探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16989

Stable Menus of Public Goods: AI-Enabled Progress

作者:

Sara Fish↗

arXiv:2606.16989v1 Announce Type: cross Abstract: Using an open problem from the EC 2025 paper "Stable Menus of Public Goods" as a testbed, we conduct experiments to understand the effectiveness of different AI-for-EconCS research workflows. Specifically, we study three questions: Does providing human intuition in the prompt help? Does automated multi-turn interaction help? And, does an LLM outperform a first-year PhD student? Regarding the first two questions, we provide evidence for the following workflow suggestions: (1) prompting with human intuition can encourage the LLM to have better "taste", (2) multi-turn workflows help when the pipeline encourages "ambitious" steps. Regarding the third question, using an unpublished manuscript written by the paper's senior authors prior to collaborating with the first-year PhD student, we compare the effectiveness of the LLM with that of the first-year PhD student, and find that the LLM is slightly less effective.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13247

EPIG: Emotion-Based Prompting for Personalised Image Generation

作者:

Emna Othmen↗Mohamed Yassine Landolsi↗Lotfi Ben Romdhane↗

arXiv:2606.13247v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved impressive results in synthesizing high-quality images from natural language prompts. However, commonly used prompting strategies remain relatively generic, limiting the model's ability to accurately express emotional intent and nuanced affective attributes. This work proposes EPIG, a method that enhances emotional expressiveness at the prompt level prior to image generation. Grounded in psychologically informed emotion representations (valence-arousal) and leveraging structured, role-aware prompt enrichment, EPIG enriches emotion-related components of prompts without modifying or retraining the image generation backbone. The resulting emotion-aware prompts guide the generative process toward more emotionally coherent visual outputs, with particular effectiveness in controlling arousal. EPIG is lightweight, training-free, and well suited for resource-constrained and personalized image generation scenarios. Experimental results on a benchmark of 10 diverse prompts show that EPIG reduces mean arousal error compared to strong baselines, including naive insertion and LLM-based prompt expansion, with reductions of 14% and 12%, respectively. These improvements are statistically significant. EPIG also preserves valence alignment and semantic consistency, as measured by CLIPScore and supported by ablation studies. The effect is more pronounced on prompts containing explicit subjects such as humans, children, or animals, where the reduction reaches 17%, highlighting the subject-sensitive behavior of the proposed method.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-11 DOI: arXiv:2606.11522

Search Discipline for Long-Horizon Research Agents

作者:

Adithya Srinivasan↗Devesh Paragiri↗

arXiv:2606.11522v1 Announce Type: new Abstract: Autoresearch agents now propose, evaluate, and select scientific candidates against a metric, and that metric is usually an aggregate reduced over a heterogeneous space of regions, slices, or cohorts. We show that when scientific validity lives in that disaggregated structure, the aggregate can rank the wrong candidate first. The headline number improves while the structure underneath inverts, so a decision made on the number accepts a candidate that quietly breaks the model. The failure is not domain-specific. It appears wherever a candidate's validity is multi-dimensional but its verifier is a single reduction. We demonstrate the inversion on a fire-model task in the Ecosystem Demography model. The highest-scoring candidate and a slightly lower one are within noise of each other on global score, yet the top-scoring one collapses the protected boreal regions while the other preserves them. What separates them is the per-region behavior, not the headline number. This decision should not be left to the agent that produced the candidates. The agent optimizing the score is the last party likely to catch the score being wrong, and a prompt has no remaining turn once the agent has stopped. We move the decision to an external control loop that audits each candidate on its disaggregated behavior and acts after the agent has decided. It can demote a candidate the agent would have accepted, and it can reopen a run the agent had declared finished. Our contribution is the inversion finding itself, and a search-discipline protocol that decides on reviewable candidate-effect evidence instead of the score.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.16501

Post-Hoc Merging is Not Enough: Many-Shot Model Merging with Loss-Gap Balancing

作者:

Kyungjin Im↗Miru Kim↗Chanin Eom↗Minhae Kwon↗

arXiv:2606.16501v1 Announce Type: new Abstract: Model merging has become a practical post-training strategy for building a single multi-task large language model (LLM) by combining multiple task-specialized models. However, most existing approaches rely on post-hoc merging, in which task-specific models are merged only once after training. This one-shot aggregation often suffers from task interference, leading to information erasure across individual tasks. In this work, we show that replacing post-hoc merging with an iterative many-shot merging protocol is effective in improving multi-task performance. Building on this insight, we propose METIS, Mitigating Erasure from Task Interference for Stable many-shot merging. METIS is a loss-aware many-shot merging method that addresses information erasure in post-hoc merging through task-wise loss-gap weighting and consensus-based masking. Notably, METIS exhibits significant performance improvement on the worst-performing task, effectively mitigating information erasure. (Project page: https://imkyungjin.github.io/METIS/)

