AI.info

Jun Wang

Explore Jun Wang on AI.info.

• DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
• A Benchmark for Deep Information Synthesis
• OSCAR: Optimization-Steered Agentic Planning for Composed Image Retrieval
• Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
• When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
• DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset
• Apollo: Unified Multi-Task Audio-Video Joint Generation
• Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
• Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
• GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation
• Switchable Token-Specific Codebook Quantization For Face Image Compression
• ColorAgent: Building A Robust, Personalized, and Interactive OS Agent
• A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
• GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians