Liang Wang
- 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
- AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping
- BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
- Chain-of-Retrieval Augmented Generation
- DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
- EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation
- GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
- MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
- Path-Enhanced Contrastive Learning for Recommendation
- Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing