Zican Hu

huzican's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 10 days ago

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

Paper • 2607.03748 • Published 15 days ago • 39

Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models

Paper • 2607.03751 • Published 15 days ago • 19

submitted 2 papers to Daily Papers 12 days ago

Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models

Paper • 2607.03751 • Published 15 days ago • 19

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

Paper • 2607.03748 • Published 15 days ago • 39

authored a paper 9 months ago

Diversity-Incentivized Exploration for Versatile Reasoning

Paper • 2509.26209 • Published Sep 30, 2025 • 18

authored 2 papers 12 months ago

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

Paper • 2505.19761 • Published May 26, 2025

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision

Paper • 2504.15046 • Published Apr 21, 2025

authored 3 papers about 1 year ago

Attention-Guided Contrastive Role Representations for Multi-Agent Reinforcement Learning

Paper • 2312.04819 • Published Dec 8, 2023

Mixture-of-Experts Meets In-Context Reinforcement Learning

Paper • 2506.05426 • Published Jun 5, 2025 • 5

Learning to Reason under Off-Policy Guidance

Paper • 2504.14945 • Published Apr 21, 2025 • 88