ZhengQi Wan

Vanqi's activity

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

upvoted 2 papers about 22 hours ago

Introspective Diffusion Language Models

Paper • 2604.11035 • Published 3 days ago • 19

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published 3 days ago • 91

upvoted 2 papers 3 days ago

Training a Student Expert via Semi-Supervised Foundation Model Distillation

Paper • 2604.03841 • Published 12 days ago • 10

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Paper • 2604.06628 • Published 8 days ago • 310

upvoted 2 papers 8 days ago

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Paper • 2604.04934 • Published 10 days ago • 42

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published 10 days ago • 200

updated a collection 8 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

updated a collection 9 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

upvoted 2 papers 9 days ago

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published 14 days ago • 52

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published 12 days ago • 34

updated a collection 9 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

updated a collection 14 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

updated a collection 17 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

upvoted a paper 17 days ago

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

Paper • 2603.25716 • Published 20 days ago • 154

updated a collection 24 days ago

From Vision to Motion

Collection

7 items • Updated 8 days ago

upvoted 2 papers 24 days ago

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 29 days ago • 109

WorldAgents: Can Foundation Image Models be Agents for 3D World Models?

Paper • 2603.19708 • Published 27 days ago • 13

upvoted a paper 27 days ago

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Paper • 2603.19235 • Published 27 days ago • 95

upvoted 2 papers about 1 month ago

Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders

Paper • 2603.06569 • Published Mar 6 • 118

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Paper • 2603.03269 • Published Mar 3 • 63