Searcharxiv⌕ Search

arXiv subjects

Le Zhang

Publications and source records attributed to Le Zhang.

At least 19 recordsLinked to original sources
arXiv2026

SurgSkill-Bench: A Benchmark for Multimodal Surgical Skill Assessment

Objective assessment of surgical technical skill is important for surgical training and structured feedback, but current workflows remain dependent on labor-intensive expert review. Existing automated approaches primarily focus on visual inputs and provide limited support for jointly studying operative performance, structured skill scores, and evaluator feedback. We introduce SurgSkill-Bench, an initial video-score-text benchmark-style dataset containing 214 surgical training simulation videos, six-dimensional OSATS scores, and expert free-text comments. We define two evaluation settings: video-only OSATS prediction for automated assessment and post hoc expert-comment-assisted prediction, where evaluator comments are available as auxiliary information. We provide controlled baseline experiments using representative frozen visual backbones, content-adaptive key-frame sampling, and a simple video-text co-attention fusion module. Under internal video-level validation, content-adaptive sampling improves video-only performance in this dataset, while evaluator comments provide additional score-related signal in the assisted setting. The best mean AUROC reaches 0.88 under dataset-specific median dichotomization. We further discuss evaluation constraints related to dataset scale, metadata completeness, and the interpretation of comment-assisted prediction. Code will be released publicly at a later date.

cs.CV↗
arXiv2026

Beyond Success and Failure: Length-Aware Contrastive Learning for GUI Agents

Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) have shown strong potential for automating tasks across diverse digital environments, where reinforcement learning (RL) has become a dominant training paradigm. However, widely used methods such as Group Relative Policy Optimization (GRPO) suffer from reward-gradient misalignment, leading to inefficient and unstable optimization. Recent work addresses this issue by reformulating RL with verifiable rewards (RLVR) as contrastive or classification-based objectives, which improve stability by eliminating problematic gradient behaviors. Despite this progress, existing contrastive RLVR methods rely primarily on outcome-level supervision and fail to capture fine-grained differences in trajectory quality within the same outcome category. In this paper, we propose Length-Aware Contrastive Learning for GUI Agents (LACL-GUI), a contrastive RLVR framework that incorporates trajectory-level quality signals into policy optimization. LACL-GUI introduces structured preferences within both successful and failed trajectories, encouraging concise successful executions and differentiating failure quality based on divergence from successful trajectories, while preserving optimization stability. Experiments on GUI agent benchmarks show that LACL-GUI provides more effective learning signals and consistently improves agent performance over prior methods, highlighting the value of trajectory-level supervision in contrastive RLVR.

cs.AI↗
arXiv2026

Photon bremsstrahlung from heavy quarks in a dense nuclear matter

We study the bremsstrahlung photon production from a hard jet parton induced by rescattering with a dense nuclear medium. Using the charged current interaction channel of deep inelastic scattering between an electron and a large nucleus, we derive the spectrum of medium-induced photons emitted from high-energy heavy and light quarks at the next-to-leading twist in a unified framework. Going beyond the collinear expansion approximation, we show that the photon spectrum is determined by the full momentum distribution of the gluon exchanged between the propagating quark and the medium, or equivalently, by the differential elastic scattering rate of the hard quark inside the medium. Modeling the gluon field with a static Debye screened potential reduces the photon spectrum to a dependence on the transverse momentum distribution of the exchanged gluon. This work provides a more reliable input for future phenomenological studies of quark mass effects on jet-induced photon production in relativistic heavy-ion collisions.

hep-ph↗
arXiv2026

LLM-Based Hierarchical Coordinated Control with Continuation-Aware Policy Learning

Coordinating multiple interacting units in complex engineering systems is challenging when system interactions are difficult to model, operational information is heterogeneous, and low-level actions must satisfy strict constraints. We propose an LLM-based hierarchical framework in which the LLM coordinates interacting units based on heterogeneous operational context, while task-specific controllers or optimizers generate executable and constraint-aware actions. We further introduce Continuation-Aware GRPO to capture the consequences of coordination decisions over subsequent control intervals. Rather than judging a decision only by its immediate outcome, the method also evaluates how the system evolves afterward under the current policy. We validate the framework on multi-ramp traffic control and virtual power plant (VPP) energy management, using simplified system models for training and more realistic simulators for evaluation. Across both tasks, the proposed method consistently outperforms direct task-specific control and optimization, end-to-end reinforcement learning, rule-based and RL-based hierarchical coordination, and prompting-only LLM coordinators, demonstrating the value of heterogeneous-context reasoning, hierarchical execution, and continuation-aware policy learning.

cs.AI↗
arXiv2026

Improved Cosmological Constraints from Morphology-Based Marked Correlation Functions

The cosmic web contains morphology-dependent information that is not fully captured by standard two-point statistics. We construct morphology-based marked correlation functions (MCFs) by assigning marks to halos according to the cosmic-web morphology identified with the \textsc{Nexus} algorithm. Using the \textsc{Kun} simulation suite, which spans 129 $w_0w_a$CDM cosmologies, we build Gaussian-process emulators for the MCFs as functions of cosmological parameters and tracer bias. We then apply the emulators to mock halo catalogues from the independent \textsc{Jiutian} simulation and perform a joint likelihood analysis to quantify the resulting cosmological constraints. We consider two marker choices: a discrete morphology marker and a continuous morphology strength marker. The continuous marker improves the Figure of Merit (FoM) by a factor of $\sim 8.6$ relative to the standard 2PCF and reduces the $1\sigma$ uncertainty on $\sigma_8$ by a factor of $\sim 5$. The discrete marker gives a more modest FoM improvement of $\sim 17\%$. We further test the impact of tracer selection by varying the halo mass threshold by a factor of $\sim 4.5$. Even for the lowest mass threshold, the continuous marker remains unbiased and achieves a FoM about $\sim 3.4$ times higher than that of the 2PCF alone. These results show that morphology-based MCFs, combined with simulation-based emulation, provide a useful framework for extracting additional cosmological information from large-scale structure surveys.

astro-ph.CO↗
arXiv2026

Reliability analysis for BraTS-GoAT segmentation: a controlled robustness study of deep-ensemble uncertainty

Deep networks segment brain tumours accurately in-distribution, but can fail silently when the input differs from their training data. That risk is central to clinical deployment and is the premise of the BraTS-GoAT generalizability task. We ask not only how well a model segments, but whether its uncertainty knows when it is wrong. On BraTS-GoAT (Task 3) we train a 5-fold cross-validated nnU-Net baseline (one held-out prediction per case) and a 3-seed deep ensemble. Both are evaluated for calibration and error detection on a per-region relevant mask, aggregated per case. In-distribution the 3-seed ensemble improves modestly over the already strong single model on the same held-out split, with the clearest gain in calibration. The separation appears under shift. In a controlled robustness study using graded synthetic corruptions as a proxy for acquisition shift, the single model's confidence stays flat while its accuracy and calibration degrade. Inter-member disagreement instead rises steeply, about a quarter to a third above the clean condition, several times the single model's response. On the official validation leaderboard the 5-fold ensemble of those folds attains whole-tumour Dice 0.87. The generalization gap is concentrated on the harder regions, with a characteristic failure of missing small, satellite lesions on unseen cohorts. In the synthetic study, disagreement among the 3-seed members is a more sensitive case-level indicator of acquisition shift than single-model confidence. Its per-voxel error localisation weakens as severity grows. The contribution is a rigorous, honest reliability comparison rather than a claim that any one uncertainty method dominates.

cs.CV↗
arXiv2026

EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory

Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in existing systems: indices built from context-poor captions are unreliable for agentic search, while retrieval ignores a question's temporal intent. To address both bottlenecks, we introduce EgoCITE (Egocentric Context-augmented Indexing and Time-aware Evidence retrieval), a long-horizon agentic memory framework for egocentric QA. EgoCITE comprises three components. EgoScheme uses local multimodal context to turn fragmentary video captions and speech transcripts into self-contained atomic memory indices. EgoIndex organizes complementary action, activity, utterance, and conversation representations into searchable multi-view memory indices at multiple granularities. EgoRetrv combines semantic search with question-conditioned temporal relevance scoring and curation of retrieved evidence. We evaluate EgoCITE on EgoLifeQA, EgoMem, and EgoR1-Bench in terms of answer accuracy and target-event retrieval alignment. EgoCITE improves accuracy over agentic memory baselines by at least 4.4--14.2% while achieving 36$\times$ lower cost than long-context LLM agents.

cs.CV↗
arXiv2026

Decoding Phenotypes: A Framework for Fusing Genomic Language Models and Neuroimaging

Neuroimaging and genetic testing are two important clinical references for nervous system diseases, offering complementary diagnostic information. However, integrating genomic and neuroimaging data for precise disease diagnosis is challenging due to cross-modality heterogeneity. Existing imaging-genetics approaches mainly encode genetic information as hard-coded labels, which lose the local sequence context around disease-associated variants. To address this limitation, we propose GeneFuse, a multimodal learning framework that aligns genetic representations from pre-trained Genomic Language Models (GLMs) with features extracted from images. GeneFuse integrates two components: (1) Genotype-Conditioned Feature Modulation (GCFM), a FiLM-inspired module that uses genomic embeddings to modulate image feature maps; and (2) Uncertainty-aware Genomic Residual Fusion (U-GRF), a fusion strategy that uses imaging-derived predictive uncertainty to gate the contribution of genotypic features. We evaluate GeneFuse on early cognitive decline identification (NC vs. MCI) and dementia screening (NC vs. AD). In the APOE-centered setting, GeneFuse achieves AUROCs of 0.77 and 0.83, outperforming existing imaging-genetics fusion methods. These results indicate that GLM-derived genomic embeddings provide additional information to imaging.

cs.AI↗
arXiv2026

OASIS: Occlusion-aware Single-image Hand Avatar Reconstruction via 3D Gaussian Splatting

Single-image 3D hand avatar reconstruction is fundamentally ill-posed and particularly challenging due to limited visual evidence under severe self-occlusion and the complex pose-dependent deformation of highly articulated hands. Existing methods predominantly rely on implicit NeRF-style representations, whose volumetric fitting is computationally expensive and often struggles to preserve fine-grained hand details. In this work, we present OASIS, a tailored 3D Gaussian Splatting framework for single-image hand avatar reconstruction. To faithfully encode sparse image-specific appearance cues in single-view reconstruction, we construct geometry-aligned visual evidence tokens by explicitly aligning input image observations with 3D hand geometry and context-adaptively tokenizing the resulting visual evidence. Since severe self-occlusion makes the reliability of image evidence inherently visibility-dependent, we introduce a visibility-conditioned point-image attention to reliably transfer visual evidence to geometric tokens, yielding occlusion-aware Gaussian features for faithful and robust reconstruction. To further capture non-rigid deformation of articulated hands, we introduce a Feature-on-Mesh representation to enable Gaussian deformation to be guided by local surface stretching. Under this framework, we adopt a one-shot adaptation scheme that learns a shared hand prior from multi-identity training data and then fits it to a target image for target-specific reconstruction. Extensive experiments show that OASIS outperforms existing baselines in both visual fidelity and efficiency across challenging poses and in-the-wild scenarios, and further demonstrates strong versatility in downstream applications such as text-to-avatar generation and texture editing.

cs.CV↗
arXiv2026

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at a reasonable cost. We introduce OmegaUse-OfficeVal, a benchmark for evaluating LLM agents on long-horizon office-suite tasks with task-level economic grounding. The benchmark comprises 100 tasks derived from office-suite requests proposed by practitioners and adapted through a privacy-preserving process. On average, these tasks require 2.32 hours of human labor to complete. An important feature of the benchmark is that each task is paired with two economic signals: human labor time and task price proxy. These signals enable direct comparisons between human costs and LLM inference costs, as well as value-weighted evaluation. To support stable evaluation, we develop code-based verifiers from fine-grained rubrics. We evaluate several frontier LLMs together with a human baseline. Although all evaluated LLMs are substantially cheaper and faster than human workers, they have not yet approached human-level deliverable quality. The code and dataset are fully open-sourced, and more information is available on our project website: https://omegause-officeval.github.io.

cs.AI↗
arXiv2026

KuaiLive-M3: A Multi-Modal, Multi-Domain, and Multi-Feedback Dataset for Live Streaming Recommendation

Existing public live streaming datasets suffer from three major limitations: they provide limited access to temporally evolving multimodal live content, overlook users' cross-domain interactions between short videos and live streams, and contain only implicit behavioral signals without explicit feedback that captures users' perceived content quality and satisfaction. These limitations prevent existing benchmarks from faithfully reflecting real-world live streaming scenarios and hinder comprehensive research on live streaming recommendation. To address these limitations, we introduce KuaiLive-M3, a multi-modal, multi-domain, and multi-feedback dataset for live streaming recommendation, collected from Kuaishou, a leading live streaming and short video platform in China. KuaiLive-M3 covers 21,938 users and contains 35 million live streaming interactions and 111 million short video interactions, with fine-grained timestamps and diverse user behaviors. It further provides approximately 88 million timestamped segment-level multi-modal embeddings that capture the temporal evolution of live streaming content, as well as 25,403 questionnaire-based feedback records that bridge implicit user behaviors and explicit user preferences. Based on these unique signals, we establish benchmarks for cross-domain recommendation, live stream highlight prediction, and questionnaire-enhanced recommendation. Extensive experiments with representative baselines demonstrate that KuaiLive-M3 provides a challenging and realistic benchmark for future live streaming recommendation research. The results further highlight the importance of modeling temporally evolving content, transferring user preferences across domains, and bridging the gap between implicit behaviors and explicit user feedback. The dataset and benchmark code are publicly available at https://imgkkk574.github.io/KuaiLive-M3/.

cs.IR↗
arXiv2026

MedDiT4SR: Tri-Stream Joint Adaptation of Pre-Trained Diffusion Transformers for Medical Image Super-Resolution

Medical image super-resolution (MedSR) requires recovering fine anatomical structures from degraded observations while avoiding unsupported details introduced by generative priors. Large-scale pre-trained multimodal diffusion transformers provide strong visual priors, but their adaptation to MedSR remains non-trivial. In conventional ControlNet-style adaptation, the low-resolution (LR) image is processed as an external condition and injected into the denoising stream through one-way connections. Consequently, LR anatomical evidence cannot be jointly updated with the evolving denoising and semantic representations. We propose MedDiT4SR, a tri-stream adaptation framework that integrates the LR, noisy latent, and text representations into the same multimodal diffusion-transformer blocks. To complement global token interaction, we introduce a Super-Resolution Adapter (SR Adapter) that aggregates scale-dependent local tokens and suppresses interpolation-induced redundancy. We further propose a Semantic Alignment Refiner (SA Refiner) that calibrates local LR responses using prompt-conditioned semantic information. Experiments under both in-domain and within-modality cross-dataset settings demonstrate the effectiveness of adapting large-scale pre-trained DiT models to medical image super-resolution across diverse imaging domains.

eess.IV↗
arXiv2026

Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution

Continuous diffusion models have become the dominant paradigm for photo-realistic image Super-Resolution (SR), but they typically formulate reconstruction as continuous signal-level denoising and incorporate semantic priors through external conditioning modules. This makes it less direct to exploit the unified token-based scaling paradigm of modern multimodal models. Autoregressive models provide a more native semantic representation by modeling images as discrete visual tokens, yet their causal decoding is inefficient for high-resolution reconstruction. Discrete diffusion offers a promising middle ground by enabling non-causal, parallel prediction over visual tokens. However, directly adapting discrete diffusion to SR remains non-trivial due to two task-specific challenges: (1) the long-tailed distribution of visual tokens, which under-represents rare but perceptually critical textures; and (2) spatially inconsistent parallel decoding, which may introduce isolated artifacts. To address these issues, we propose DiMOO-SR, a rarity-aware multimodal discrete diffusion framework for photo-realistic image SR. During training, Inverse Frequency Sampling (IFS) prioritizes under-represented but information-rich tokens. During inference, Spatial Consistency Ranking (SCR) refines token confidence using local neighborhood agreement to improve structural coherence. Extensive experiments on widely used real-world SR benchmarks demonstrate that DiMOO-SR achieves competitive perceptual quality with only a few parallel decoding steps, highlighting the potential of discrete diffusion for generative image super-resolution. The code will be released upon publication.

cs.CV↗
arXiv2026

Foreground Characterization and Mitigation in the Observations of the CD/EoR with the SKA

The Square Kilometre Array (SKA), with its unprecedented sensitivity, frequency coverage, and large collecting area, is poised to revolutionize our understanding of the Cosmic Dawn (CD) and Epoch of Reionization (EoR) epochs marking the formation of the first luminous sources and the subsequent reionization of the intergalactic medium (IGM). However, detecting the faint redshifted 21-cm signal from neutral hydrogen remains one of the foremost challenges in observational cosmology, as it is buried beneath bright foregrounds from Galactic synchrotron radiation, free-free emission, and extragalactic point sources that are 4-5 orders of magnitude stronger than the cosmological signal. In this chapter, we highlight the key components and characteristics of these foregrounds and review ongoing efforts to model, characterize, and mitigate them. We emphasize how the SKA-Low AA* configuration, through its optimized array design, wide field of view, and improved calibration accuracy, enhances our capacity to suppress foreground contamination and recover the cosmological signal. The SKA Observatory Foreground Challenge plays a pivotal role in this effort by bringing together the global EoR/CD community to develop, compare, and validate foreground removal pipelines using realistic simulated datasets. Building on the experience of existing pathfinders such as LOFAR, MWA, and HERA, these collaborative initiatives are helping refine statistical and machine learning-based approaches for signal recovery. Together, these advancements are laying the groundwork for the SKA to probe the thermal and ionization history of the early Universe with unprecedented precision.

astro-ph.CO↗
arXiv2026

A Non-Negativity Iterative Approach to Image Deconvolution for SKA

We introduce a novel algorithm for image deconvolution applicable to interferometric radio observations, based on the assumption of non-negative source fluxes. The method enables rapid and efficient image reconstruction in an iterative manner, without requiring prior knowledge or training. Its computational cost scales linearly with the number of pixels: for example, a $512\times 512$ image can be processed in about 1-2 seconds on a standard laptop. We validate the algorithm using both point sources and an extended galaxy image, incorporating a realistic SKA-Low PSF with incomplete $uv$-coverage, though tests are conducted in noise-free simulations. Comparison with the CLEAN method demonstrates that our approach yields a good reconstruction, showing particular promise for the SKA and VLBI observations with sparse $uv$-coverage.

astro-ph.IM↗
arXiv2026

HiMatch-AD: DINOv3-driven Hierarchical Matching for Training-free Medical Anomaly Detection

Anomaly detection is essential for medical image analysis, where pathological regions often appear as rare deviations from normal anatomical structures. While training-based methods have achieved promising performance, they require task-specific optimization and extensive normal data, which limits scalability across modalities and institutions. Training-free approaches offer greater flexibility by leveraging pretrained visual representations, yet existing methods typically rely on simple nearest-neighbor retrieval and naive aggregation strategies, which may fail to capture hierarchical semantics and ignore the reliability of multiple anomaly responses. In this work, we propose HiMatch-AD, a DINOv3-driven hierarchical matching framework for training-free medical anomaly detection. Our method first retrieves semantically relevant normal references via dual-branch matching that jointly considers global CLS-token similarity and patch-level representations. Hierarchical anomaly maps are then generated across multiple transformer stages by comparing clustered normal features with query representations. To robustly aggregate anomaly responses, we introduce a unified uncertainty-based fusion mechanism that adaptively weights maps according to their reliability. The entire framework operates without any task-specific training. Extensive experiments on the BMAD benchmark, including brain MRI, liver CT, and retinal OCT datasets, demonstrate that HiMatch-AD consistently outperforms both training-based and DINO-based state-of-the-art methods, which highlights the effectiveness of multi-level matching and uncertainty-aware fusion for scalable medical anomaly detection.

cs.CV↗
arXiv2026

Unlocking LLM Code Correction with Iterative Feedback Loops

Large Language Models have shown remarkable capabilities in code generation. However, most existing evaluations focus only on single-attempt accuracy and overlook the iterative refinement process that is central to real-world programming. This study presents a systematic investigation of LLMs' ability to rectify their own code through execution feedback. Using real-world programming problems across four models and two major programming languages, this study evaluates performance using iterative refinement framework where LLMs receive compiler error messages and testcase feedback after each attempt. This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models, offering actionable insights into both the understanding and practical application of feedback loops in LLM-driven code generation systems. Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback, while syntactic and runtime errors are far more tractable than logical or algorithmic failures.

cs.SE↗
arXiv2026

Data-driven modeling of Galactic diffuse emission with multi-wavelength observations

We present a data-driven investigation of Galactic diffuse emission. Using multi-frequency Planck radio/microwave maps (30-857 GHz) and Fermi-LAT gamma-ray data (50 MeV-814 GeV), we construct a nonlinear mapping between radio emission and gamma-ray intensity through supervised machine learning. Our models achieve high predictive accuracy (R^2 > 0.90 in the 0.1-10 GeV range), demonstrating that multi-frequency radio observations encode sufficient information to reconstruct both spatial morphology and spectral properties of diffuse gamma-ray emission. By analyzing model performance across different frequency bands and spatial regions, we identify high-frequency radio bands as the dominant predictor, providing direct empirical support for the hadronic origin of Galactic 0.1-10 GeV gamma rays, while low-frequency radio bands for the leptonic origin above 10 GeV. Residual maps reveal coherent large-scale structures, including Loop I and III, highlighting regions where standard interstellar emission models are incomplete or biased. Compared with the GALPROP model, our machine learning approach yields a higher R^2=0.95 and lower mean absolute relative error (14.7%) in the inner Galactic disk and the Galactic center region. Our results illustrate that machine learning serves as a physically interpretable tool for multi-messenger astrophysics, providing a data-driven baseline for separating non-standard emission components and deriving new constraints on cosmic-ray propagation and interstellar medium structure.

astro-ph.HE↗