When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
Paper • 2602.08236 • Published • 9
AI & ML interests
Multimodality, RL, VLA, Reasoning
Recent Activity
View all activity
Huaxiu
authored 4
papers 4 days ago
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Paper • 2602.08234 • Published • 72
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 • 16
richardxp888
authored a
paper 4 days ago
Huaxiu
authored a
paper 4 days ago
richardxp888
authored a
paper 4 days ago
Huaxiu
authored 2
papers 4 days ago
Huaxiu
submitted a
paper to Daily Papers 4 days ago
richardxp888
authored 3
papers about 1 month ago
Reliable and Responsible Foundation Models: A Comprehensive Survey
Paper • 2602.08145 • Published • 8
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
Paper • 2602.08234 • Published • 72
MedVerse: Efficient and Reliable Medical Reasoning via DAG-Structured Parallel Execution
Paper • 2602.07529 • Published
ChilleD
submitted a
paper to Daily Papers about 1 month ago
richardxp888
submitted a
paper to Daily Papers about 1 month ago
FanNie1208
authored 2
papers about 2 months ago
richardxp888
authored a
paper 2 months ago
JiaaqiLiu
authored a
paper 2 months ago
JiaaqiLiu
submitted a
paper to Daily Papers 3 months ago