Yu Wang

13 papers Tsinghua University

• A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction
• AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
• Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
• FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
• Graphs Help Graphs: Multi-Agent Graph Socialized Learning
• PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models
• Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection
• R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
• ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
• Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
• VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
• What Can RL Bring to VLA Generalization? An Empirical Study