ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning
Paper • 2610.37666 • Published • 45
Fu-En Yang
FuEnYang
AI & ML interests
Computer Vision, Deep Learning, Vision-Language Models (VLMs), Vision-Language-Action Models (VLAs), Reasoning Models, Embodied AI
Recent Activity
authored a paper about 7 hours ago
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning authored a paper about 7 hours ago
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining authored a paper about 7 hours ago
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly UnderstandingOrganizations
authored 6
papers about 7 hours ago
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
Paper • 2609.33419 • Published • 19
ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding
Paper • 2609.07941 • Published • 18
Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction
Paper • 2609.04201 • Published • 50
PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration
Paper • 2608.21031 • Published • 4
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Paper • 2606.06361 • Published • 16
upvoted a paper about 12 hours ago
upvoted a paper 8 days ago
upvoted 7
papers 26 days ago
Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence
Paper • 2609.34563 • Published • 227
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 235
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 118
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Paper • 2609.40340 • Published • 112
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement
Paper • 2609.38721 • Published • 227
Omni-IO Skills: Harnessing Your Agent Omni-Native
Paper • 2609.31847 • Published • 486
In-Context Learning for Robots: Methods and Applications
Paper • 2609.36012 • Published • 347
upvoted a paper 27 days ago
upvoted a paper about 2 months ago
upvoted 3
papers 4 months ago
One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications
Paper • 2606.25621 • Published • 20
World Action Models: A Survey
Paper • 2606.20781 • Published • 59
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
Paper • 2606.22807 • Published • 49