Shukai Gong

ShukaiGong's activity

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

upvoted 4 papers 7 days ago

MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

Paper • 2610.06801 • Published 15 days ago • 46

World Action Learning via Interaction-Centric Spectral Latent Guidance

Paper • 2610.03607 • Published 18 days ago • 50

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

Paper • 2608.04436 • Published Aug 5 • 61

RoboCoach: World Models as Active Coaches for Compositional Robot Skills

Paper • 2609.39685 • Published 20 days ago • 17

upvoted a paper 8 days ago

Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation

Paper • 2610.02368 • Published 19 days ago • 74

upvoted a paper 10 days ago

OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning

Paper • 2610.12458 • Published 12 days ago • 18

upvoted 2 papers 4 months ago

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

Paper • 2606.28128 • Published Jun 26 • 55

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

Paper • 2606.20521 • Published Jun 18 • 15

upvoted 2 papers 5 months ago

StableVLA: Towards Robust Vision-Language-Action Models without Extra Data

Paper • 2605.18287 • Published May 18 • 15

HumanNet: Scaling Human-centric Video Learning to One Million Hours

Paper • 2605.06747 • Published May 7 • 55

upvoted a paper 8 months ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 60

upvoted 2 papers 9 months ago

Rethinking Video Generation Model for the Embodied World

Paper • 2601.15282 • Published Jan 21 • 46

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53