ZhengQi Wan

Vanqi's activity

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

upvoted a paper 4 days ago

Evidence-RL: Towards Evidence-intensive Visual Reasoning

Paper • 2608.08021 • Published 8 days ago • 16

upvoted a paper 12 days ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published 21 days ago • 105

updated a collection 12 days ago

Interesting work but not directly related

Collection

8 items • Updated 12 days ago

upvoted a paper 17 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 20 days ago • 491

upvoted a paper 19 days ago

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Paper • 2607.18217 • Published 27 days ago • 61

updated a collection 29 days ago

From Vision to Motion

Collection

22 items • Updated 29 days ago • 1

upvoted a paper 29 days ago

RoboTTT: Context Scaling for Robot Policies

Paper • 2607.15275 • Published about 1 month ago • 23

updated a collection 29 days ago

Interesting work but not directly related

Collection

8 items • Updated 12 days ago

updated 2 collections 30 days ago

Interesting work but not directly related

Collection

8 items • Updated 12 days ago

From Vision to Motion

Collection

22 items • Updated 29 days ago • 1

upvoted 3 papers 30 days ago

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

Paper • 2606.25041 • Published Jun 23 • 122

Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?

Paper • 2606.26428 • Published Jun 24 • 17

SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

Paper • 2606.28276 • Published Jun 26 • 17

upvoted a paper about 1 month ago

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Paper • 2606.08671 • Published Jun 23 • 47

updated a collection about 1 month ago

From Vision to Motion

Collection

22 items • Updated 29 days ago • 1

upvoted 5 papers about 1 month ago

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published Jun 26 • 53

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published Jul 2 • 68

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published Jul 7 • 95

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Paper • 2607.02515 • Published Jul 2 • 19

Attending to Multimodal Generation One Token at a Time

Paper • 2607.03738 • Published Jul 4 • 10