探索全球前沿学术脉络

01.

medRxiv (Medicine) 2026-06-17 DOI: HASH:c30fbf9538506a52adc72dcd89f9614c

Cardio Heart Connect: Protocol for a Randomized Trial of a Commercially Available mHealth Fitness Intervention for Cardiac Rehabilitation After Transcatheter Aortic Valve Replacement

作者:

Rosen↗Butala↗N. M↗Kramer↗D. B↗Helmkamp↗L. J↗Gama↗Goldberg↗Marzec↗Peterson↗P. N↗…

Background: Despite ample evidence of the benefits of cardiac rehabilitation (CR), few transcatheter aortic valve replacement (TAVR) patients participate. Commercially available mobile health offers an opportunity to deliver activity-promotion content to populations that are challenged to participate in CR. This study aims to test the efficacy of clinically controlled, commercially available fitness programming for improving physical activity and cardiovascular health outcomes designed to be initiated while patients are on waitlists for traditional CR. Methods: The Cardio Heart Connect study is a hybrid type I effectiveness-implementation trial aiming to enroll N=200 patients who have been placed on a cardiac rehab waitlist following a TAVR procedure from the University of Colorado Hospital Heart and Vascular Center. Participants will be randomized 1:1 to the Cardio Heart Connect intervention with commercially available fitness or attention control, designed to control for technology access. At baseline, post-intervention (8 weeks), and follow-up (12 months), we will assess the primary outcome of participants? daily steps as measured by smartwatch accelerometer and secondary outcomes of interest including functional capacity (Duke Activity Status Index; VO2max), quality of life (Kansas City Cardiomyopathy Questionnaire), and cardiovascular health status (Life Essential 8). In addition, we will use mixed methodologies to evaluate the implementation of intervention using the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) Framework. Conclusions: Commercially available fitness programs have the potential to provide more accessible opportunities for patients recovering from TAVR to engage in physical activity and may be preferred due to their customizability, convenience, and ease of scheduling. Overall, this study will provide insight into the use of commercial mHealth to promote activity following TAVR.

阅读与讨论 → 访问原文 →

02.

arXiv (math.PR) 2026-06-15 DOI: arXiv:2011.07199

Laws of Large Numbers for Non-Independent Random Variables on Hyperspaces with respect to the Hausdorff Metric

作者:

Jinping Zhang↗Li Guan↗

arXiv:2011.07199v5 Announce Type: replace Abstract: This paper investigates the limit behavior of the Minkowski sums for sequences of set-valued random variables. When the underlying space is finite dimensional, by using the support function, we establish the weak and strong laws of large numbers for non-independent random variables in the hyperspace with respect to the Hausdorff metric $d_H$.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2606.20014

Hierarchical Control in Multi-Agent Games: LLM-based Planning and RL Execution

作者:

Jannik H\"osch↗Alessandro Sestini↗Florian Fuchs↗Amir Baghi↗Joakim Bergdahl↗Konrad Tollmar↗Jean-Philippe Barrette-LaPierre↗Linus Gissl\'en↗

arXiv:2606.20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies. We propose a hierarchical architecture where a pretrained large language model (LLM) acts as a centralized strategic controller that selects among specialized RL skill policies for a team of agents, while RL policies handle reactive low-level execution. We evaluate this hybrid system in a competitive 2v2 King of the Hill environment against behavior tree (BT) and ``Flat'' RL (end-to-end training without skill decomposition) baselines. The LLM+RL system achieves task performance statistically equivalent to hand-crafted BT (46.4\% vs 51.5\% win rate, $p=0.103$) while both significantly outperform Flat RL trained without skill decomposition. A user study ($n=15$) reveals that 60\% of participants perceive LLM+RL agents as the most human-like ($p=0.027$), citing behavioral adaptability and tactical variability. These results demonstrate that pretrained LLM reasoning can effectively orchestrate pretrained RL skills, achieving competitive multi-agent coordination and superior perceived believability without manual rule engineering.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2606.19684

Exploring Multi-Modal Large Language Models and Two-Stage Fine-Tuning for Fashion Image Retrieval

作者:

Nguyen Cao Hoang↗Hoang Bui Le↗Nam Vo Hoang↗Trung-Nghia Le↗

Composed image retrieval retrieves a target image using a composed query of a reference image and a modified text description. In the fashion domain, this task requires understanding subtle attribute variations such as color, pattern, and texture. However, existing approaches face limitations due to scarce annotated data and simplistic negative sampling. We propose a novel framework that integrates a multi-modal large language model (LLaVA) to generate attribute-aware triplets and introduces a two-stage fine-tuning strategy to enhance contrastive learning. We leverage pretrained vision-language models, such as CLIP-ViT/B32, to generate and concatenate sentence-level prompts with the relative caption and to scale the number of negatives using static representations. Experimental results demonstrate enhanced compositional reasoning and improved fine-grained retrieval behavior, underscoring the feasibility and potential of the proposed framework for fashion retrieval.

阅读与讨论 → 访问原文 →

05.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.16259

Super-Arrhenius relaxation of the triangular plaquette model in any dimension

作者:

Laurent Bartholdi↗Ivailo Hartarsky↗Ivan Mitrofanov↗

arXiv:2606.16259v1 Announce Type: new Abstract: Consider the following plaquette model from statistical physics: a lamp lies at every vertex of the triangular lattice and a switch lies at every even vertex of the (bipartite) dual hexagonal lattice. Each switch toggles the three lamps on its face. The energy of a configuration is the number of ON lamps. For the Glauber dynamics associated with the Gibbs measure defined by this Hamiltonian at any inverse temperature $\beta>0$, we show that, in any dimension $d\ge 2$, the infinite volume relaxation time satisfies \[e^{\beta^2/C}/C \le T_{\mathrm{rel}}\le Ce^{e^{C\beta}}\] for some $C>0$. Our result entails that the Gibbs measure is unique. The $e^{\beta^2}$ scaling was conjectured by Newman and Moore in 1999 and matches the behaviour of supercritical rooted kinetically constrained models such as the East model, thus recovering fragile glass phenomenology in the absence of kinetic constraints. More precisely, we show that, on a torus of side length $2^k$, when $\beta\to\infty$ and $k/\beta\to0$, we have $T_{\mathrm{rel}}=e^{2\beta k(1+o(1))}$. Quite surprisingly, however, we also prove that, on non-periodic finite domains of size $n\le e^{\beta/C}$ for large $C>0$, we have the much larger asymptotics $\ln T_{\mathrm{rel}}=\beta n^{\Theta(1)}$. The main ingredients of the proofs are new results in extremal and enumerative combinatorics and rely on renormalisation ideas for the dynamics and its groundstates also known as the Ledrappier subshift. We note consequences of our results to geometric group theory (more precisely to the complexity of the word problem for the Baumslag finitely presented group) and to ergodic theory.

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.18401

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

作者:

Hongyi Liu↗Haoyan Yang↗Tao Jiang↗Bo Tang↗Feiyu Xiong↗Yuyu Luo↗Zhiyu Li↗

Long-horizon LLM agents generate traces that could become reusable experience, but raw trajectories are noisy, local, and hard to govern. Agent Skills offer a structured artifact for combining procedural guidance, executable resources, and applicability boundaries. Yet open skill ecosystems contain redundant, uneven, environment-sensitive artifacts, and indiscriminate updates can pollute future context. We present SkillsVote, a lifecycle-governance framework for Agent Skills across collection, recommendation, attribution, and evolution. SkillsVote profiles a million-scale open source corpus for environment requirements, quality, and verifiability, and synthesizes tasks for verifiable skills. Before execution, it performs agentic library search over structured skill folders to expose instructional context. After execution, it decomposes trajectories into skill-linked subtasks, attributes outcomes to skill-guided execution, agent exploration, environment, and result signals, and admits only successful reusable discoveries to evidence-gated updates. Experiments on Terminal-Bench 2.0 and SWE-Bench Pro show that SkillsVote improves agent performance on challenging agentic coding benchmarks. The gains arise from two complementary pathways: online evolution over task streams at test time and offline transfer via frozen libraries built from either historical trajectories or curated open source skills.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-19 DOI: arXiv:2603.07236

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

作者:

Mengxuan Wu↗Xuanlei Zhao↗Ziqiao Wang↗Ruicheng Feng↗Zhangyang Wang↗Kai Wang↗

Foundation models are transitioning from offline predictors to deployed systems expected to operate over long time horizons. In real deployments, objectives are not fixed: domains drift, user preferences evolve, and new tasks appear after the model has shipped. This elevates continual learning and instant personalization from optional features to core architectural requirements. Yet most adaptation pipelines still follow a static weight paradigm: after training (or after any adaptation step), inference executes a single parameter vector regardless of user intent, domain, or instance-specific constraints. This treats the trained or adapted model as a single point in parameter space. In heterogeneous and continually evolving regimes, distinct objectives can induce separated feasible regions over parameters, forcing any single shared update into compromise, interference, or overspecialization. As a result, continual learning and personalization are often implemented as repeated overwriting of shared weights, risking degradation of previously learned behaviors. We propose HY-WU (Weight Unleashing), a memory-first adaptation framework that shifts adaptation pressure away from overwriting a single shared parameter point. HY-WU implements functional (operator-level) memory as a neural module: a generator that synthesizes weight updates on-the-fly from the instance condition, yielding instance-specific operators without test-time optimization.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16626

Using AI in engineering education: a balancing act, driven by clear purpose

作者:

Olya Kudina↗

arXiv:2606.16626v1 Announce Type: cross Abstract: Based on a questionnaire of 100 higher-education students, predominantly from engineering-related fields, and a critical review of recent literature, this chapter examines how students use and perceive Large Language Models (LLMs) in engineering education. Students primarily value LLMs for writing support, conceptual clarification, coding assistance, and brainstorming, while simultaneously expressing concerns about inaccuracies, bias, overreliance, academic integrity, and the burden of verification. Through an analysis of two dominant metaphors, namely LLMs as an "oracle" and as a "tutor," the chapter shows how these systems cultivate expectations of authority, expertise, and personalized learning that often exceed their actual capabilities. The chapter further argues that students' attachment to the promises of efficiency and personalized support reflects a form of "cruel optimism," where the perceived benefits of LLMs often depend on the very skills, vigilance, and expertise that students are still developing. Overall, the chapter argues for a purpose-driven and context-sensitive approach to AI integration in engineering education, emphasizing critical AI literacy, reflective assessment design, pedagogical caution, and consideration of broader ethical and environmental impacts.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2606.11686

Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness

作者:

Sawyer Zhang↗Alexander Wang↗Sophie Lei↗

End-to-end task-success is the dominant way to evaluate LLM agents, but one aggregate number tells you that an agent regressed, not where. We present layer-isolated evaluation: a deployed ordering agent is decomposed into a fixed taxonomy of layers (ontology, intent, routing, decomposition, escalation, safety, memory, and cross-cutting envelope/defense), each exercised by its own assertion slice in a deterministic, no-LLM "pure" mode. The pure suite (238 cases across 23 slices; 225 run in 2.39 s, ~10 ms/case) runs in CI on every change against a locked per-slice baseline. We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers. The effect we did not design in is masking: the aggregate pass-rate barely moves (-1.7 to -5.9 pp for six local regressions), while the matching slice craters (-25 to -91 pp). A layer's slice reacting to its own fault is partly by construction; the measured results are (i) the aggregate masking and (ii) that damage stays off the other slices: the injected layer's slice is the single worst-hit in 5 of 7 cases and top-3 in 7 of 7 (mean rank 1.29 of 19). Localization replicates on a second, structurally different tenant (Starbucks SG): all seven matching slices crater, so it is not a single-catalog artifact. We position it as a concrete, deterministic instantiation of the component-level evaluation EDDOps prescribes but leaves unimplemented, with CheckList as ancestor and as the deterministic mirror image of whole-workflow stochastic mutation testing. Our contributions: (a) a fully decomposed, sub-second, no-LLM per-layer harness for a production agent, (b) a coverage-honesty test-adequacy criterion that refuses to score an unexercised layer, and (c) the regression-injection demonstration that per-slice baseline-locked gates localize regressions an aggregate metric masks.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2605.28734

Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests

作者:

Richard J. Young↗Gregory D. Moody↗

A general-purpose language model that answers a harmful question returns text; a coding model that complies with a malicious request can return a working weapon: a keylogger, ransomware, an exploit that runs as written. This asymmetry in the severity of a single act of compliance implies coding-specialized models should clear a higher refusal bar than general-purpose chat models, not a lower one, yet the field cannot tell whether they do. Refusal benchmarks for malicious code are fragmented: they mix requests for executable software with requests for harmful security knowledge and report refusal rates over non-comparable corpora. This paper's central result is that the CODE-versus-KNOWLEDGE classification axis established in a prior four-corpus release remains stable under a substantially expanded corpus pool and an independently refreshed judge panel, evidence that it measures a real construct rather than an artifact of the prompts or judges. Eight corpora spanning diverse elicitation paradigms (direct, jailbreak-decorated, indirect, and agent/interpreter: ASTRA, CySecBench, AdvBench/harmful_behaviors, JailbreakBench, MalwareBench, RedCode, RMCBench, Scam2Prompt) are classified under a five-judge consensus protocol (6,675 prompts x 5 judges = 33,375 calls), reaching Fleiss' kappa = 0.767 [95% CI 0.755, 0.777] ("substantial"). Critically, the panel shares no judge with the prior release (five paid commercial APIs replaced by five open-weight models from five vendors), yet the two panels agree on 94.45% of the 3,133 shared prompts and reach Cohen's kappa = 0.952 [0.942, 0.963] on the 3,031-prompt binary overlap: the axis survives near-total panel replacement. The released bank comprises 4,748 consensus-CODE and 1,923 consensus-KNOWLEDGE prompts, a reliability-quantified benchmark whose central classification axis is shown stable across corpus expansion and judge-panel replacement.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.12730

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

作者:

Rafal Kocielnik↗Pengrui Han↗Peiyang Song↗Myrl G. Marmarelis↗Ramit Debnath↗Dean Mobbs↗Anima Anandkumar↗R. Michael Alvarez↗

Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined with weak context matching left open whether LLMs truly lack coherence or whether the conditions needed to detect such coherence were not met. We contrast Big 5 with the Theory of Planned Behavior (TPB), which measures intention targeted to a specific behavior and predicts human behavior substantially better than broad traits. We run experiments across four behavioral tasks and 11 frontier LLMs, while also varying session context and identity induction. We find that SR-behavior coherence exists but is selective. 1) Within a shared conversation, the Theory of Planned Behavior reaches human-level coherence; Big 5 does not. 2) Across separate conversations, coherence survives only for behaviors anchored outside the immediate prompt, such as implicit bias shaped by training, and collapses when behavior is strongly primed by context, as with sycophancy. 3) Persona prompting makes self-reports more consistent across conversations, but does not bring behavior into alignment. These findings suggest that coarse personality frameworks, such as Big 5 may not be the best tools for testing deployment behavior. More task- and behavior-specific instruments are needed, and even these must be evaluated across tasks and contexts.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2502.07531

VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation

作者:

Sixiao Zheng↗Zimian Peng↗Yanpeng Zhou↗Yi Zhu↗Hang Xu↗Xiangru Huang↗Yanwei Fu↗

Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. While precise control over camera motion, object motion, and lighting is essential for high-fidelity creation, existing methods often treat these factors independently. This overlooks the physical coupling among viewpoint, geometry, and illumination in dynamic scenes, leading to visual inconsistencies such as mismatched shadows and perspective drift under simultaneous changes. We present VidCRAFT3, a unified and flexible I2V framework that explicitly models cross-factor interactions among geometry, motion, and illumination, enabling both independent and joint control over camera motion, object motion, and lighting direction. Image2Cloud provides explicit 3D geometric priors for accurate camera motion control. ObjMotionNet encodes sparse object trajectories into multi-scale motion features to guide realistic object motion. A Spatial Triple-Attention Transformer integrates lighting direction through lighting cross-attention for consistent relighting. To address the scarcity of jointly annotated data, we construct the VideoLightingDirection (VLD) dataset with accurate per-frame lighting direction annotations, and introduce a three-stage progressive training strategy that enables robust learning without fully joint annotations. Extensive experiments demonstrate that VidCRAFT3 achieves state-of-the-art performance in control precision and visual coherence across diverse scenarios.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15963

PreLort: Prefix-Nested LoRA for Federated Fine-Tuning under Rank Heterogeneity

作者:

Muhammad Waseem↗Nurbek Tastan↗Andrej Jovanovic↗Nicholas D. Lane↗Nils Lukas↗Karthik Nandakumar↗Samuel Horvath↗

Federated fine-tuning of large language models using parameter-efficient methods such as LoRA enables privacy-preserving adaptation of foundation models. Heterogeneous hardware resources introduce challenges, as clients with different adapter ranks cannot be directly aggregated. While existing methods enable aggregation under heterogeneous ranks, they fail to control how information is distributed across rank dimensions, leading to suboptimal use of shared low-rank representations. Instead, we propose PreLort: a nested low-rank formulation for federated LoRA that organizes adapter dimensions into a prefix hierarchy. Our approach ensures that lower-rank dimensions encode task-relevant information, while higher-rank dimensions capture additional capacity. Building on this, we introduce (i) a segment-wise aggregation rule that averages only over clients contributing to each rank segment, avoiding dilution from zero-padded lower-rank clients, and (ii) a prefix-nested training strategy that optimizes each adapter under multiple rank truncations, encouraging useful signal to concentrate in low-rank prefix dimensions. Together, these components encourage a consistent low-rank prefix capturing the most task-relevant information, while higher-rank dimensions learn additional capacity. This allows low-rank clients to benefit from richer information contributed by higher-rank clients, as prefix dimensions are consistently learned and aggregated. Experiments demonstrate that our method consistently outperforms prior heterogeneous federated LoRA methods in accuracy and ROUGE-L, while achieving lower or comparable perplexity across multiple base models.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16991

A Multi-Center Benchmark for Abdominal Disease Diagnosis and Report Generation from Non-Contrast CT

作者:

Mariam Elbakry↗Aliaa Sayed Sheha↗Salma Hassan Tantawy↗Aya Yassin↗Concetto Spampinato↗Karim Lekadir↗Xiaomeng Li↗Marawan Elbatel↗

Multiphasic contrast-enhanced CT (CECT) is widely used for abdominal lesion characterization, yet it carries inherent risks of contrast-induced nephropathy, escalates acquisition burden, and heavily contributes to radiologist workload. To address these challenges, we introduce a novel multi-center benchmark for multi-organ abdominal disease diagnosis and automated radiology report generation, which learns to synthesize contrast-enhanced findings from single-phase non-contrast CT (NCCT). To support this, we curated a large-scale dataset of paired NCCT-CECT studies and their corresponding contrast-enhanced radiology reports from two centers, partitioned into internal sets and an external validation cohort. Under a unified evaluation protocol, we benchmarked five contemporary deep learning architectures encompassing chest-specific, abdomen-specific, and general-purpose multimodal domains. Extensive experiments demonstrate that NCCT retains diagnostic signals, achieving an average multi-organ AUC of 69.1% on the internal cohort and 63.1% on the external cohort, respectively. By releasing this dataset and standardized benchmark publicly, this study aims to catalyze future research into safer, resource-efficient, and globally accessible contrast-free abdominal imaging workflows. Code is available at: https://github.com/xmed-lab/TriALS-Report.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14688

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

作者:

Xiaoyu Li↗Andi Han↗Dai Shi↗Zheng Gao↗Jiaojiao Jiang↗Junbin Gao↗

AI systems coupled to proof assistants now generate formal mathematics at scale, and the gap between what a checker can verify and what a mathematician would value has become the binding constraint. We model the generation of valuable mathematics as nested language generation in the limit: a verifiable formal language $F$, accessed through a membership oracle (the proof checker), contains an unknown valuable language $H \in \mathcal{H}$ revealed only through an adversarial enumeration of a core $C \subseteq H$ of exact density $\alpha$ (the literature). Every output is valuable ($\in H$), trivial ($\in F \setminus H$), or a hallucination ($\notin F$). We settle four questions. First, the verifier is not taste: the collections admitting generation with breadth are exactly those of the oracle-free model, characterized fiber-wise by Angluin's condition. Second, the verifier does buy sound coverage, covering all unseen valuable statements while asserting only valid ones: possible with it, impossible without it; it relocates unavoidable errors from false to trivial. Third, and centrally, a sharp dichotomy on the tight family: generators emitting finitely many trivia achieve optimal coverage $\alpha/2$, while any infinite trivia allowance, even at vanishing rate, jumps the optimum to $1-\alpha/2$ (both tight, for cores presented as the candidate intersection), and one generator attains both ends. The transition is in trivia count, not rate; the gap $1-\alpha$ is the unrecorded mass. Fourth, both regimes instantiate in a compression model of mathematics. A perfect verifier cannot substitute for taste: the unbounded stream of correct-but-worthless statements is not an engineering accident but a provable necessity, since covering unrecorded valuable mathematics requires an infinite, but asymptotically negligible, stream of certified trivia.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17519

Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery

作者:

Kellen Gillespie↗Robyn Perry↗

Production LLM assistants route user requests to growing libraries of specialized tools, but how does routing accuracy degrade as the catalog scales? We study single-step routing on a 110-agent, 584-tool catalog from a deployed enterprise productivity assistant, evaluating three frontier models from 10 to 110 agents. Routing F1 on under-specified requests drops 16–23 percentage points across models. An oracle analysis decomposes the degradation into a retrieval gap (the model cannot surface the right tool) and a confusion gap (even with perfect retrieval, the oracle ceiling drops 10pp). Embedding-based shortlisting recovers +10–11pp F1 at full scale across all three models and two providers. A production annotation study (1,435 human-labeled utterances, three annotators) confirms the recovery on real traffic at +10–17pp despite 10–15pp lower absolute performance.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-12 DOI: arXiv:2606.13032

GeoCFNet: Geometry-Aware Confidence Field Network for Robot-Assisted Endoscopic Submucosal Dissection

作者:

Rui Tang↗Guankun Wang↗Long Bai↗Haochen Yin↗Huxin Gao↗Jiewen Lai↗Jiazheng Wang↗Hongliang Ren↗

Advanced surgical robotics has made robot-assisted endoscopic submucosal dissection (ESD) a promising approach for the en-bloc resection of large lesions, with the potential to reduce recurrence and improve long-term outcomes. However, the technical complexity and risk of complications in ESD demand stable and precise visual guidance to maintain an accurate dissection corridor and a safe tissue margin. Dense confidence fields provide an effective representation for this purpose by describing both the preferred dissection region and its spatial transition to surrounding tissue. However, reliable confidence field estimation remains challenging in dynamic endoscopic scenes due to smoke, specular highlights, tissue deformation, weak texture, and the thin geometric structure of the target region. To address these challenges, we formulate dissection guidance as a geometry-aware confidence field estimation problem and propose GeoCFNet, a geometry-aware confidence field network built on a pretrained DINOv3 backbone. GeoCFNet integrates a Token-Differentiated Fusion module to aggregate class-token context with dense patch representations, a SegFormer decoder for confidence regression, and Geometry-Aware Spatial Regularization (GASR) to preserve spatial coherence and local geometric transitions. Experimental results show that GeoCFNet achieves RMSE 0.0480, PSNR 27.1995, SSIM 0.3397, and CC 0.2466, indicating accurate and geometrically stable confidence field estimation for robot-assisted ESD guidance.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17107

Models Take Notes at Prefill: KV Cache Can Be Editable and Composable

作者:

