CS.CL) 2026-06-12

EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery

作者:
Amy Xin↗Jiening Siow↗Junjie Wang↗Zijun Yao↗Fanjin Zhang↗Jian Song↗Lei Hou↗Juanzi Li↗

LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform human-designed approaches. As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments: the resources, constraints, and interfaces that shape agent behavior. We frame this as environment engineering: building environments that amplify productive behaviors, such as open-ended exploration, systematic artifact management, and inter-agent collaboration, while suppressing harmful behaviors, such as reward hacking and high-friction human oversight. We present EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery. EurekAgent engineers the environment along four dimensions: permissions engineering for bounded agent execution and isolated evaluation; artifact engineering for filesystem and Git-based collaboration; budget engineering for budget-aware exploration; and human-in-the-loop engineering for easy human supervision and intervention. EurekAgent sets new state-of-the-art results on multiple mathematics, kernel engineering, and machine learning tasks, including new state-of-the-art 26-circle packing results discovered with less than $11 in total API cost. We open-source our code and results, and call for environment engineering as a core research direction for developing reliable autonomous research agents.

阅读与讨论 → 访问原文 →
17.
arXiv (CS.LG) 2026-06-12

Policy-driven Conformal Prediction for Trustworthy QoT Estimation

作者:
Kiarash Rezaei↗Omran Ayoub↗Paolo Monti↗Carlos Natalino↗

arXiv:2606.12501v1 Announce Type: new Abstract: We propose Conformal QoT, a policy-driven framework that combines statistically guaranteed QoT estimation with operational decision policies, enabling reliable lightpath-feasibility predictions under domain shift and improving accuracy from 92\% to 99.6\% on open datasets.

阅读与讨论 → 访问原文 →
18.
arXiv (CS.LG) 2026-06-19

On the Variance of Temporal Difference Learning and its Reduction Using Control Variates

作者:
Hsiao-Ru Pan↗Bernhard Sch\"olkopf↗

arXiv:2606.20357v1 Announce Type: new Abstract: We analyze the variance of temporal difference (TD) learning using the phased setting with tabular representation, and show that one of the mechanisms behind its ability to reduce variance is by effectively aggregating over a larger number of independent trajectories. Based on this insight, we demonstrate that (1) the variance of TD is asymptotically bounded from above by Monte Carlo (MC) estimators, and (2) shorter horizon updates incurs less variance for a fixed number of samples. Beyond TD, we show that Direct Advantage Estimation (DAE), a method for estimating the advantage function, can be seen as a type of regression-adjusted control variate, which achieves a tighter bound on the variance compared to TD in the large-sample limit. Finally, we numerically illustrate the behaviors of these estimators with carefully designed environments.

阅读与讨论 → 访问原文 →
19.
arXiv (CS.CV) 2026-06-17

Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA

作者:
Yiqing Shen↗Han Zhang↗Mathias Unberath↗

Surgical video question answering requires multi-step reasoning across semantic, spatial, and temporal dimensions. Existing methods architecturally compress videos into discrete token representations and couple visual perception with reasoning. This approach fragments continuous spatial-temporal relationships and has been shown to restrict multi-step reasoning capabilities. We introduce a reinforcement learning (RL) framework that trains large language models (LLMs) to decouple perception from reasoning by operating over digital twin representations constructed from surgical foundation models. Additionally, we introduce hierarchical representations across frame, temporal window, and procedure levels with probabilistic uncertainty estimates. Finally, we propose a novel reward that combines format validation with accuracy assessment through clinical plausibility evaluation and uncertainty-aware calibration for training. To demonstrate the capabilities of this approach, we introduce REAL-Colon-Reason, a colonoscopic benchmark with 2000 question-answer pairs across three complexity levels. We achieve state-of-the-art performance on REAL-Colon-Reason and two existing surgical VideoQA benchmarks REAL-Colon-VQA and EndoVis18-VQA.

