Xu Huang

Savoia's activity

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

upvoted a paper about 10 hours ago

dNaViT: Discrete Codes are General-Purpose Visual Representations

Paper • 2611.12426 • Published 3 days ago • 32

upvoted a paper 3 days ago

Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models

Paper • 2611.06817 • Published 1 day ago • 37

liked a dataset 3 days ago

DAGroup-PKU/Open-HumanWAM-50K

Viewer • Updated about 1 hour ago • 56.5M • 1.02M • 20

updated a model 11 days ago

DAGroup-PKU/G-star

Text-to-Image • 10B • Updated 11 days ago • 76 • 1

liked a model 12 days ago

DAGroup-PKU/G-star

Text-to-Image • 10B • Updated 11 days ago • 76 • 1

published a model 12 days ago

DAGroup-PKU/G-star

Text-to-Image • 10B • Updated 11 days ago • 76 • 1

upvoted a paper 26 days ago

WorldCast: Exploring Intelligent Visual Generation in World State Prediction

Paper • 2610.20731 • Published 29 days ago • 34

liked a model 30 days ago

DAGroup-PKU/ViGAR

Robotics • Updated 21 days ago • 42 • 19

authored a paper about 1 month ago

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published Sep 30 • 24

upvoted 3 papers about 1 month ago

Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens

Paper • 2610.01939 • Published 30 days ago • 24

DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence

Paper • 2609.39222 • Published Sep 30 • 24

Post-Training Leaves Behavioral Shadows on Unrelated Decisions

Paper • 2609.29233 • Published Sep 24 • 45

liked a model about 2 months ago

XiaomiMiMo/MiMo-V2.6-Flash-RL

Text Generation • 311B • Updated 14 days ago • 69.7k • • 593

upvoted 3 papers 3 months ago

EchoWM: Open and Enterable Omnimodal World Models

Paper • 2608.23189 • Published Aug 24 • 82

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published Aug 13 • 60

ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation

Paper • 2608.04436 • Published Aug 5 • 58

authored a paper 3 months ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published Jul 29 • 55

upvoted a paper 3 months ago

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published Jul 29 • 55

upvoted a paper 4 months ago

GEAR: Guided End-to-End AutoRegression for Image Synthesis

Paper • 2606.32039 • Published Jun 30 • 32

upvoted a paper 5 months ago

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published Jun 26 • 51