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11507

SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining

作者:

Abdalmalek Aburaddaha↗Venkatraman Narayanan↗Keval Thaker↗Samir A. Rawashdeh↗

Mining hard, safety-critical scenes from driving logs is bottlenecked by the absence of difficulty labels, and no single proxy, collision risk, trajectory ambiguity, or semantic rarity suffices to find such scenes on its own. We present SceneMiner, a unified, camera-only bird's-eye-view pipeline that emits complementary mining signals from a frozen vision-language backbone in a single forward pass, with no LiDAR or radar: a retrieval embedding for text-prompted scenario search, a multi-label scene-tag distribution, and a continuous physics-based risk score (a motion forecast is a byproduct, not a contribution). Building such a multi-head model exposes our central finding, a failure mode we term cross-task interference: adding or upgrading one head shifts a shared activation stream and degrades weight-frozen sibling heads, so freezing parameters alone is insufficient. Our contribution, identity-preserving multi-task fine-tuning, removes this interference by zero-initializing every new sub-module and freezing every parameter that feeds the shared stream. The mining heads are thereby preserved bit-identically while training only ~102k parameters. The tagging head reaches mAP 0.4614 (micro-F1 0.5557) on 20 scene tags by pooling each scene into 32 visual tokens, and the embedding head supports text-prompted retrieval, validated qualitatively. Code is available at: https://anonymous.4open.science/r/sceneminer_anonymous-64E5

阅读与讨论 → 访问原文 →

06.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13610

One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders

作者:

Minghao Luo↗Liang Chen↗

Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This creates a new risk: generative recommenders may consume polluted web content, such as fake reviews and promotional pages crafted to mislead recommendations. We ask: to what extent do search-augmented LLMs become unwitting promoters of fake products when consuming polluted retrieval results? To answer this, we introduce FORGE (Fake Online Recommendations in Generative Environments), a benchmark for measuring fake-product promotion under controlled web-content pollution. Given an upstream search result, FORGE locally rewrites real products in retrieved web pages into fake ones to simulate web-content pollution, and measures how often the LLM recommends the fake product. FORGE covers 225 real-world products across 15 categories and 5 consumer scenarios. Across 12 commercial and open-weights LLMs, all models are vulnerable: a single polluted page yields fooled rates of up to 27%, while the full top-3 replacement raises this to 73.8%. Vulnerability varies substantially across categories, increasing when models lack stable prior knowledge of the relevant products. Reasoning does not mitigate this vulnerability; instead, it often generates spurious social proof to justify false recommendations. We evaluate three defenses: skepticism prompting and consensus filtering (over model priors or cross-document evidence). Skepticism can exacerbate vulnerability, much like reasoning, while filtering risks suppressing legitimate products. We release FORGE at https://github.com/leoluolol/forge-benchmark.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2512.20014

Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting

作者:

Sangoh Lee↗Sangwoo Mo↗Wook-Shin Han↗

arXiv:2512.20014v3 Announce Type: replace-cross Abstract: While Vision-Language-Action (VLA) models generalize well to generic instructions, they struggle with personalized commands such as "bring my cup," where the robot must act on one specific instance among visually similar objects. We study this setting of manipulating personal objects, in which a VLA must identify and control a user-specific object unseen during training using only a few reference images. To address this challenge, we propose Visual Attentive Prompting (VAP), a simple-yet-effective training-free perceptual adapter that equips frozen VLAs with top-down selective attention. VAP treats the reference images as a non-parametric visual memory, grounds the personal object in the scene through open-vocabulary detection and embedding-based matching, and then injects this grounding as a visual prompt by highlighting the object and rewriting the instruction. We construct two simulation benchmarks, Personalized-SIMPLER and Personalized-VLABench, and a real-world tabletop benchmark to evaluate personalized manipulation across multiple robots and tasks. Experiments show that VAP consistently outperforms generic policies and token-learning baselines in both success rate and correct-object manipulation, helping to bridge the gap between semantic understanding and instance-level control.

阅读与讨论 → 访问原文 →

08.

medRxiv (Medicine) 2026-06-11 DOI: HASH:cad4b9149156755c231c50ff37e2997d

Wealth-Related Inequalities in Cesarean Section Utilization Among Facility-Based Births in Bangladesh: Evidence from Public and Private Healthcare Facilities

作者:

Mahmud↗

Background Bangladesh has experienced a rapid increase in cesarean section (CS) utilization over the past two decades. While previous studies have documented socioeconomic disparities in CS use, evidence on how wealth-related inequalities differ between public and private healthcare facilities remains limited. This study assessed the magnitude and drivers of socioeconomic inequality in CS utilization among facility-based births in Bangladesh. Methods We analyzed data from 3,008 facility-based births reported in the 2022 Bangladesh Demographic and Health Survey (BDHS). Survey-weighted multivariable logistic regression was used to identify factors associated with CS utilization. Wealth-related inequality was assessed using concentration curves and the Erreygers-corrected concentration index (ECCI). Regression-based decomposition of the standard concentration index was performed to quantify the contribution of socioeconomic, demographic, and healthcare-related factors to observed inequalities overall and separately for public and private facilities. Results Overall, 71.2% of facility-based births were delivered by CS, with substantially higher prevalence in private facilities (84.2%) than in public facilities (35.9%). Women delivering in private facilities had markedly higher odds of CS than those delivering in public facilities (adjusted odds ratio [AOR]: 9.07; 95% confidence interval [CI]: 7.17-11.47). Significant pro-rich inequality was observed overall (ECCI: 0.154; 95% CI: 0.117-0.191), with inequality substantially greater in public facilities (ECCI: 0.189; 95% CI: 0.114-0.264) than in private facilities (ECCI: 0.049; 95% CI: 0.014-0.084). Decomposition analysis showed that household wealth was the dominant contributor to inequality, particularly the richest wealth quintile, accounting for 81.5% of overall inequality, 63.8% in public facilities, and 109.7% in private facilities. Conclusions Wealth-related inequalities in CS utilization remain substantial in Bangladesh despite widespread use of the procedure. Although pro-rich inequality exists across both sectors, inequality is considerably greater in public facilities and is driven by different mechanisms across facility types. Policies should simultaneously improve equitable access to medically necessary CS and reduce unnecessary procedures, particularly within the private sector.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.14528

BayLing-Duplex: Native Full-Duplex Speech Dialogue with a Single Autoregressive LLM

作者:

Qingkai Fang↗Shoutao Guo↗Yang Feng↗

Real-time, full-duplex speech interaction is a key feature of next-generation spoken chatbots, allowing the model to listen and speak at the same time and to handle natural phenomena such as overlap, hesitation, and barge-in. Existing speech language models (SpeechLMs) such as LLaMA-Omni and GLM-4-Voice are still turn-based and rely on an external Voice Activity Detection (VAD) module to mark the end of the user's turn, which fundamentally limits their interactive ability. In this paper, we introduce BayLing-Duplex, a native full-duplex SpeechLM where a single autoregressive LLM decides when to listen, when to speak, and when to stop, with no auxiliary turn-taking module. The design adds only a few special tokens to the standard vocabulary, so it transfers across LLMs and reuses existing training and serving stacks with no architectural adaptation. Starting from the public GLM-4-Voice checkpoint and using only 400K full-duplex samples for fine-tuning followed by a lightweight DPO stage, BayLing-Duplex reaches 92% turn-taking success and 100% interruption success on InstructS2S-Eval, while improving the speech-response score from 2.17 to 3.39 over Moshi. BayLing-Duplex also matches or surpasses its turn-based counterpart on Llama Questions, Web Questions, and Alpaca-Eval, showing that simultaneous listen-and-speak modeling does not sacrifice response quality.

阅读与讨论 → 访问原文 →

10.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.06926

SVHighlights: Towards Extremely Long Sport Video Highlight Detection

作者:

Donggyu Lee↗Youngbin Ki↗Jeonghun Kang↗Taehwan Kim↗

While highlight detection for long-form videos is of great practical importance, most existing methods remain limited to short-form content, largely due to the absence of a suitable benchmark. To bridge this gap, we introduce SVHighlights, to the best of our knowledge, the first benchmark for highlight detection in extremely long sports videos, each exceeding one hour in duration, across multiple sports categories. SVHighlights is constructed from pairs of full-length sports videos and their corresponding official highlight videos using a dataset generation pipeline, enabling scalable label generation without conventional per-clip saliency annotation. The benchmark comprises 320 videos with an average duration of 2.00 hours and a total of 640.18 hours, substantially exceeding previous datasets. Existing methods also face fundamental challenges on long videos: models trained on short clips fail to generalize to hour-long content, and their clip-level scoring lacks the broader context needed to identify highlights. To address this and provide a strong baseline, we present TF-SELECTOR, a training-free segment-based approach that divides each video into context-aware segments by merging adjacent shots sharing the same semantic content, and predicts segment-level saliency scores using a large language model with multimodal inputs including visual captions, transcripts, and audio volume. Experiments demonstrate that TF-SELECTOR achieves superior performance across most metrics compared to Video Temporal Grounding (VTG)-tuned baselines, with improvements of +2.50 in HIT@1, +4.04 in HIT@K, and +2.95 in IoU. These results establish SVHighlights as a challenging testbed for long-form highlight detection and demonstrate that a simple segment-based strategy can effectively scale to hour-long videos.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.LG) 2026-06-12 DOI: arXiv:2606.12497

$\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models

作者:

Egor Cherepanov↗Nikita Kachaev↗Daniil Zelezetsky↗Aydar Bulatov↗Artem Pshenitsyn↗Yuri Kuratov↗Alexey Skrynnik↗Aleksandr I. Panov↗Alexey K. Kovalev↗

arXiv:2606.12497v1 Announce Type: new Abstract: Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumption that fails under partial observability, where decisions depend on information no longer visible. Existing memory-augmented VLAs simultaneously introduce recurrence, retrieval, compression modules, auxiliary objectives, hierarchical memory, or task-specific architectural changes, so the contribution of recurrence itself remains entangled with surrounding machinery. We present a controlled isolation study of recurrence in a strong pretrained VLA backbone. Our formulation augments the transformer with a small set of learnable memory tokens carried across timesteps and updated through self-attention, trained end to end with truncated backpropagation through time, with no auxiliary losses and no architectural changes. We instantiate this as $\mu$VLA, a family of OpenVLA-OFT variants parameterized by memory width m, TBPTT length K, and the memory update rule (cross-step gradients or a detached EMA), so that recurrence is the only varying factor. On MIKASA-Robo, $\mu$VLA improves average success rate on five training tasks from 0.42 to 0.84 at the strongest setting and reaches 0.23 on held-out tasks with the same memory structure versus 0.07 for the memoryless baseline. On tasks requiring different memory structure, performance remains near baseline. On LIBERO, the strongest recurrent variant achieves 96.2% average success, indicating no regression under full observability. We interpret these results as a calibration of the capability envelope of minimal in-backbone recurrence, identifying the regime in which it is sufficient and the regime where additional memory structure is required. Demos and videos can be found in https://avanturist322.github.io/mu-vla/.

阅读与讨论 → 访问原文 →

12.

arXiv (quant-ph) 2026-06-19 DOI: arXiv:2606.20387

Interaction geometry and ground-state properties of sparse quantum lattice models

作者:

Alex Gunning↗Sebastian Schmid↗Zhengxiao Liu↗Sridevi Kuriyattil↗Aydin Deger↗Andrew J. Daley↗

arXiv:2606.20387v1 Announce Type: new Abstract: We investigate how interaction geometry shapes the low-energy phases of sparse tunable long-range quantum models. We focus on a class of graphs whose degree grows logarithmically with system size, and show how symmetry and frustration in graph connectivity can drive, suppress, and reshape ground-state phase transitions. The central examples are power-of-$p$ graphs, where even and odd values of $p$ exhibit qualitatively distinct behaviour: even-$p$ graphs inherit the rich phase structure of the power-of-two model, while odd-$p$ graphs are governed by geometric frustration. Fibonacci graphs provide a contrasting case, lacking the discrete self-similarity of the power-of-$p$ family but exhibiting a direct geometric mapping between the short- and long-range limits. Across our models, we find that phase structure and criticality are governed by the same effective-geometry principle, unifying our framework for experimentally motivated long-range quantum systems.