Bojie Li↗

arXiv:2606.17107v1 Announce Type: cross Abstract: Prefix caching reuses prefill only across an exactly shared prefix, so one changed field invalidates the entire downstream cache. Yet overwriting the field's own key/value vectors and reusing the rest leaves the model acting on the old value. The reason, established causally across four model families: at prefill the model has already written the field-conditioned conclusion onto downstream notes; the field's own key/value drives under 1% of the decision. Read as a notebook of memoized conclusions, two capabilities follow. (1) It is editable. A salient erratum amends the notes; and with chain-of-thought, editing the field alone recovers the decision (1.00 at 8B, ~1% compute), while without CoT it is ignored. (2) It is composable. The notes are position-portable, so a precompiled skill can be RoPE-repositioned and spliced into any context, indistinguishable from full recompute (logit cosine 0.90-0.999, twelve models) at O(L) rather than O(L^2) time-to-first-token. A unified edit+compose agent stays decision-identical to recompute at up to 14.9x lower latency. The approach applies to any per-token attention KV cache, validated across scale, quantization, Mixture-of-Experts, and multimodal caches, and extends to several attention variants through small adapters. Because the erratum is append-only, it composes with production prefix caching: in an online vLLM benchmark it keeps the prefix cache-aligned (98.5% hit-rate), cutting p90 time-to-first-token by 53-398x.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.15064

Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering

作者:

Aarav Bedi↗

arXiv:2606.15064v1 Announce Type: new Abstract: Manipulation demonstrations have temporal phase structure, and a natural hypothesis is that demonstration-curation metrics should be applied within phases rather than globally. The idea is to segment each trajectory into phases, score each phase with the metric that is locally most informative, and then aggregate. This follows directly from prior work showing that a single global metric can be the best detector of a defect and yet the worst curator of the resulting policy. We test the per-phase hypothesis on three contact-rich LIBERO pick-and-place tasks with a controlled early-release structural defect, comparing phase-gated curation against the same metrics applied uniformly and against a strong single global metric. Across all three tasks and five random seeds per condition, phase-gated curation is never the best curation strategy, and it is the worst of the three on two of the three tasks (Task 1: 86.0 vs. 92.0 for global; Task 3: 22.7 vs. 48.0 for uniform). We trace the failure to a concrete mechanism. When the defect signal is concentrated in a single phase, rank-aggregating across phases dilutes that signal with uninformative scores from defect-free phases, selecting a worse demonstration subset than simply applying the defect-informative metric everywhere. We further show that the per-phase metric selection does not transfer across tasks, since no phase shares a winning metric between any two tasks, so the selection cannot be reused and must be re-derived per task from a noisy sweep. These results bound a plausible and previously untested method, and they argue that practitioners should prefer identifying a single defect-informative metric over decomposing curation by phase. We release the full pipeline, all metric implementations, and per-seed results.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.06176

RQUL-UIE: Revitalizing Quality-Unstable Labels for Underwater Image Enhancement via In-Dataset Self-Supervision

作者:

Haochen Hu↗Yanrui Bin↗Chih-yung Wen↗Bing Wang↗

Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced significantly, most rely on paired datasets with unstable label quality, which bottlenecks model performance. This paper proposes a diffusion-based, in-dataset self-supervised learning strategy designed to exploit the quality distribution of training labels. Specifically, we evaluate label quality via semantic perception embeddings from a pre-trained diffusion model in a training-free manner. These quality scores are subsequently quantized into noise-level indices, guiding a multi-step denoising process for level-wise supervision. This mechanism prevents low-quality labels from degrading the model while maximizing their utility during training. Furthermore, a Fourier-based refinement network is incorporated to explicitly reconstruct high-frequency components. Extensive evaluations demonstrate that our method consistently outperforms SOTA approaches in restoration quality. The code and pre-trained model will be available once accepted in link.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-11 DOI: arXiv:2601.22025

When Generic Prompt Improvements Hurt: Evaluation-Driven Iteration for LLM Applications

作者:

Daniel Commey↗

Evaluating Large Language Model (LLM) applications differs from conventional software testing because outputs are probabilistic, semantically variable, and sensitive to prompt and model changes. This technical report proposes the Minimum Viable Evaluation Suite (MVES), an audit-oriented structure for application-level LLM evaluation. MVES links application categories to failure modes, metrics, required artifacts, and validation evidence across general LLM applications, retrieval-augmented systems, and agentic workflows. We pair the framework with a reproducible local evaluation harness covering structured extraction, RAG citation/content-compliance, and instruction-following checks. Using Ollama with Llama 3 8B Instruct and Qwen 2.5 7B Instruct, we evaluate five prompt conditions over expanded 30-case-per-suite ablations. The results show that, in the tested local conditions, generic prompt additions do not produce monotonic improvements: stronger output-contract prompts improve strict extraction for both models, while RAG citation/content-compliance declines under some generic-rule conditions. The largest observed decline occurs for Qwen 2.5 on RAG when generic rules are appended to the user prompt, from 26/30 to 9/30. These findings support evaluation-driven prompt iteration: prompt changes should be treated as potential regression risks and tested against task-specific suites before deployment. The accompanying repository contains the test suites, prompt variants, evaluation harness, raw result logs, and scripts needed to reproduce the reported local ablations.

阅读与讨论 → 访问原文 →

22.

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 →

23.

arXiv (CS.LG) 2026-06-18 DOI: arXiv:2606.04404

Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks

作者:

Wenyu Liao↗Yiqing Shi↗Fang Xie↗

arXiv:2606.04404v2 Announce Type: replace-cross Abstract: The deep neural network is a widely used framework in machine learning that has been widely applied in various fields. However, deep neural networks often involve a large number of parameters and inputs, many of which may be irrelevant to the goal or true output. These parameters and input variables not only increase computational complexity, but also contribute to additional computational cost. One solution to this problem is knockoff methods, which have proven successful in controlling false discovery rates in high-dimensional regression. Building on the knockoff methods and using the regularised neural network, this paper proposes three variable screening methods under the condition of controlling false discovery rates: one layer filter, multiple layers filter, and variable weight aggregation filter. In comparison with existing algorithms, we find that our algorithms show satisfactory performance.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19521

Interactive Pareto navigation for deep multi-task learning

作者:

Augustina C. Amakor↗Konstantin Sonntag↗Sebastian Peitz↗

arXiv:2606.19521v1 Announce Type: new Abstract: In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity to choose appropriate trade-offs. A widely used approach is thus to aggregate the individual losses in a single loss function by a weighted sum. This often fails to capture either the decision maker's preferences as a result of the shape of the Pareto front, or requires multiple adjustments and computations which becomes prohibitively expensive in deep learning applications. To address these issues, we introduce a novel framework, Preference Pareto Exploration (PPE), which enforces the decision maker's preferences while accounting for the geometry of the Pareto set in an interactive exploration process. PPE is based on a predictor-corrector method that performs predictor steps tangential to the manifold of Pareto-optimal solutions, following the decision maker's preference. The subsequent corrector step results in a new trade-off reflecting this preference. To avoid explicit Hessian computations when characterizing the tangent space of the manifold, we employ a Krylov subspace method that relies solely on matrix-vector products. These products can be efficiently obtained via automatic differentiation, ensuring both efficiency and robustness throughout the optimization process. The method's functionality and performance are demonstrated using both toy problems and examples from deep learning.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16032

Machine learning enables roughness-driven inverse design of milling processes

作者:

Hadi Bakhshan↗Sima Farshbaf↗Fernando Rastellini↗Josep Maria Carbonell↗

arXiv:2606.16032v1 Announce Type: cross Abstract: Interest in applying data-driven approaches in manufacturing has grown significantly, particularly for mapping complex, high-dimensional relationships. The milling process is one area where predictive models can link influential parameters to surface roughness metrics prior to in situ operations. While this approach offers clear advantages, it faces challenges due to limited datasets and robustness issues in inverse design paradigms. To address these challenges, this paper proposes a machine learning (ML)-based framework for the inverse design of the surface milling process, with a focus on surface roughness as the design objective. The framework employs forward training of two ML models, a deep neural network (DNN) and a random forest (RF) ensemble, both developed using a high-fidelity synthetic dataset generated from a computational simulation framework. These trained models are integrated into a Bayesian optimization (BO) procedure to overcome the multiplicity problem arising from the many-to-one mapping inherent in the dataset. The approach identifies top-performing milling process configurations, considering both process and tool parameters, and presents them from the full solution space. The models achieve average relative errors below 5% when compared to reference results, thereby demonstrating the robustness and reliability of the proposed methodology.

阅读与讨论 → 访问原文 →