When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Paper • 2602.08236 • Published • 9
Yao
Huaxiu
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning authored a paper 1 day ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning authored a paper 1 day ago
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement LearningOrganizations
authored 7
papers 1 day ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Paper • 2602.08234 • Published • 70
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
Paper • 2602.10090 • Published • 51
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Paper • 2602.22190 • Published • 15
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Paper • 2603.12180 • Published • 62
SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
Paper • 2602.22426 • Published
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 106
submitted a
paper to Daily Papers 1 day ago
authored 4
papers over 1 year ago
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
Paper • 2410.13085 • Published • 24
MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
Paper • 2410.10139 • Published • 51
MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?
Paper • 2407.04842 • Published • 55
RULE: Reliable Multimodal RAG for Factuality in Medical Vision Language Models
Paper • 2407.05131 • Published • 26