AI.info

Yu Wang

Explore Yu Wang on AI.info.

• Human-Aligned MLLM Judges for Fine-Grained Image Editing Evaluation: A Benchmark, Framework, and Analysis
• Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly Detection
• Reliable and Responsible Foundation Models: A Comprehensive Survey
• Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis
• ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins
• Agentic Reasoning for Large Language Models
• A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
• Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
• Towards Efficient LLM-aware Heterogeneous Graph Learning
• Neural Graph Navigation for Intelligent Subgraph Matching
• Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning
• Dual-branch Spatial-Temporal Self-supervised Representation for Enhanced Road Network Learning
• FedMGP: Personalized Federated Learning with Multi-Group Text-Visual Prompts
• Identifying the Periodicity of Information in Natural Language
• Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
• Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning
• Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
• DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction
• RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models