arXiv subjects

Wei Chen

Publications and source records attributed to Wei Chen.

At least 91 records · Page 5Linked to original sources

arXiv2026

Weighted Estimation by Discrete-time Sparse Domination on Martingale Spaces

Lacey used sparse domination to study the sharp weighted norm estimate of the maximal function of predictable multipliers in discrete time filtration spaces. Domelevo, Petermichl, and Škreb developed the self similarity argument known as sparse domination in an abstract martingale setting with a continuous time parameter. In our investigation, we establish sparse domination for discrete-time martingale transforms, introducing the novel concept of conditional sparsity as a core property of our approach. The conditional sparsity framework enables derivation of sharp weighted estimates and a mixed-norm estimate $ A_p^αA_r^β$ that improves upon known sharp $ L^p $ bounds. Moreover, we develop dedicated sparse domination specifically for Doob's maximal operator, recovering the sharp bound as a direct application. Finally, we focus on the application of sparse theory to quantitative two-weight estimates.

math.ST↗

arXiv2026

MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis

The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest. However, existing benchmarks largely focus on textual reasoning or isolated visual question-answering (VQA) tasks, lacking holistic integration of clinical narratives and medical imaging, and thus failing to assess the multimodal diagnostic synthesis capability central to expert clinical judgment. To bridge this gap, we introduce MedReaMM, a benchmark specifically designed to evaluate models' ability to synthesize heterogeneous clinical evidence consisting of detailed patient histories alongside multiple medical images into accurate differential diagnoses under a complete-information paradigm. Constructed from case reports sourced from top-tier medical journals and curated clinical case databases, MedReaMM comprises 625 expert-validated cases with an average of 2.79 medical images per case and a total of 1,042 standardized diagnoses annotated with ICD-11 codes. These cases predominantly represent rare, atypical, or multi-system presentations that demand expert-level evidence integration beyond routine pattern recognition. We evaluate 23 Large Multimodal Models (LMMs) and find that most achieve diagnostic accuracy scores below 50%, underscoring a substantial gap in multimodal diagnostic synthesis capability. Further analysis reveals that medical knowledge proficiency, medical image understanding, and evidence integration are all highly correlated with diagnostic performance.

cs.CV↗

arXiv2026

SAFE-G: Structure-aware Faithful Evidence-guided Generation for Knowledge-based Visual Question Answering

Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visual content. Typically, current methods fuse multimodal features to retrieve external information, subsequently leveraging Multimodal Large Language Models (MLLMs) to derive answers from the retrieved evidence. However, these methods often struggle to capture structural associations within complex contexts to effectively filter noise. Furthermore, they frequently fail to ensure that the reasoning process remains strictly faithful to the retrieved evidence. To address these challenges, we propose SAFE-G, a Structure-Aware Faithful Evidence-guided Generation framework, which enables precise evidence localization and trustworthy reasoning. Specifically, we first employ a coarse-grained hybrid search fusing visual and textual modalities to recall candidate documents, and subsequently implement a structure-aware fine-grained graph retrieval that captures structural dependencies to filter noise and pinpoint precise evidence. Moreover, we introduce a reinforcement learning (RL) strategy with an evidence-grounded reward that assigns credit to correct answers only when the selected evidence is correct. This strict alignment constraint compels the model to anchor its response in the retrieved context, effectively enhancing its capability to locate evidence via multimodal features and perform faithful reasoning. Extensive experiments on the Encyclopedic-VQA and InfoSeek benchmarks demonstrate that SAFE-G outperforms prior methods by a margin of 8.9% and 3.5%, substantially enhancing the overall reasoning accuracy. Our source code is publicly available at: https://github.com/MINE-USTC/SAFE-G.

cs.CV↗

arXiv2026

ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS

Large language models have transformed code generation, enabling unprecedented automation in software development. As mobile ecosystems evolve, HarmonyOS has emerged as a critical platform requiring robust development tools. Software development for the HarmonyOS ecosystem relies heavily on ArkTS, a statically typed extension of TypeScript. Despite its growing importance, the ecosystem lacks robust tools for automated code repair, primarily due to the absence of a high-quality benchmark for evaluation. To address this gap, we present ArkEval, a unified framework for ArkTS automated repair workflow evaluation and benchmark construction. It provides the first comprehensive benchmark specifically designed for ArkTS automated program repair. We constructed this benchmark by mining issues from a large-scale official Huawei repository containing over 400 independent ArkTS applications. Through a rigorous multi-stage filtering process, we curated 502 reproducible issues. To ensure testability, we employed a novel LLM-based test generation and voting mechanism involving Claude and other models. Furthermore, we standardized problem statements to facilitate fair evaluation. Finally, we evaluated four state-of-the-art Large Language Models (LLMs) on our benchmark using a retrieval-augmented repair workflow. Our results highlight the current capabilities and limitations of LLMs in repairing ArkTS code, paving the way for future research in this low-resource language domain.

cs.SE↗

arXiv2026

Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models scale poorly with document length, while visual retrieval-based pipelines are brittle and passive. We propose Doc-$V^*$, an \textbf{OCR-free agentic} framework that casts multi-page DocVQA as sequential evidence aggregation. Doc-$V^*$ begins with a thumbnail overview, then actively navigates via semantic retrieval and targeted page fetching, and aggregates evidence in a structured working memory for grounded reasoning. Trained by imitation learning from expert trajectories and further optimized with Group Relative Policy Optimization, Doc-$V^*$ balances answer accuracy with evidence-seeking efficiency. Across five benchmarks, Doc-$V^*$ outperforms open-source baselines and approaches proprietary models, improving out-of-domain performance by up to \textbf{47.9\%} over RAG baseline. Other results reveal effective evidence aggregation with selective attention, not increased input pages.

cs.CL↗

arXiv2026

PonyEval: Evaluating LLM-Based Program Repair for Capability-Safe and Actor-Oriented Pony Software

Repository-level issue-resolution benchmarks have made executable evaluation central to software-engineering agents, but their language coverage remains concentrated in mainstream ecosystems. Pony presents a different regime: it combines actors, reference capabilities, ahead-of-time compilation, and a rapidly evolving historical toolchain, making both patch generation and faithful replay difficult. We introduce PonyEval, a SWE-bench-style benchmark of 291 real GitHub issue-pull-request pairs from 15 Pony repositories. Every instance binds an issue statement, a historical base commit, a developer gold patch, a black-box test patch, and a reproducible runtime mapping. The frozen release passes an offline audit requiring the issue-specific test to fail on the base state and pass after the gold patch; it contains no duplicate instance identifiers or canonical repository-PR pairs. In a separate full-set semantic selection audit, three isolated machine reviewers label all 291 instances as include or exclude; their Fleiss' kappa is 0.8968, with 249 unanimous inclusions and 32 unanimous exclusions. To replay eleven years of repository history, we reconstruct 72 runtime images covering 289 unique base commits and verify their availability on five heterogeneous compute nodes. We define a matched evaluation with mini-SWE-agent 2.4.6 for GPT-5.6-sol, DeepSeek-V4-Pro, GLM-5.2, MiniMax-M3, and Kimi-K3, followed by strict patch application, compilation, and hidden-test validation. Across the patches actually produced by each model, conditional resolution rates range from 10.21% to 24.68%. These rates characterize the quality of generated patches rather than success over all 291 benchmark tasks.

cs.SE↗

arXiv2026

From Reasoning Strings to Partial Orders: Verifier-Certified Rule Transport through Quotient Policy Optimization

Many computations admit several valid execution orders because independent subgoals or disjoint state updates can commute. Reinforcement learning with verifiable rewards usually treats each successful trace as a separate token sequence, so serialization choices can be mistaken for logical dependencies. We introduce Verifier-Certified Rule Transport (VCRT), which replays adjacent operation pairs with native verifiers. Pairs whose two orders are accepted and reach the same canonical state provide commutation certificates; rejected or state-changing reversals provide anti-diamonds. VCRT uses anti-diamonds to preserve genuine prerequisites and assigns policy credit to the total probability mass of each certified orbit. It also constrains post-swap consistency, source retention, and policy drift. We evaluate leave-one-environment-out transfer across ProofWriter, CLRS, and Lean through a shared anonymized relation-graph interface. All training and checkpoint decisions are frozen before held-out evaluation, which uses one greedy trajectory per item without search or verifier feedback. VCRT obtains a 77.60% macro pass rate versus 64.53% for the strongest matched baseline, a paired gain of 13.06 points (95% bootstrap CI [12.58, 13.54]). Lean accounts for most of this gain at 33.49 points, while ProofWriter and CLRS improve by 2.85 points on average. Mechanism tests consistently favor anti-diamond supervision, whereas No-Orbit is statistically indistinguishable from full VCRT. The evidence does not establish a general benefit from exact orbit aggregation.

cs.LG↗

arXiv2026

AppEval: A Unified Benchmark for LLM-Based Mobile Application Repair in ArkTS, Swift, and Kotlin

Repository-level LLM agents are typically evaluated on projects whose tests run on the build host. It remains unclear whether their repairs survive the mobile build-install-launch-test boundary, where a missing SDK, offline device, or pre-assertion crash can be mistaken for a program failure. We present AppEval, a benchmark and native-toolchain evaluation framework for mobile application repair across HarmonyOS/ArkTS, iOS/Swift, and Android/Kotlin. Each task separates a hidden behavior test from the reference production fix and is accepted only when the same installed-app target reaches an assertion failure on the defective revision and passes after the fix; infrastructure failures remain a distinct outcome. A common schema maps this contract to each platform's build system, runtime, and test runner. The audited Android partition contains 200 accepted instrumentation tasks from 24 independently buildable repositories. On these tasks, five agents achieve Pass@1 between 22.00% and 90.50%, a 68.50-percentage-point spread under the same dynamic oracle. These results show that mobile repair performance depends strongly on the evaluated agent while demonstrating why runtime-aware acceptance is necessary for meaningful comparison. The quantitative findings in this paper are Android-specific; audited iOS and HarmonyOS results are required before drawing cross-platform generalization conclusions.

cs.SE↗

arXiv2026

OdinEval: A Reproducible Benchmark for LLM-Based Program Repair in the Odin Programming Language

Repository-level repair benchmarks still center on a few mainstream languages, leaving systems languages such as Odin largely untested. We present OdinEval, a reproducible benchmark built from documented defects in public Odin repositories. Each instance binds an issue to base and fix commits, a gold patch, an issue-specific regression test, a historical toolchain, and execution records. Admission requires the test to fail on the base revision and pass after the gold fix. When no usable developer test exists, a black-box test is reviewed independently by three instances of the same model, executed in both historical states, and revised from recorded feedback under a versioned Test Writing Skill. We evaluate six language models on 168 filtered instances under one shared protocol. Kimi-K3 records the highest Resolved score at 66.7%, while Qwen3.8-Max has the highest Repro score at 96.4%. The release includes frozen data, source archives, containers, validators, model patches, and audit manifests.

cs.SE↗

arXiv2026

Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction

Automatic sleep staging from polysomnography (PSG) is a well-studied task, but PSG itself is expensive, clinic-based, and burdensome to manually score, which limits its use for long-term or at-home monitoring. Most existing sleep-staging foundation models are evaluated using the full PSG montage. We instead ask how much of that montage is actually necessary. We evaluate six sleep staging models on the Multi-Ethnic Study of Atherosclerosis (MESA) PSG dataset across three signal conditions: electroencephalography (EEG), electrocardiography (ECG), and their combination (EEG+ECG). This is motivated by edge-cloud deployment, where EEG requires a clinic-grade scalp electrode, whereas ECG is already captured by consumer wearables. We test state-of-the-art foundation models such as SleepFM with an encoder trained from scratch on MESA, alongside BIOT, MOMENT, LaBraM, a base-scale Vision Transformer (ViT-B) reimplementation of SensorLM trained from scratch, and YASA, spanning EEG-pretrained, general-time-series, from-scratch, and classical non-learned approaches. No model architecture is modified from its original form; SensorLM's encoder is reimplemented only in PyTorch. For EEG-only staging, BIOT achieves the best result with a macro~F1 of 0.7237, followed by LaBraM (0.6835) and SleepFM from scratch (0.6582). Across the five models capable of ECG-only staging, switching from EEG to ECG costs between 0.2798 (MOMENT) and 0.4151 (BIOT) macro~F1, averaging 0.3531, while cutting the raw channel data rate to a third. Adding ECG to EEG provides no gain for most models. These results show that EEG carries most of the sleep-staging signal, quantify the consistent accuracy cost of the wearable-compatible alternative, and demonstrate that sleep-relevant pretraining transfers well to MESA.

eess.SP↗

arXiv2026

The $θ$-Symmetric SRG with Applications to Stability of Cactus Dynamic Networks

In this paper, we systematically study a variant of the scaled relative graph (SRG), referred to as the $θ$-symmetric SRG, and apply it to the stability analysis of cactus networks. Compared with the previous SRG definition, the $θ$-symmetric SRG enables the characterization of phase lead and lag behaviors, and serves as a more natural multivariable extension of the classical Nyquist plot. We first analyze the gain and phase aspects of $θ$-symmetric SRG separately and build a connection between $θ$-segmental phase and a norm minimization problem. This connection makes it possible to compute $θ$-segmental phase via semidefinite programming. We further derive the submultiplicative and subadditive properties of $θ$-symmetric SRG. These algebraic properties are crucial to determine the nonsingularity of product-type and sum-type return difference matrices, which topologically correspond to the cyclic and parallel-feedback extreme cases of cactus networks. By taking the cyclic interconnection as the fundamental starting point, we establish necessary and sufficient conditions for its robust stability. Integrating this with the parallel case, we synthesize a unified stability framework for general multi-loop cactus networks. The $θ$-symmetric SRG framework is less conservative and provides a more intuitive geometric interpretation of system behaviors compared with some existing approaches. Several examples are included to demonstrate the effectiveness of the proposed methods.

eess.SY↗

arXiv2026

Contextual Information Policy Optimization for Search Agents

Search agents extend large language models beyond static parametric memory by enabling them to acquire and use external evidence during multi-step reasoning. For knowledge-intensive tasks involving complex or evolving information, their reliability depends not only on retrieving relevant evidence but also on using it to guide subsequent reasoning. However, existing methods primarily reward final-answer correctness or intermediate progress, without directly assessing whether post-retrieval actions are grounded in the retrieved evidence. This misalignment encourages prior-driven reasoning: agents form conclusions based on internal knowledge and use retrieval mainly to confirm them, resulting in confirmation bias and inefficient evidence use. To address this issue, we propose Contextual Information Policy Optimization (CIPO), an evidence-oriented reinforcement learning framework that explicitly aligns policy optimization with external evidence use. CIPO assigns dense, turn-level credit to reasoning actions influenced by retrieved information, while combining this evidence-use signal with a global outcome reward to preserve answer correctness. With this manner, CIPO discourages evidence-detached guesses and promotes reasoning trajectories in which retrieved facts can guide or revise subsequent reasoning. Importantly, CIPO requires neither human process annotations nor an additional reward model. Extensive experiments on seven in-domain and out-of-domain benchmarks show that CIPO reduces the prevalence of prior-driven reasoning and achieves excellent performance on most tasks.

cs.AI↗

arXiv2026

FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation

Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery. We introduce FinReportBench, an expert-grounded benchmark for measuring and improving institution-grade financial report generation. Expert review reveals recurring gaps in report identity, institutional components, source discipline, and visual delivery. We derive a 35-item rubric through expert partial orders, multimodal evidence, and audits of decision boundaries, covering deliverability, report identity, and institutional completeness. Starting from 10,000 balanced Chinese and English financial-research source records, we curate 244 bilingual tasks across three research objects and two input tiers. Each task separates the public query, reconstructed research trajectory, and hidden source packet. Three independent judge families reproduce the expert partial order at near-ceiling rates, showing that bounded, observable criteria support reliable evaluation. Across nine model families, basic deliverability is nearly saturated, while report identity and institutional completeness remain the primary bottlenecks. The largest cross-model gaps concern generation-trace control, information density, and data discipline rather than basic report framing. We then use benchmark-guided skill distillation to turn recurrent failures into reusable generation and self-review constraints. Across five model families, the evolved skill improves mean G1 by 33.85 points and mean G2 by 13.83 points over paired no-skill runs while preserving G0 for every pair. Code and benchmark artifacts are available at https://github.com/MisterBrookT/finreportbench.

cs.CL↗

arXiv2026

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

GUI agents must remember both useful experience from earlier tasks and unfinished progress in the current interaction. Latent memory offers a compact solution by compressing multimodal trajectories into a few continuous tokens. Existing methods, however, usually map each trajectory to one fixed memory block and train it mainly through next-action supervision. This creates three practical problems: important details may be lost during compression, the same memory block must serve different decision stages, and irrelevant retrieved trajectories may still mislead the agent. We introduce FocusMem, which separates these responsibilities within a compact latent-memory interface. A role-aware content basis encourages episodic memory to retain reusable experience and working memory to retain task progress. A state-conditioned readout generates a decision-specific view of the same stored evidence, while a lightweight trust gate can suppress memory blocks that appear irrelevant to the current step. All components are trained while the GUI policy remains frozen. Across five GUI-agent benchmarks, FocusMem consistently outperforms a fully matched action-only fixed-memory baseline and prior latent memory adaptations. Further analysis shows that semantic and functional supervision preserve complementary information, state-conditioned readout is more robust as surrounding trajectory context grows, and the trust gate reduces the harm caused by injected irrelevant episodic evidence. These results show that effective latent memory depends not only on compressing past interaction, but also on what is retained, what is exposed, and what is allowed.

cs.CV↗

arXiv2026

ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional Human-AI Augmentation

High-quality annotation of artworks is essential for computational art research, yet extracting implicit semantics remains challenging due to the reliance on culturally grounded meanings and deep contextual knowledge behind the images. Current AI-assisted annotation tools often lack assistance or rely on one-way workflows where experts have to perform extra manual calibrations to improve AI models, resulting in limited efficiency. To address this, we propose Bidirectional Human-AI Augmentation(BiHAA), a closed-loop framework in which skills and domain knowledge base evolve through real-time interaction and bidirectional HAI augmentation. Informed by a formative study with 20 artwork annotators from different backgrounds, we implement this framework in ArtAnno, an artwork annotation system driven by a multi-agent architecture. The system includes a Proactive Agentic Support Module, where AI augments humans through semantic mining and label suggestion, and an Interaction-Driven Evolution Module, where human expertise continuously enhances the AI through distilling annotation trajectories into reusable experience. Evaluation through a user study and two case studies demonstrates that our framework and system improve annotation efficiency, enable knowledge accumulation, and reduce the effort of information seeking and verification for annotators with limited domain expertise. We conclude by discussing broader implications and future directions.

cs.HC↗

arXiv2026

MeloCodec: Harnessing Melodic Priors for High-Fidelity Singing Voice Representation

Neural audio codecs serve as fundamental tokenizers for LLM-based audio generation. While semantic priors are widely exploited to enhance linguistic intelligibility, the integration of explicit acoustic priors remains underexplored, limiting synthesis fidelity in frequency-sensitive domains. To address this gap, we introduce MeloCodec, a novel framework designed to effectively incorporate melodic priors, a critical form of acoustic information for singing. To address the optimization instability typically caused by the direct fusion of such explicit priors, we propose a Tokenize-then-Fuse paradigm that pre-trains a discrete melodic branch to lock in structures before feature fusion. To robustly realize this paradigm, we further propose a two-stage training strategy that prevents codebook collapse and ensures stable convergence. Experiments show that MeloCodec outperforms baselines in singing voice representation, improving pitch consistency and enabling controllable pitch manipulation with minimal timbre degradation.

cs.SD↗

arXiv2026

Topological properties and phase diagram of the triangular Hofstadter model with staggered flux

We study the topological properties and phase diagram of the triangular Hofstadter model with staggered flux in adjacent triangles in this work. This lattice can be used to describe the low energy physics of the twisted bilayer transition metal dichalcogenides (TMD) in a certain range of the electric displacement field between the two layers. We show that the Hofstadter spectrum of this model is generally asymmetric except at specific staggered flux $3ϕ= π/2 \mod π$ due to an additional P symmetry at such $ϕ$. Breaking the translation symmetry by dimerization lifts the P symmetry and results in rich topological phases in the system. The dimerized model with different rational external magnetic flux $Φ_B = 2πp/q$ has phase diagram with the following common features. For even q, the dimerized model generally has three gapped regimes. The one with small dimerization has finite Chern number and the other two have zero Chern number. For odd q, the model is gapped with zero Chern number at any finite dimerization. For both q even and odd, the two regimes with zero Chern number can be further characterized by the inversion symmetry of the parametrized one-dimensional chains of the system at ϕ= 0 \mod π/3$, and one regime is topologically non-trivial and the other is trivial. Our results may be tested in twisted bilayer TMD with weak interaction or cold atom systems in optical lattice or photonic crystals achieved in recent experiments.

cond-mat.other↗

arXiv2026

LiveEvalBench: Toward Open-World Evaluation for Web Generation

Large language models are increasingly capable of synthesizing executable frontend projects, yet existing benchmarks still treat web generation as a static evaluation problem. We argue that frontend artifacts demand a different paradigm: they are interactive rather than static, admit diverse yet equally valid implementations, and evolve faster than rigid pipelines can accommodate. To address these gaps, we present LiveEvalBench, an automated framework that reformulates web-generation evaluation as an agentic, adaptive, and extensible process. LiveEvalBench instantiates evaluation as a collaborative review workflow, in which a Build Engineer, a Code Engineer, and a UI Tester collectively gather evidence across the full lifecycle of a frontend project, from deployment and code inspection to browser-based interaction. To handle implementation diversity, an adaptive protocol couples shared rubrics for cross-model comparability with implementation-grounded criteria tailored to each artifact. The framework further supports incremental integration of new evaluator roles and assessment dimensions without pipeline redesign. Experiments across diverse real-world web-generation scenarios show that LiveEvalBench aligns closely with human expert judgment and provides fine-grained insights into frontier models' web generation capabilities. Code is available at https://github.com/wyysteelhead/LiveEvalBench

cs.AI↗