ZhengQi Wan

Vanqi's activity

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

upvoted a paper 1 day ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 3 days ago • 371

upvoted a paper 3 days ago

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

Paper • 2607.18217 • Published 10 days ago • 59

upvoted a paper 13 days ago

RoboTTT: Context Scaling for Robot Policies

Paper • 2607.15275 • Published 14 days ago • 23

upvoted 13 papers 14 days ago

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

Paper • 2606.25041 • Published Jun 23 • 120

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 • 15

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

Paper • 2606.08671 • Published Jun 23 • 46

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 28 days ago • 67

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

Paper • 2607.06559 • Published 23 days ago • 95

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Paper • 2607.02515 • Published 28 days ago • 19

Attending to Multimodal Generation One Token at a Time

Paper • 2607.03738 • Published 26 days ago • 10

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published 23 days ago • 79

Latent-Identity Tuning in Text-to-Image Personalization Models

Paper • 2607.11885 • Published 17 days ago • 14

Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model

Paper • 2607.11643 • Published 17 days ago • 44

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published 20 days ago • 53

upvoted 3 papers about 2 months ago

VideoMDM: Towards 3D Human Motion Generation From 2D Supervision

Paper • 2606.13364 • Published Jun 11 • 20

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 141

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Paper • 2605.31604 • Published May 29 • 63

upvoted a paper 2 months ago

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 93