阅读与讨论 → 访问原文 →

13.

medRxiv (Medicine) 2026-06-17 DOI: HASH:df041ec0ec230670ae40dbce596186e3

Clinician knowledge and self-efficacy in snakebite management: A cross-sectional assessment in Northern Uganda

作者:

Kamugisha↗MUSOKE↗Ssewante↗Bongomin↗

Background: Snakebite envenomation (SBE) is a major public health crisis in rural Uganda, yet it remains a neglected tropical disease. Effective management is often compromised by systemic barriers and a lack of clinician training. This study assessed clinician self-efficacy and objective knowledge regarding SBE management in Northern Uganda. Methods: A descriptive, cross-sectional study was conducted between February and July 2025 among 379 healthcare workers in Gulu, Omoro, and Pader districts. A validated questionnaire was used to collect data on socio-demographics, self-reported efficacy (scale 1-10), and objective knowledge. Knowledge scores [&ge;]70% were categorized as adequate. Multivariable logistic regression identified independent predictors of adequate knowledge, and Spearmans correlation ({rho}) assessed the relationship between knowledge and self-efficacy. Results: The participants had a mean age of 35.6 years (SD {+/-}7.3), were predominantly female (56.5%, 214/379), and most (83.6%, 317/379) practiced at Health Centre III level facilities. While 53.8% (204/379) reported prior training, 48.3% (183/379) of these had not received an update in over 10 years. Adequate knowledge was demonstrated by 51.5% (195/379) of participants. In the multivariable analysis, practicing in Omoro (adjusted odds ratio [aOR]: 0.3, 95% CI: 0.1-0.6, p < 0.001) or Pader (aOR: 0.2, 95% CI: 0.1-0.4, p < 0.001) was associated with lower odds of adequate knowledge compared to Gulu district. Prior training significantly increased the odds of adequate knowledge (aOR: 2.3, 95% CI: 1.3-4.2, p = 0.006). A moderate positive correlation was observed between self-efficacy and objective knowledge (Spearmans {rho} = 0.33, p < 0.0001). Conclusion: Approximately half of the frontline healthcare workers in Northern Uganda lack adequate knowledge on SBE management, with significant geographic differences and outdated training. The gap between clinician self-efficacy and objective knowledge poses a risk to patient safety. Regular, mandatory refresher training and targeted educational outreach to remote districts are required to reduce SBE-related morbidity and mortality.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12699

LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data

作者:

Yifan Gao↗Yanmin Gong↗Yun Shi↗Yuanxiong Guo↗

arXiv:2606.12699v1 Announce Type: cross Abstract: Type 2 Diabetes (T2D) poses an increasing global health threat, demanding effective glycemic assessment to support personalized and improved diabetes care. Wearable sensors such as continuous glucose monitors (CGM) and fitness trackers offer many valuable insights for glycemic assessment. However, effectively analyzing these data requires integration with essential individual-level context. Existing methods are often based on traditional machine learning (ML) and rely primarily on historical blood glucose measurements and overlook personalized information, which limits their performance across diverse diabetes populations. Recent advances in large language models (LLMs) have demonstrated their ability to integrate diverse data modalities while modeling sequential dependencies, motivating the exploration of their potential for personalized glycemic assessment. In this paper, we propose GlyLLM, an LLM-powered framework for modeling CGM-based glycemic dynamics through the integration of wearable sensor data and structured metadata. GlyLLM can leverage the extensive prior knowledge of pre-trained LLMs and achieve sensor-text semantic abstraction at decision time. Experiments on two related tasks on the AI-READI dataset demonstrate that our model outperforms traditional ML methods by an average of 13.66\% in Root Mean Squared Error (RMSE) for glucose forecasting and 13.08\% in Area Under the Receiver Operating Characteristic (AUROC) for diabetes categorization. Additionally, our ablation study shows that diabetes surveys and biometric tests are more critical than other health information for glycemic assessment. Our work presents a promising step toward harnessing the power of LLMs to advance personalized glycemic assessment in T2D care.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17328

MemTrace: Probing What Final Accuracy Misses in Long-Term Memory

作者:

Xianxuan Long↗Zhikai Chen↗Shenglai Zeng↗Shouren Wang↗Kai Guo↗Jiliang Tang↗

arXiv:2606.17328v1 Announce Type: new Abstract: LLM agents increasingly maintain long-term memory of user facts across sessions. Yet such memory is usually evaluated by aggregating accuracy over question rows or episodes. Because this approach scores question rows independently, even when several questions probe the same fact, it cannot show how that fact behaves as conditions change. We introduce MemTrace, a benchmark whose unit of measurement is the knowledge point: a single typed fact about the user, rather than an individual question. MemTrace probes each fact along three controlled dimensions: memory age, defined by how many sessions ago the fact appeared in the history; question type, covering current state, earlier state, and trajectory of change; and evidence condition, covering present, missing, and contradicted-by-false-premise settings. Evaluating 13 memory-system configurations across four paradigms, we find that similar pooled accuracy hides different failures: recovering a fact's current and earlier states does not imply tracking how it changed, and safe abstention does not imply correcting a false premise. The dominant bottleneck is evidence use, not retrieval: when systems fail, the evidence was retrievable 10 times more often than it was missing. These results suggest that improving long-term memory requires better use of reachable evidence, not simply more storage or retrieval.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2509.14860

MARIC: Multi-Agent Reasoning for Image Classification

作者:

Wonduk Seo↗Minhyeong Yu↗Hyunjin An↗Seunghyun Lee↗

Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate some of these constraints, they remain limited by their reliance on single pass representations, often failing to capture complementary aspects of visual content. In this paper, we introduce Multi Agent based Reasoning for Image Classification (MARIC), a multi agent framework that reformulates image classification as a collaborative reasoning process. MARIC first utilizes an Outliner Agent to analyze the global theme of the image and generate targeted prompts. Based on these prompts, three Aspect Agents extract fine grained descriptions along distinct visual dimensions. Finally, a Reasoning Agent synthesizes these complementary outputs through integrated reflection step, producing a unified representation for classification. By explicitly decomposing the task into multiple perspectives and encouraging reflective synthesis, MARIC mitigates the shortcomings of both parameter-heavy training and monolithic VLM reasoning. Experiments on 4 diverse image classification benchmark datasets demonstrate that MARIC significantly outperforms baselines, highlighting the effectiveness of multi-agent visual reasoning for robust and interpretable image classification.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.19046

Low-Rank Tensor Completion Based on Fractional Regularization with Ky Fan p-k Norm

作者:

Shan Fan↗Feng Zhang↗Jianjun Wang↗Xi-Le Zhao↗Tingwen Huang↗

This paper addresses low-rank tensor completion (LRTC) by proposing a novel nonconvex surrogate, namely the ratio of the tensor nuclear norm to the tensor Ky Fan p-k norm (TNPK), to accurately approximate the tensor tubal rank. The TNPK possesses appealing properties, including scale invariance, parameter flexibility, and the existence of closed-form solutions under specific choices of p and k. With specific parameter settings of p and k, it reduces to the ratio of the tensor nuclear norm to the tensor Ky Fan k norm (TNK) or the ratio of the tensor nuclear norm to the tensor Frobenius norm (TNF). We construct a LRTC model and, under the tensor null space property (NSP), prove that low-rank tensors are local minimizers of the proposed model. Moreover, we derive the proximal operator of the Ky Fan p-k inverse-norm and further develop an efficient alternating direction method of multipliers (ADMM) algorithm with guaranteed subsequential convergence under mild conditions. Extensive experiments on synthetic and real-world datasets validate the superior performance of our method against state-of-the-art competitors.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2601.19072

HalluJudge: A Reference-Free Hallucination Detection for Context Misalignment in Code Review Automation

作者:

Kla Tantithamthavorn↗Hong Yi Lin↗Patanamon Thongtanunam↗Wachiraphan Charoenwet↗Minwoo Jeong↗Ming Wu↗

arXiv:2601.19072v3 Announce Type: replace-cross Abstract: Large Language models (LLMs) have shown strong capabilities in code review automation, such as review comment generation, yet they suffer from hallucinations – where the generated review comments are ungrounded in the actual code – poses a significant challenge to the adoption of LLMs in code review workflows. To address this, we explore effective and scalable methods for a hallucination detection in LLM-generated code review comments without the reference. In this work, we design HalluJudge that aims to assess the grounding of generated review comments based on the context alignment. HalluJudge includes four key strategies ranging from direct assessment to structured multi-branch reasoning (e.g., Tree-of-Thoughts). We conduct a comprehensive evaluation of these assessment strategies across Atlassian's enterprise-scale software projects to examine the effectiveness and cost-efficiency of HalluJudge. Furthermore, we analyze the alignment between HalluJudge's judgment and developer preference of the actual LLM-generated code review comments in the real-world production. Our results show that the hallucination assessment in HalluJudge is cost-effective with an F1 score of 0.85 and an average cost of $0.009. On average, 67% of the HalluJudge assessments are aligned with the developer preference of the actual LLM-generated review comments in the online production. Our results suggest that HalluJudge can serve as a practical safeguard to reduce developers' exposure to hallucinated comments, fostering trust in AI-assisted code reviews.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18686

ForecastBench-Sim: A Simulated-World Forecasting Benchmark

作者:

Jaeho Lee↗Nick Merrill↗Ezra Karger↗

Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the world is simulated, the same setup can generate continuous or binary forecasting questions at arbitrary time horizons, paired intervention worlds for conditional or causal questions, and resolved examples of rare or disruptive outcomes. We describe the benchmark pipeline, question families, scoring protocol, and release artifacts, and report validation slices from model evaluations and an anonymized human pilot. ForecastBench-Sim is intended to complement real-world forecasting benchmarks by providing controlled, immediately resolvable tasks for studying probabilistic reasoning under dynamic world states.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18681

Moving Beyond Diversity: Visual Token Pruning as Subspace Reconstruction for Efficient VLMs

作者:

Jaeyeon Lee↗Shunjie Wen↗Dong-Wan Choi↗

Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens. While diversity maximization has become a dominant strategy for token reduction, existing methods rely on cosine-based normalized similarity that discards magnitude information, failing to faithfully approximate the original feature representation and leading to suboptimal performance, particularly on compositional multi-skill reasoning tasks. In this paper, we introduce SPARE, a subspace reconstruction method that reformulates token pruning as a column subset selection problem and explicitly minimizes reconstruction error. By iteratively selecting tokens with large projection residuals, SPARE performs reconstruction-driven pruning beyond angular diversity. Moreover, we reveal a counterintuitive anti-relevance phenomenon: tokens with lower image-text relevance score can better preserve contextual information. Based on this finding, we incorporate anti-relevance into SPARE as an additional selection criterion to promote context-aware token selection. Extensive experiments across multiple VLMs and benchmarks demonstrate that SPARE consistently achieves state-of-the-art performance, with strong gains on compositional tasks. When applied to LLaVA, SPARE removes up to 94% of visual tokens while retaining 95% of the baseline performance, all in a fully training-free manner.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.19964

Low-Energy Reduced RISC-V Instruction Subset Processor for Tsetlin Machine Inference at the Edge

作者:

Chanda Gupta↗Sanidhya Bhatia↗Shaurya Priyadarshi↗Himani Panwar↗Rishad Shafik↗Sudip Roy↗

arXiv:2606.19964v1 Announce Type: new Abstract: Tsetlin Machine (TM) is a logic-based machine learning approach that relies on simple bitwise operations and finite-state automata, which makes it attractive for edge AI deployments. Recent work has focused on co-processor and accelerator designs based on Tsetlin Machines (TMs). Although these designs achieve high performance, they typically depend on tightly coupled interfaces, microcode-style programming, and external host processors, limiting flexibility and ease of programming. In this work, we present a domain-specific RISC-V microprocessor architecture and design flow tailored for TM inference. Leveraging the modular structure of RISC-V, we design a reduced instruction subset processor that retains programmability while targeting improved performance and lower energy consumption for TM workloads. Instruction profiling is employed to guide instruction reduction, followed by datapath and control path simplifications tailored to TM inference. Both the baseline RV32IM core and the proposed reduced core are evaluated across multiple datasets and compared with Binarized Neural Networks (BNNs), which serve as a hardware-efficient baseline due to their reliance on bitwise operations during inference. Results show that TM achieves comparable or higher accuracy (e.g., up to 88.18% on CIFAR-2 compared to 60.0% for BNN) while reducing execution time by up to 98% across multiple datasets. Furthermore, the proposed design achieves an average $29.7\times$ reduction in energy consumption, demonstrating its effectiveness for programmable and efficient edge AI systems.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-19 DOI: arXiv:2606.20537

Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

作者:

Liang Su↗

arXiv:2606.20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of execution state: the KV cache. We study the opposite regime: low-latency, small-batch, on-device physical-AI serving, where interactive LLM agents, speech systems, and robot policies repeatedly branch, reset, interrupt, and re-enter under tight responsiveness budgets. We introduce execution-state capsules, a graph-bound checkpoint and restore mechanism for the complete restorable state at a committed boundary. FlashRT is a white-box, backend-facing kernel runtime whose evaluated NVIDIA CUDA backend runs captured graph plans over contiguous static buffers with no block-table indirection. Because the live state is a closed set of named buffers, a capsule can snapshot, restore, fork, or roll back the whole execution boundary, including KV, recurrent state, convolution state, MTP state, and metadata. This moves reuse from token-addressed KV fragments to graph-bound execution-state boundaries. On an RTX 5090, capsule restore is byte-exact at the stored-state level and token-identical under greedy decode. A KV-only ablation diverges, showing that recurrent state is load-bearing. GPU-resident snapshot and restore are sub-millisecond, and TTFT speedup over cold prefill grows from 3.9x at 2k tokens to 27x at 16k tokens. On Jetson AGX Thor and DGX Spark, the same correctness and structural properties hold. Capsules are not a replacement for high-throughput KV-cache serving; they define a complementary latency-first serving point for explicit execution-state reuse.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-15 DOI: arXiv:2606.14361

SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines

作者:

Olga Ovcharenko↗Luciano Duarte↗Sebastian Schelter↗

arXiv:2606.14361v1 Announce Type: new Abstract: Machine learning (ML) pipelines require extensive data preparation, feature engineering, and integration across heterogeneous sources, making them tedious and error-prone to develop. While large language models (LLMs) have recently shown promise for assisting programming tasks, chat-based interfaces provide limited control over pipeline behavior and often produce code that is difficult to optimize or integrate into production systems. We demonstrate SemPipes, a novel programming model that extends ML pipelines with declarative, LLM-powered semantic data operators. SemPipes allows developers to specify high-level natural language instructions for data-centric operations, while seamlessly combining these operators with arbitrary Python code from standard data science libraries. For the semantic operators, it synthesizes specialized implementations at pipeline training time, conditioned on dataset characteristics and pipeline context, enabling the flexible yet controlled integration of LLM capabilities. We demonstrate SemPipes through SemPiper, an interactive interface that visualizes computational graphs of the pipelines, synthesized operator implementations, and optimization trajectories produced by an evolutionary search procedure. Attendees can explore three end-to-end scenarios, modify pipelines, inspect generated code, and observe how semantic operators are synthesized and iteratively optimized. The demonstration highlights how declarative semantic operators enable controllable, optimizable, and practical integration of LLMs into ML pipeline development.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2606.17539

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

作者:

Yatai Ji↗An-Chieh Cheng↗Yang Fu↗Yukang Chen↗Han Zhang↗Zhaojing Yang↗Wei Huang↗Ka Chun Cheung↗Song Han↗Vidya Nariyambut Murali↗Pavlo Molchanov↗Jan Kautz↗…

Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging. Moreover, different spatial queries call for fundamentally different strategies: some are best addressed through purely linguistic, step-by-step deduction, while others require explicit 3D grounding before quantitative inference. We present Dual-Path Spatial Reasoning via Reinforcement Learning for Spatial VLMs (SR-REAL), a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR), which performs step-by-step linguistic deduction, and Detect-Then-Reason (DTR), which detects 3D geometric cues (e.g., centers or bounding boxes) via region tokens before explicit geometric inference. SR-REAL begins with a cold-start supervised fine-tuning stage that constructs LOR and DTR chain-of-thought supervision and exposes a region-to-3D interface, followed by RL that optimizes the policy model with accuracy and format rewards; for DTR, a discrete center-based detection reward further refines geometric alignment. Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines: (i) a single RL-trained model supports both reasoning paths, with DTR excelling in region-aware tasks through precise 3D localization and LOR enhancing general spatial reasoning; (ii) jointly training both paths fosters mutual reinforcement; (iii) high-quality, blended cold-start data is crucial for stable RL optimization; and (iv) the model generalizes across datasets and domains without per-task tuning, demonstrating positive transfer between LOR and DTR.

阅读与讨论 → 访问原文 →

25.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2604.01463

Low-Burden LLM-Based Preference Learning: Personalizing Assistive Robots from Natural Language Feedback for Users with Paralysis

作者:

Keshav Shankar↗Dan Ding↗Wei Gao↗

arXiv:2604.01463v2 Announce Type: replace-cross Abstract: Physically Assistive Robots require personalized behaviors to ensure user safety and comfort. However, traditional preference learning methods, like exhaustive pairwise comparisons, cause substantial physical and cognitive fatigue for users with severe motor impairments. To solve this, we propose a low-burden, offline framework that translates unstructured natural language feedback directly into deterministic robotic control policies. To safely bridge the gap between ambiguous human speech and robotic code, our pipeline uses Large Language Models (LLMs) grounded in the Occupational Therapy Practice Framework. This clinical reasoning decodes subjective user reactions into explicit physical and psychological needs, which are then mapped into transparent decision trees. Before deployment, an automated "LLM-as-a-Judge" verifies the code's structural safety. We validated this system in a simulated meal preparation study with 10 adults with paralysis. Results show our natural language approach significantly reduces user workload compared to traditional baselines. Additionally, occupational therapists confirmed the generated policies are safe and accurately reflect user preferences.

阅读与讨论 → 访问原文 →