阅读与讨论 → 访问原文 →
20.
arXiv (CS.CV) 2026-06-12

MinhwaNet: Faithful but Insufficient Object Grounding in Korean Folk Painting

作者:
Joonhyung Bae↗

Korean folk painting (minhwa) is built from a small vocabulary of auspicious symbols, a tiger for protection, a pair of birds for marital harmony, a peony for wealth, that recur across many of its painted genres. This suggests an obvious computational approach, identify which symbols appear in a painting and read the genre from the inventory. Working with a public corpus that pairs whole paintings, eight-field bilingual curatorial captions, and a separate set of expert object crops, we find that this approach does not work. A model given only a list of which symbols a painting contains predicts the genre far worse than a model that fuses the image with the curatorial text, and forcing the genre representation to be object-grounded actively hurts accuracy. The visual evidence on which the genre prediction rests is nonetheless localized and inspectable. A leakage-safe object evidence map projected from a part-level detector is spatially faithful to where curators isolated symbolic objects and to a patch-based surrogate's own gradient saliency. We name this configuration a faithful-but-insufficient dissociation. The part-level explanation is honest about what the part-level model sees, yet the genre target turns on how symbols are arranged rather than on which ones appear. The same lens separates a content label that survives transfer to held-out source institutions, genre, from a style label that does not, era, a prediction we confirm on two further labels in the corpus. We release the multimodal system, a worked-example reading of one painting's evidence map against its catalogue, and a set of evaluation cautions that recur in long-tailed heritage collections.

阅读与讨论 → 访问原文 →
21.
arXiv (CS.AI) 2026-06-16

Action with Visual Primitives

作者:
Weilong Guo↗Yuchen Wang↗Renping Zhou↗Yunfeng Zhang↗Rui Fang↗Yuyang Pang↗Wenda Xu↗Gao Huang↗

arXiv:2605.22183v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning objective. As a result, the action expert must implicitly relearn cognitive and perceptual capabilities already present in the pretrained VLM, which can limit both learning efficiency and generalization. We introduce AVP (Action with Visual Primitives), an end-to-end architecture that implements this visual-primitive-centric interface: the VLM infers the next-stage target and emits visual-primitive tokens that condition a flow-matching action expert, with supervision derived from end-effector kinematics. Real-robot experiments on general pick-and-place tasks show that AVP improves the success rate by 37.04% over pi_0.5 and outperforms other recent methods, with consistent gains in data efficiency, spatial-compositional generalization, and object-level transfer.

阅读与讨论 → 访问原文 →
22.
arXiv (math.PR) 2026-06-12

Data-driven subsampling rates for diffusion parameter estimation of SDEs

作者:
Felix Lindner↗Andre Schmei{\ss}er↗Felipe Trolldenier↗Raimund Wegener↗

arXiv:2606.13615v1 Announce Type: new Abstract: We study the problem of diffusion parameter estimation for stochastic differential equation (SDE) models in scenarios where data and model are compatible only on specific scales that have yet to be determined. We introduce a simple and efficient method for selecting suitable rates at which given time series data should be subsampled in order to ensure that the statistical structure of the subsampled data is consistent with the behavior of the SDE model on an infinitesimal scale. Our approach is based on analyzing the statistics of the lengths of monotonically increasing or decreasing segments in the subsampled data sequence, which we refer to as monotone runs. As an analytical foundation, we prove for a large class of SDEs with additive noise that the lengths of monotone runs at an infinitesimal scale are approximately geometrically distributed with success probability $1/2$. This universal characterization is employed to derive an automated method for selecting appropriate subsampling rates for given time series data that is directly applicable in real-world scenarios and does not rely on an asymptotic framework of multiscale diffusions. The approach is demonstrated using an application from industrial mathematics concerning surrogate models for fiber lay-down curves in production processes of nonwoven textiles.

阅读与讨论 → 访问原文 →
23.
medRxiv (Medicine) 2026-06-18

From Paper Letters to an Integrated Digital Workflow: Improving Efficiency, Reliability, and Engagement in Health Guidance

作者:
Kakizaki↗Hirafuji↗Araba↗Yoshida↗Aoki↗

Background: Post-checkup health guidance in Japan has traditionally relied on paper-based communication and manual administrative processes. These workflows are time-consuming, prone to transcription errors, and can delay timely engagement with health guidance recipients. Objective: To assess whether replacing a paper-based workflow with an integrated digital system using Microsoft Access, robotic process automation (RPA), and web-based responses could improve administrative efficiency, operational reliability, and engagement among health guidance recipients. Methods: This single-site quality improvement initiative redesigned the existing letter-based workflow. Access served as a central interface for managing recipients and generating guidance letters. RPA (EzRobot) automated repetitive clerical and billing-related tasks. A web form accessed via a QR code enabled recipients to respond digitally. Outcomes included manual administrative handling time per case, occurrence of transcription-related errors, health guidance completion rate, and guidance duration distribution. Results: Following implementation, staff active handling time per case decreased from approximately 10 minutes to less than 1 minute (approximately 30 seconds), while automated RPA execution typically required about 4-5 minutes per case without staff input. No transcription-related errors were detected during the post-implementation observation period. Health guidance completion rates improved from 28.3% to 39.2% (chi-square test, P=200 days decreased from 30.5% to 20.9% and cases with >=240 days decreased from 13.6% to 8.9% (R4 n=59, R5 n=158). Conclusion: An integrated Access-RPA-Web workflow was associated with improvements in administrative efficiency and operational reliability in post-checkup health guidance while retaining human verification and exception handling. This pragmatic, non-AI-dependent approach may offer a useful model for process-level improvement in preventive care settings.

阅读与讨论 → 访问原文 →
24.
arXiv (CS.CL) 2026-06-17

Rethinking Groups in Critic-Free RLVR

作者:
Yihong Wu↗Liheng Ma↗Lingfeng Xiao↗Muzhi Li↗Xinyu Wang↗Yingxue Zhang↗Jian-Yun Nie↗

Reinforcement learning (RL) has become a central paradigm for post-training large language models. Existing critic-free RL methods typically generate a group of rollouts for the same question to estimate value baselines for advantage computation. However, this design suffers from data inefficiency, group synchronization barriers, and inflexibility with structured rollouts. In this work, we revisit the role of the ``group'' and show that its underlying function is not merely to estimate baselines but to prevent false penalties on negative samples. Building on this insight, we propose negative token filtering, a simple and effective strategy that enables stable single-rollout training. We apply it to two batch-level advantage methods, achieving comparable performance on reasoning tasks and stronger performance on agentic tasks relative to group-based RL techniques.

阅读与讨论 → 访问原文 →
25.
medRxiv (Medicine) 2026-06-22

Genetic and Shared Environmental Influences on Cancer Risk and Cross-Cancer Associations in Nordic Twins

作者:
Harris↗J. R↗Clemmensen↗S. B↗Adami↗H.-O↗Mucci↗L. A↗Kaprio↗Hjelmborg↗J. v. B↗

The relative contributions of genetic and shared environmental influences to cancer risk and cross-cancer associations remain poorly understood. We analyzed data from 222,530 same-sex twins from Denmark, Finland, Norway, and Sweden in the Nordic Twin Study of Cancer, including 43,060 incident cancers over a median follow-up of 41.6 years. Using a target trial framework, biometric modeling, and competing-risk adjustment, we estimated familial risk, heritability, and shared environmental contributions across 35 cancer sites. Lifetime cancer risk was 36.5%, increasing to 51.4% in monozygotic (MZ) twins and 45.3% in dizygotic (DZ) twins with an affected co-twin. Overall cancer risk was explained by heritable (28%) and shared environmental (40%) influences. Heritability was highest for prostate (42%), non-melanoma skin (24%), and breast (18%) cancers. Cross-cancer analyses revealed extensive overlap in the genetic and shared environmental factors across sites, consistent with widespread pleiotropy and shared environmental susceptibility. Prostate cancer exhibited the strongest genetic overlap with rectum/anus (12%) and kidney (11%) cancers, whereas co-shared environmental influences were most pronounced for breast-lung (11%), prostate-bladder (11%), and prostate-lung (12%) cancers. These findings show pervasive genetic overlap across cancers at different sites and emphasize the importance of incorporating familial shared environmental exposures into cancer risk prediction and prevention strategies.

阅读与讨论 → 访问原文 →