Wanli Ouyang
- Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
- Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
- CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding
- Flow-GRPO: Training Flow Matching Models via Online RL
- FuncGenFoil: Airfoil Generation and Editing Model in Function Space
- Improving Video Generation with Human Feedback
- LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
- MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search
- Native-Resolution Image Synthesis
- PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs
- Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization
- STAR: A Benchmark for Astronomical Star Fields Super-Resolution
- ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models
- SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning
- Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation
- Venus-MAXWELL: Efficient Learning of Protein-Mutation Stability Landscapes using Protein Language Models
- scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration