Wei Wang

Full Professor@University of California, Los Angeles·美国·OpenReview

研究方向

foundation model · AI for science · natural language processing · computational medicine · machine learning · social network · time series · bioinformatics · graph analytics · data mining

Wei Wang

Preference Leakage: A Contamination Problem in LLM-as-a-judge

Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

SE-Diff: Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation

GTD: Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models

MatSciBench: Benchmarking the Reasoning Ability of LLM in Materials Science

A Multimodal LLM Approach for Visual Question Answering on Multiparametric 3D Brain MRI

LinguaMate: Language‑Guided Metamaterial Discovery via Symbolic-Driven Latent Optimization

TIDAL: A Temporal Causal Diffusion Framework for Visualizing Knee Osteoarthritis Treatment Outcomes

DoMiNO: Down-scaling Molecular Dynamics with Neural Graph Ordinary Differential Equations

Do LLMs Really Understand Code? A Semantic Benchmark with Automated Question Generation and Evaluation

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

CoRGI: GNNs with Convolutional Residual Global Interaction for Lagrangian Simulation

Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning

Rethink GraphODE Generalization within Coupled Dynamical System

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

Mixture of In-Context Prompters for Tabular PFNs

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

GIVE: Structured Reasoning with Knowledge Graph Inspired Veracity Extrapolation

Flow Field Reconstruction with Sensor Placement Policy Learning

MIRAI: Evaluating LLM Agents for International Event Forecasting

LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts

Physics-Informed Self-Guided Diffusion Model for High-Fidelity Simulations

CliBench: A Multifaceted and Multigranular Evaluation of Large Language Models for Clinical Decision Making

Joint Modeling of Spatial and Temporal Multiscales in Molecular Dynamics

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection