ZhengQi Wan

Vanqi's activity

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

updated a collection 1 day ago

From Vision to Motion

Collection

3 items • Updated 1 day ago

upvoted a paper 1 day ago

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

Paper • 2603.25716 • Published 5 days ago • 140

updated a collection 8 days ago

From Vision to Motion

Collection

3 items • Updated 1 day ago

upvoted 2 papers 8 days ago

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

Paper • 2603.17024 • Published 14 days ago • 106

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

Paper • 2603.19708 • Published 11 days ago • 12

upvoted a paper 11 days ago

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

Paper • 2603.19235 • Published 12 days ago • 93

upvoted a paper 20 days ago

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

Paper • 2603.06569 • Published 25 days ago • 117

upvoted 2 papers 21 days ago

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Paper • 2603.03269 • Published 28 days ago • 61

Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence

Paper • 2603.07660 • Published 23 days ago • 84

upvoted 2 papers 25 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 27 days ago • 178

T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning

Paper • 2603.03790 • Published 27 days ago • 121

upvoted a paper about 1 month ago

On Data Engineering for Scaling LLM Terminal Capabilities

Paper • 2602.21193 • Published Feb 24 • 101

upvoted a collection about 1 month ago

Nemotron-Terminal

Collection

We are releasing Nemotron-Terminal models and training datasets. • 5 items • Updated 7 days ago • 32

upvoted 5 papers about 1 month ago

The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies

Paper • 2602.09877 • Published Feb 10 • 197

Revisiting the Platonic Representation Hypothesis: An Aristotelian View

Paper • 2602.14486 • Published Feb 16 • 11

RynnBrain: Open Embodied Foundation Models

Paper • 2602.14979 • Published Feb 13 • 44

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published Feb 19 • 58

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Paper • 2602.08354 • Published Feb 9 • 262

upvoted a paper about 2 months ago

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

Paper • 2602.02402 • Published Feb 2 • 32

upvoted a paper 2 months ago

Your Group-Relative Advantage Is Biased

Paper • 2601.08521 • Published Jan 13 • 158