Wei Liu

lefutonku's activity

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

liked a model 3 days ago

zgcagi/ZGCM-1-7B

Text Generation • 7B • Updated 4 days ago • 2.13k • 35

liked a dataset 3 days ago

zgcagi/ZGCM-1-Data

Viewer • Updated 4 days ago • 5.44B • 23.7k • 58

upvoted a paper 4 days ago

Agent as Policy for Robotic Manipulation

Paper • 2609.12541 • Published 12 days ago • 17

liked a dataset 14 days ago

openbmb/UltraX-Preview

Viewer • Updated Jul 17 • 114M • 14.6k • 286

liked a model 14 days ago

openbmb/MiniCPM5-2B

Text Generation • 3B • Updated 11 days ago • 509k • 1.67k

upvoted 3 papers 15 days ago

NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference

Paper • 2609.01657 • Published 23 days ago • 34

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

Paper • 2609.04131 • Published 20 days ago • 31

Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training

Paper • 2608.26730 • Published 27 days ago • 155

liked a dataset 20 days ago

3DReflecNet/3DReflecNet

Updated Aug 6 • 284 • 5

upvoted 2 papers 21 days ago

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

Paper • 2608.30935 • Published 23 days ago • 32

Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction

Paper • 2608.27529 • Published 27 days ago • 32

liked a model 22 days ago

Qwen/Qwen3-Embedding-8B

Feature Extraction • 8B • Updated Jul 7, 2025 • 2.6M • • 809

liked a Space 25 days ago

Running on Zero

Agents

Featured

464

Depth Anything 3

🏢

464

Generate depth maps from your photos

liked a dataset 29 days ago

LightwheelAI/EgoStandard

Updated Aug 22 • 576 • 77

upvoted a collection 29 days ago

EgoSuite-Open100K

Collection

The largest fully-annotated open egocentric human dataset. 100,000 hours across 15,000+ tasks and scenes. • 3 items • Updated Aug 19 • 59

upvoted 5 papers about 1 month ago

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

Paper • 2605.03042 • Published May 4 • 152

VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?

Paper • 2608.15265 • Published Aug 15 • 60

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published Aug 17 • 152

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Paper • 2608.04205 • Published Aug 4 • 54

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published Aug 17 • 122