ZhengQi Wan

Vanqi's activity

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

upvoted 2 papers 7 days ago

Prox-E: Fine-Grained 3D Shape Editing via Primitive-Based Abstractions

Paper • 2604.23774 • Published 14 days ago • 15

Let ViT Speak: Generative Language-Image Pre-training

Paper • 2605.00809 • Published 12 days ago • 32

upvoted a paper 10 days ago

MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

Paper • 2604.28130 • Published 13 days ago • 22

upvoted 2 papers 20 days ago

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published Apr 9 • 245

CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation

Paper • 2604.19636 • Published 22 days ago • 87

upvoted a paper 21 days ago

OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Paper • 2604.18486 • Published 23 days ago • 90

upvoted 2 papers 28 days ago

Introspective Diffusion Language Models

Paper • 2604.11035 • Published 30 days ago • 24

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

Paper • 2604.11297 • Published 30 days ago • 141

upvoted 2 papers 29 days ago

Training a Student Expert via Semi-Supervised Foundation Model Distillation

Paper • 2604.03841 • Published Apr 4 • 10

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

Paper • 2604.06628 • Published Apr 8 • 324

upvoted 5 papers about 1 month ago

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

Paper • 2604.04934 • Published Apr 6 • 46

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 203

VOID: Video Object and Interaction Deletion

Paper • 2604.02296 • Published Apr 2 • 54

LightThinker++: From Reasoning Compression to Memory Management

Paper • 2604.03679 • Published Apr 4 • 38

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

Paper • 2603.25716 • Published Mar 26 • 156

upvoted 3 papers about 2 months ago

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

Paper • 2603.17024 • Published Mar 17 • 109

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

Paper • 2603.19708 • Published Mar 20 • 13

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

Paper • 2603.19235 • Published Mar 19 • 95

upvoted 2 papers 2 months ago

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

Paper • 2603.06569 • Published Mar 6 • 119

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Paper • 2603.03269 • Published Mar 3 • 63