×

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。

作者: Hou ×
换一批
01.
medRxiv (Medicine) 2026-06-15

Sociodemographic Disparities in Tafamidis Initiation and Clinical Outcomes in ATTR-CM Across the United States

BACKGROUND Transthyretin amyloid cardiomyopathy (ATTR-CM) is a progressive, life-threatening disease. Sociodemographic factors may influence time to treatment initiation and resulting clinical outcomes, yet these relationships are poorly characterized. OBJECTIVE Assess the effects of sex and race on tafamidis initiation and subsequent outcomes and their interaction with factors such as ATTR-CM type and social deprivation measures. METHODS A retrospective cohort analysis was conducted using the US Komodo Healthcare Map (01/2016-06/2024) among patients with amyloidosis, identified by ICD-10-CM diagnosis codes. Cumulative incidence of treatment initiation and survival probabilities for cardiovascular-related hospitalization (CVH) or death were estimated by Kaplan-Meier, stratified by sex and race. Cox proportional hazards models were fitted for both endpoints to estimate hazard ratios, adjusting for demographics and clinical characteristics. RESULTS Of 11,311 patients identified, White and Black patients (n=9,223) were included in subsequent analyses. Within 12 months of diagnosis, White women had the lowest cumulative incidence of tafamidis initiation (11.4%), followed by Black women (22.0%), Black men (26.7%), and White men (31.0%). Event-free survival at 12 months was lowest in Black women (42.9%), followed by Black men (46.8%), White women (48.6%), and White men (54.4%). Median (95% CI) time to CVH or death was shortest for Black women (8.0 months [6.8-10.0]) followed by Black men (9.9 months [8.8-12.0]), White women (11.0 months [9.6-13.0]), and White men (15.0 months [14.0-16.0]). CONCLUSIONS In this large, real-world cohort of US patients with ATTR-CM, sex and race contributed to disparities in tafamidis initiation and survival, underscoring compounded disparities in both access and outcomes.

02.
arXiv (CS.CV) 2026-06-12

Modality-Aware Feature Matching in Visual and Vision-Language Applications: A Comprehensive Survey

Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring traditional handcrafted methods and emphasizing contemporary deep learning approaches across various modalities, including RGB images, depth images, 3D point clouds, LiDAR scans, medical images, and vision-language interactions. Traditional methods, leveraging detectors like Harris corners and descriptors such as SIFT and ORB, demonstrate robustness under moderate intra-modality variations but struggle with significant modality gaps. Contemporary deep learning-based methods, exemplified by detector-free strategies like CNN-based SuperPoint and transformer-based LoFTR, substantially improve robustness and adaptability across modalities. We highlight modality-aware advancements, such as geometric and depth-specific descriptors for depth images, sparse and dense learning methods for 3D point clouds, attention-enhanced neural networks for LiDAR scans, and specialized solutions like the MIND descriptor for complex medical image matching. Cross-modal applications, particularly in medical image registration and vision-language tasks, underscore the evolution of feature matching to handle increasingly diverse data interactions.

03.
arXiv (CS.LG) 2026-06-11

A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth

arXiv:2601.21817v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on open-ended tasks without ground-truth labels is increasingly done via the LLM-as-a-judge paradigm. A critical but under-modeled issue is that judge LLMs differ substantially in reliability; treating all judges equally can yield biased leaderboards and misleading uncertainty estimates. More data can make evaluation more confidently wrong under misspecified aggregation. We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters, jointly estimating latent model quality and judge reliability from pairwise comparisons without reference labels. We establish identifiability up to natural normalizations and prove consistency and asymptotic normality of the maximum likelihood estimator, enabling confidence intervals for score differences and rank comparisons. Across multiple public benchmarks and a newly collected dataset, our method improves agreement with human preferences, achieves higher data efficiency than unweighted baselines, and produces calibrated uncertainty quantification for LLM rankings.

04.
arXiv (CS.CV) 2026-06-12

VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents

We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric development, where agents must produce functional, visually coherent applications from underspecified inputs. We define five prompt-information conditions that vary along two axes, visual/structural fidelity and stack constraint: (1) text only with free stack choice, (2) text with reference screenshots under three specified stacks, (3) text with reference screenshots under free stack choice, (4) text with screenshots and pruned Figma structure under a single specified stack, and (5) text with screenshots and pruned Figma structure under free stack choice. To enable robust evaluation, each page in the benchmark is manually annotated with interactive UI components and around three visual anchor points, addressing the well-known limitations of script-based testing tools such as Playwright in open-ended code generation settings. Evaluation combines DOM-grounded reference matching, behavior-specific browser tests, and CLIP-based visual similarity, jointly measuring structural alignment, behavioral completeness, and overall visual fidelity. We use VISTA to assess four agent systems drawn from two model families and two harnesses, finding that visual fidelity and functional correctness are partially decoupled across both input conditions and agents, and that agent editing style varies sharply but is largely orthogonal to task quality. VISTA establishes a rigorous and reproducible foundation for advancing agent-based software engineering research.

05.
arXiv (quant-ph) 2026-06-12

Observation of Non-Gaussian Magnon Dynamics in a Two-Dimensional Long-Range XY Model

arXiv:2606.13499v1 Announce Type: new Abstract: Non-Gaussian evolution of high-order spin correlations characterizes important properties of quantum many-body systems. In practice, decoherence, statistical fluctuation and miscalibration of experimental parameters all hinder the witness of non-Gaussian dynamics. Here we demonstrate the crossover between Gaussian and non-Gaussian dynamics on a two-dimensional XY model with long-range and spatially structured interaction using a trapped ion quantum simulator. We prepare different initial densities of magnon excitations and verify the dynamics of single-spin observables for the engineered Hamiltonian. Then we compare the high-order spin correlations with the mean-field solution and the Holstein-Primakoff approximation, and demonstrate the non-Gaussian behavior in a way independent of the calibration errors. Our work provides a verifiable path from classically simulatable dynamics to regimes where quantum advantage may emerge.

06.
arXiv (CS.CL) 2026-06-11

WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning

Forecasting real-world events requires language-model agents to reason under uncertainty from incomplete, time-bounded information. Yet evaluating whether agents genuinely forecast requires more than final-answer accuracy: a model may be correct by recalling memorized training facts, citing fabricated evidence, or producing an unsupported causal story. We present WorldReasoner, an evaluation framework for temporally valid event forecasting. Each task gives an agent a resolved forecasting question, a simulated forecast date, and access only to evidence available before that date; after resolution, the framework scores the submitted probability, cited evidence, and optional causal event graph. WorldReasoner reports three complementary axes: outcome quality against resolved answers, evidence quality over cited sources, and reasoning quality against post-resolution hindsight graphs. The benchmark is built by an agentic construction pipeline that generates forecasting questions, collects time-stamped evidence, and builds hindsight reference graphs at scale, yielding 345 resolved tasks derived from 14,141 articles with graphs covering 8,087 extracted events. Across six controlled agent settings, temporally valid retrieval is the strongest driver of outcome accuracy; causal graph construction improves key-event recovery; and correct graph-enabled forecasts are more strongly grounded in key events and relevant sources, yet agents still struggle to convert grounded evidence into calibrated probabilities.

07.
arXiv (CS.CV) 2026-06-15

Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process

This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based framework built upon SD-Turbo to enhance underwater 4-D LF imaging by leveraging its spatial-angular structure. GeoDiff-LF consists of three key adaptations: (1) a modified U-Net architecture with convolutional and attention adapters to model geometric cues, (2) a geometry-guided loss function using tensor decomposition and progressive weighting to regularize global structure, and (3) an optimized sampling strategy with noise prediction to improve efficiency. By integrating diffusion priors and LF geometry, GeoDiff-LF effectively mitigates color distortion in underwater scenes. Extensive experiments demonstrate that our framework outperforms existing methods across both visual fidelity and quantitative performance, advancing the state-of-the-art in enhancing underwater imaging. The code will be publicly available at https://github.com/linlos1234/GeoDiff-LF.

08.
arXiv (CS.CV) 2026-06-19

How Fragile Are Training-Free AI-Generated Image Detectors? A Controlled Audit of Score Direction, Preprocessing, and Compression

Training-free detectors of AI-generated images promise generator-agnostic deployment without classifier training, yet their reported numbers are rarely compared under a single controlled protocol. We audit two representative training-free scores – an autoencoder-reconstruction score (AEROBLADE-style) and a noise-perturbation feature-similarity score (RIGID-style) – plus a naive feature-kNN control, on a common 1,500-image GenImage-derived benchmark spanning seven generators and JPEG compression at quality 70 and 50. The audit yields three cautionary findings. (i) Implementation details masquerade as method differences: replacing the LPIPS backbone (AlexNet -> VGG-16) changes overall AUROC by +0.085, and switching between resize-to-512 and native-resolution preprocessing flips per-generator conclusions by up to 0.38 AUROC. (ii) Score direction is not a property of the method but of its hyperparameters: the RIGID-style score is inverted (AUROC < 0.5) on SD1.5 and Wukong at noise level sigma=0.05, recovers to >0.5 for every generator at sigma=0.01, and collapses to 0.15 at sigma=0.3. (iii) Dataset format bias inflates robustness claims: without unified re-encoding, AUROC under JPEG-50 exceeds the clean condition for the AlexNet-backbone reconstruction score; after bias correction the residual anomaly localizes to a single generator (BigGAN). The audited scores have complementary per-generator failure sets, but naive z-score fusion does not beat the best single score, indicating that exploiting complementarity requires direction-aware combination.

09.
arXiv (CS.LG) 2026-06-19

UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

arXiv:2606.04101v3 Announce Type: replace-cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes. Existing balancers redistribute experts periodically based on historical load, which becomes unreliable for production deployments with non-stationary load patterns. We present UltraEP, the first exact-load, real-time balancer for large-EP MoE training and serving prefill on rack-scale nodes (RSNs). Leveraging the extended scale-up connectivity among dozens of GPUs within RSNs, UltraEP rebalances every microbatch and layer on critical paths, which requires nontrivial co-design of plan solving and expert replication communication to minimize exposed overhead. To this end, UltraEP eagerly reacts to post-gating load with an efficient quota-driven planner, and executes the resulting irregular expert-state transfers with RSN-native persistent tile streaming and relay-based fan-out mitigation. We evaluate UltraEP in a multi-RSN deployment of up to 256 GPUs, using cutting-edge MoE models from 106B to 671B parameters. Averaged across training and serving, UltraEP achieves 94.3% of the force-balanced ideal throughput, delivering 1.49$\times$ improvement over no-balancing, while reducing the final inter-rank imbalance from 1.30$-$4.01 to 1.01$-$1.04.

10.
arXiv (CS.AI) 2026-06-17

Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation

arXiv:2509.15210v2 Announce Type: replace-cross Abstract: Realistic sound simulation plays a critical role in many applications. A key element in sound simulation is the room impulse response (RIR), which characterizes how sound propagates within a given space. Recent studies have applied neural implicit methods to learn RIR using context information collected from the environment, such as scene images. However, these approaches do not effectively leverage explicit geometric information from the environment. To further exploit neural implicit models with direct geometric features, we present MiNAF, which queries a rough room mesh at given locations and extracts distance distributions as an explicit representation of local context. Our approach demonstrates that incorporating explicit local geometric features can better guide the model in generating more accurate RIR predictions. Through comparisons with conventional and state-of-the-art methods, we show that MiNAF performs competitively across various evaluation metrics.

11.
arXiv (CS.AI) 2026-06-17

MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation

arXiv:2606.04513v2 Announce Type: replace Abstract: Lane-level maps are critical infrastructure for autonomous driving and lane-level navigation, yet constructing and maintaining standardized lane networks for hundreds of cities remains highly labor-intensive. Recent end-to-end vectorized mapping methods can predict lane geometry and topology directly from sensor data, but they typically treat mapping specifications and traffic regulations as implicit, dataset-dependent supervision. Moreover, in complex scenes (e.g., worn or missing markings and occlusions), correct lane configurations are often under-determined by visual evidence alone, making specification violations a major source of human post-editing. We propose MapAgent, an industrial-grade agentic architecture that augments a vectorization backbone for specification-compliant lane-map production. Rather than merely adding an agent loop to map prediction, MapAgent couples backbone perception with explicit specification verification, constraint-aware reasoning, and deterministic map editing under a bounded, verification-driven Judge-Planner-Worker loop. A vision-language Judge diagnoses errors by jointly inspecting visual evidence and draft vectors, while a tool-calling Planner generates minimal corrective edits with post-edit re-validation. To remain scalable for city-scale production, MapAgent is selectively triggered only on tiles with low backbone confidence, adding modest overhead while preserving throughput. Experiments on real-world datasets show consistent gains over strong production baselines, especially in complex and long-tail scenarios. Additionally, MapAgent has been integrated into Baidu Maps, supporting lane-level map generation for over 360 cities nationwide and elevating the overall production automation to over 95%, demonstrating MapAgent's practicality and effectiveness for large-scale lane-level map generation.

12.
medRxiv (Medicine) 2026-06-18

Comparative Evaluation of Pretrained Large Language Models for Suicide Risk Prediction from Clinical Notes in U.S. Veterans

Background: Suicide remains a significant and potentially preventable cause of death among United States veterans. Predictive models based on structured electronic health record (EHR) data, including the U.S. Department of Veterans Affairs' Recovery Engagement and Coordination for Health-Veterans Enhanced Treatment (REACH-VET) program, aim to identify individuals at elevated risk for enhanced monitoring and follow-up. Increasing evidence suggests that unstructured clinical narratives contain additional psychosocial information that may enhance risk prediction when analyzed using natural language processing (NLP). However, optimal approaches for representing clinical text remain uncertain. Recent advances in large language models (LLMs) enable contextual text representations that capture complex semantic relationships beyond traditional lexical methods. Methods: We compared the predictive performance of pretrained LLMs with classical bag-of-words (BoW) representations for suicide risk prediction using clinical notes from 27,241 veterans receiving care in the Veterans Health Administration. Patients were stratified by REACH-VET risk tier (low, moderate, high), and models were evaluated across prediction windows defined by note look-back periods (

13.
medRxiv (Medicine) 2026-06-17

Low-Density Lipoprotein Cholesterol and Dementia Risk: Integrating Mendelian Randomization and Target Trial Emulation Within the Heart-Brain Axis

Background: The heart-brain axis links cardiovascular and neurodegenerative disease through shared vascular and inflammatory mechanisms. Although low-density lipoprotein cholesterol (LDL-C) is an established causal factor in atherosclerotic cardiovascular disease (ASCVD), its relationship with dementia remains uncertain, with midlife elevations associated with increased risk but late-life associations often appearing null or inverse. To address this cholesterol paradox, we integrated mendelian randomization (MR) with an active-comparator new-user target trial emulation. Methods: We applied a triangulated causal inference framework integrating two-sample MR with observational target trial emulation. Genetic variants associated with LDL-C were used as instrumental variables to evaluate Alzheimer disease (AD), dementia with Lewy bodies (DLB), frontotemporal dementia (FTD), and any dementia (AnyDem), with causal estimates derived using inverse-variance weighted models and sensitivity analyses for heterogeneity and pleiotropy. In parallel, an active-comparator new-user design compared statin versus ezetimibe initiation among adults aged 60 years or older using propensity score (PS) overlap weighting and Cox proportional hazards models to evaluate cardiovascular and dementia outcomes. Results: Genetically predicted LDL-C was associated with increased risk of DLB (OR 1.65, 95% CI 1.30-2.10; p

14.
arXiv (CS.AI) 2026-06-12

HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness

arXiv:2606.12882v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents for long-horizon tasks, yet their performance is shaped not only by model capability and environment design, but also by the harness that mediates agent–environment interaction. Existing harnesses are largely manually engineered, making them difficult to scale as trajectories grow longer and interactions become more complex. In this work, we ask whether harness can be generated by a learnable plug-in module that can be trained in an end-to-end fashion. We introduce HarnessBridge, a lightweight learnable harness controller that parameterizes the agent–environment interface as a bidirectional projection. HarnessBridge learns two bidirectional projections: observation projection, which distills raw trajectories into compact, decision-relevant states, and action projection, which converts proposed actions into executable transitions or trajectory-grounded rejections. We train HarnessBridge on a harness supervision dataset via unified instruction tuning. On Terminal-Bench~2.0 and SWE-bench Verified, HarnessBridge matches or surpasses strong specialized harnesses while substantially reducing token usage and trajectory length, and generalizes from smaller generators to larger commercial models.

15.
arXiv (CS.AI) 2026-06-11

IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization

arXiv:2606.12086v1 Announce Type: new Abstract: Contextualized assessment offers high ecological validity for evaluating creativity but introduces a critical challenge: observed performance may be confounded with cognitive proficiency (domain knowledge) and agency (willingness to engage). Meanwhile, in the age of generative AI, creative problem solving increasingly occurs in tool-mediated and human–AI interactive environments, making fully static assessment less aligned with contemporary creative practice. To address these issues, this paper proposes IntElicit, a framework for eliciting and assessing contextualized creativity via dialogue policy optimization. IntElicit functions as a constrained adaptive AI Interviewer: it provides non-directive knowledge and agency scaffolds in multi-turn interaction to reduce non-creative confounders, while preserving participants' responsibility for generating the creative content being evaluated. Specifically, to tackle sparse rewards and potential reward hacking (e.g., answer dictation) in open-ended educational dialogue, IntElicit introduces a decomposed process reward mechanism. This mechanism aligns the policy with pedagogical elicitation, rewarding prompts that draw out participant reasoning rather than producing optimal answers on their behalf. Extensive experiments, including participant simulation and a human subject study (N=64), show that IntElicit improves elicited creative outcomes over expert-designed baselines. Together, the results suggest that interactive elicitation can reveal creative potential that static FPSP-style assessment may miss, providing a formative and diagnostic lens for contextualized creativity assessment in AI-mediated learning contexts.

16.
arXiv (CS.LG) 2026-06-11

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling

arXiv:2509.20241v2 Announce Type: replace Abstract: As AI inference scales to billions of queries, estimates of per-query energy use are increasingly important for capacity planning, efficiency interventions, and policy. Yet many public estimates assume non-production settings, leading to systematic overestimation. We introduce a bottom-up framework estimating inference energy from token throughput, node power, and overhead under large-scale deployment assumptions. For frontier-scale models (>200B parameters) on H100 nodes, we estimate a median energy of 0.31 Wh/query (IQR 0.16-0.60), indicating widely cited estimates are overstated by 4-20x. In test-time scaling scenarios 15x longer than typical queries, the median energy rises 13x to 3.91 Wh (IQR 2.15-7.05). Across models, serving systems, and hardware, we estimate 8-20x line-of-sight energy reductions. At datacenter scale, serving 1 billion queries/day requires 0.7 GWh; if 10% are long queries, demand rises to 1.7 GWh/day. With efficiency interventions, it falls to 0.8 GWh/day, mitigating the energy impact of test-time scaling.

17.
arXiv (CS.AI) 2026-06-19

Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe

arXiv:2606.20381v1 Announce Type: new Abstract: FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class systems and AMD MI350-series GPUs, remain centered on E2M1 data elements. In this study, we identify a fundamental limitation of that choice: non-uniform formats such as E2M1 inherently suffer from Shrinkage Bias, a systematic negative rounding error caused by the geometric asymmetry of their representable bins. We show that this bias accumulates multiplicatively across layers and is amplified by the Random Hadamard Transform (RHT), providing a unified explanation for the training instability observed in existing E2M1-based FP4 recipes. In contrast, uniform grids (E1M2/INT4) bypass this grid-geometry error and better convert the improved bucket utilization from RHT into higher quantization quality. Based on this finding, we propose UFP4, a uniform 4-bit training recipe that applies RHT to all three training GEMMs while restricting stochastic rounding to dY alone. On Dense 1.5B, MoE 7.9B, and MoE 124B long-run pretraining, UFP4 consistently achieves lower BF16-relative loss degradation than strong E2M1-based baselines, supported by scaling-law analysis and ablation studies. Our results suggest that future accelerators should support E1M2/INT4-style uniform 4-bit grids as first-class training primitives alongside E2M1.

18.
arXiv (CS.LG) 2026-06-19

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

arXiv:2606.20437v1 Announce Type: cross Abstract: Charged-particle tracking – reconstructing trajectories from sparse detector measurements – is a fundamental high-energy-physics inference problem and a canonical example of learning under extreme combinatorial ambiguity. At the High-Luminosity Large Hadron Collider (HL-LHC), tracking must remain accurate and efficient despite unprecedented collision densities. Graph neural networks perform strongly, but incur substantial costs from graph construction and processing, while transformer-based approaches rely on auxiliary stages that prevent end-to-end optimization. To address this, we present HEPTv2, an end-to-end point-transformer architecture that reconstructs tracks from detector hits in one trainable pipeline. HEPTv2 combines a locality-aware point encoder with a track decoder that predicts complete trajectories without graph-building, clustering, or filtering. The encoder uses locality-sensitive hashing in detector coordinate space to preserve tracking-relevant geometry while enabling efficient local attention. The decoder resolves ambiguities through sectorized decoding and direct hit-to-track prediction under joint encoder-decoder supervision, allowing the full pipeline to be optimized end-to-end. On TrackML, HEPTv2 achieves 98.6% double-majority tracking efficiency at a 0.8% fake rate, while requiring only $\sim$15~ms inference time and 0.4~GB peak memory per event on a NVIDIA A100 GPU. Latency and memory scale approximately linearly for events with up to $5\times10^5$ hits. HEPTv2 establishes a new state of the art in the accuracy-latency trade-off, improving efficiency by 4.5% over the strongest prior transformer and by 1.1–2.2% over optimized graph-based pipelines, while reducing latency by factors of 7 and 38–52, respectively. These results show end-to-end transformers can deliver the accuracy and efficiency required for real-time particle reconstruction at the HL-LHC.

19.
arXiv (CS.CL) 2026-06-16

Let LLMs Judge Each Other: Multi-Agent Peer-Reviewed Reasoning for Medical Question Answering

Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Method: We designed a multi-agent peer-reviewed reasoning method in which multiple LLM agents independently generate chain-of-thought reasoning with candidate answers, then act as peer reviewers to evaluate each other's reasoning for factual correctness and logical soundness. The highest-rated reasoning chain is selected to produce the final answer. Experiments were conducted with five state-of-the-art LLMs (Llama-3.1-8B, Qwen2.5-7B, Phi-4, DeepSeek-LLM-7B, GPT-oss-20B) on three benchmark datasets: HeadQA, MedQA-USMLE, and PubMedQA. Performance was compared against single-model chain-of-thought reasoning and chain-of-thought-based majority voting. Results: Peer-reviewed reasoning consistently outperformed both baselines. The best model combination achieved an average accuracy of 0.820 across datasets, exceeding the strongest single model (0.777) and majority voting ensembles (up to 0.789). The method also scaled effectively with more participating models, while peer assessments reliably distinguished high- from low-quality reasoning chains. Conclusion: The proposed multi-agent peer-reviewed reasoning method enables LLMs to act as both solvers and evaluators, yielding superior performance in MedQA. By emphasizing reasoning quality rather than answer agreement alone, this approach improves accuracy, interpretability, and robustness, offering a promising direction for trustworthy biomedical AI systems.

20.
arXiv (CS.CL) 2026-06-11

Improving Cross-Format Robustness in Language Models with Multi-Format Training

Large language models often remain sensitive to answer format: a question solved correctly in one form may fail in another semantically equivalent form. To study this gap, we define cross-format robustness as the extent to which a model answers the same underlying question consistently across formats. We then compare full-format training with FormatMix, which expands only a subset of training items into multiple equivalent formats using either random or targeted selection. Across GLM4 and Llama-3.1, multi-format supervision consistently improves both task performance and cross-format robustness, whereas Multiple-choice question (MCQ)-only supervision alone brings little benefit and can even reduce robustness. We further find that expanding only about 30% of the training set into multiple formats often recovers most of the gain from full-format training, and this effect appears across the model families and sizes we study. These results suggest that format diversity, rather than additional supervision alone, is the key driver of robustness. That lightweight multi-format augmentation is a practical way to make LLMs less sensitive to answer format without changing the base model.

21.
arXiv (CS.AI) 2026-06-12

Reasoning for Mobile User Experience with Multimodal LLMs: Task, Benchmark, and Approach

arXiv:2606.13192v1 Announce Type: new Abstract: User experience (UX) centered on usability, perceived consistency, and functional clarity is fundamental to real-world user interfaces (UI). The application of multimodal large language models (MLLMs) in the field of user interfaces is evolving rapidly, such as visual element grounding, graphical user interface (GUI) agents, and design-to-code generation. However, research efforts on evaluating UX based on UI screenshots are still immature. To address this, we propose UXBench, a novel multimodal benchmark consisting of 2,000 VQA data samples designed to assess MLLMs' ability to perform UI-based reasoning. UXBench includes 8 tasks based on real-world UI screenshots that require fine-grained diagnosis of UX issues across layout relationships, visual hierarchy, and content consistency. Our extensive evaluation of mainstream MLLMs shows that they remain fundamentally limited in their capacity for UI-based reasoning. The results underscore the need for further advancements in this area. To bridge this gap, we propose UI-UX, an MLLM based on Qwen3-VL-4B-Thinking foundation model and enhanced via reinforcement learning with two key innovations: a reward routing mechanism that dynamically balances perceptual understanding and logical reasoning during inference, and an asymmetric transition reward that suppresses redundant or insufficient reasoning steps. Experiments demonstrate that UI-UX achieves state-of-the-art (SOTA) performance on UXBench, attaining an accuracy of 0.7963 – surpassing Claude-4.5-Sonnet's 0.6550 – while exhibiting strong generalization across diverse UI tasks and maintaining low inference latency.

22.
arXiv (quant-ph) 2026-06-19

Discrimination of genuinely nonlocal sets without entanglement in multipartite systems

arXiv:2606.20380v1 Announce Type: new Abstract: Genuine nonlocality arises when a set of multipartite orthogonal states is locally indistinguishable under any bipartition of the subsystems. The entanglement-assisted discrimination of such genuinely nonlocal orthogonal product sets has attracted significant attention in quantum information. Based on the criterion of local irreducibility, genuine nonlocality is classified into Type I (reducible) and Type II (irreducible). We present entanglement-assisted discrimination schemes for both types of genuinely nonlocal sets that use minimal resources. For low-dimensional cases, Type I sets require only a single EPR pair, whereas Type II sets necessitate only one GHZ state. We extend these protocols to higher-dimensional systems: the discrimination of Type I sets requires only one maximally entangled state in a two-qutrit system, while that of Type II sets similarly demands a single maximally entangled state in a three-qutrit system. For $n$-partite ($n > 3$) systems, Type I sets continue to require only one maximally entangled state, whereas Type II sets necessitate just one additional EPR pair compared to their Type I counterparts. These results provide a robust framework for the efficient discrimination of genuinely nonlocal sets using minimal quantum resources.

23.
arXiv (CS.CL) 2026-06-16

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs offered by AI providers, which introduces a critical but underexplored supply chain threat: backdoor attacks. In this work, we first unveil that MLLM-powered GUI agents naturally expose multiple interaction-level triggers, such as historical steps, environment states, and task progress. Based on this observation, we introduce AgentGhost, an effective and stealthy framework for red-teaming backdoor attacks. Specifically, we first construct composite triggers by combining goal and interaction levels, allowing GUI agents to unintentionally activate backdoors while ensuring task utility. Then, we formulate backdoor injection as a Min-Max optimization problem that uses supervised contrastive learning to maximize the feature difference across sample classes at the representation space, improving flexibility of the backdoor. Meanwhile, it adopts supervised fine-tuning to minimize the discrepancy between backdoor and clean behavior generation, enhancing effectiveness and utility. Extensive evaluations of various agent models in two established mobile benchmarks show that AgentGhost is effective and generic, with attack accuracy that reaches 99.7\% on three attack objectives, and shows stealthiness with only 1\% utility degradation. Furthermore, we tailor a defense method against AgentGhost that reduces the attack accuracy to 22.1\%. Our code is available at \texttt{anonymous}.

24.
arXiv (CS.AI) 2026-06-17

Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers

arXiv:2602.07429v2 Announce Type: replace-cross Abstract: Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer analytical precision but are visually abstract, whereas discrete methods provide intuitive clarity at the expense of geometric precision. To bridge this gap, we introduce Brep2Shape, a novel self-supervised pre-training method designed to align abstract boundary representations with intuitive shape representations. Our method employs a geometry-aware task where the model learns to predict dense spatial points from parametric Bézier control points, enabling the network to better understand physical manifolds derived from abstract coefficients. To enhance this alignment, we propose a Dual Transformer backbone with parallel streams that independently encode surface and curve tokens to capture their distinct geometric properties. Moreover, the topology attention is integrated to model the interdependencies between surfaces and curves, thereby maintaining topological consistency. Experimental results demonstrate that Brep2Shape offers significant scalability, achieving state-of-the-art accuracy and faster convergence across various downstream tasks.Code is available at this repository: https://github.com/thuml/Brep2Shape.

25.
arXiv (CS.LG) 2026-06-15

FreshRetailNet-LT: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

arXiv:2505.16319v4 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobserved demand creates systemic policy biases. Existing datasets lack the temporal resolution and annotations needed to address this censoring effect. To fill this gap, we present FreshRetailNet-50K, the first large-scale benchmark for censored demand estimation. It comprises 50,000 store-product time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 863 perishable SKUs meticulously annotated for stockout events. The hourly stock status records unique to this dataset, combined with rich contextual covariates, including promotional discounts, precipitation, and temporal features, enable innovative research beyond existing solutions. We demonstrate one such use case of two-stage demand modeling: first, we reconstruct the latent demand during stockouts using precise hourly annotations. We then leverage the recovered demand to train robust demand forecasting models in the second stage. Experimental results show that this approach achieves a 2.73% improvement in prediction accuracy while reducing the systematic demand underestimation from 7.37% to near-zero bias. With unprecedented temporal granularity and comprehensive real-world information, FreshRetailNet-50K opens new research directions in demand imputation, perishable inventory optimization, and causal retail analytics. The unique annotation quality and scale of the dataset address long-standing limitations in retail AI, providing immediate solutions and a platform for future methodological innovation. The data (https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K) and code (https://github.com/Dingdong-Inc/frn-50k-baseline}) are openly released.