Ye Huang

henry-y1's activity

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

authored 2 papers 1 day ago

MEGS$^{2}$: Memory-Efficient Gaussian Splatting via Spherical Gaussians and Unified Pruning

Paper • 2509.07021 • Published Sep 7, 2025

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

Paper • 2606.20521 • Published 9 days ago • 13

upvoted a paper 1 day ago

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

Paper • 2606.20521 • Published 9 days ago • 13

upvoted a paper 17 days ago

AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing

Paper • 2606.09811 • Published 19 days ago • 15

upvoted 2 papers 22 days ago

Qwen-Image-Flash: Beyond Objective Design

Paper • 2606.03746 • Published 25 days ago • 36

Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems

Paper • 2605.27492 • Published May 26 • 25

upvoted a paper 28 days ago

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models

Paper • 2605.30263 • Published 30 days ago • 59

upvoted a paper 29 days ago

Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving

Paper • 2605.23163 • Published May 25 • 17

upvoted 3 papers about 1 month ago

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

Paper • 2605.18287 • Published May 18 • 15

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published May 14 • 96

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published May 13 • 105

upvoted 3 papers about 2 months ago

WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors

Paper • 2605.10434 • Published May 11 • 29

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

Paper • 2605.06747 • Published May 7 • 55

Efficient Training on Multiple Consumer GPUs with RoundPipe

Paper • 2604.27085 • Published Apr 29 • 47

updated a model 2 months ago

DAGroup-PKU/MHLA

Updated Apr 17 • 3 • 4

upvoted a paper 4 months ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 60

upvoted 3 papers 5 months ago

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention

Paper • 2602.04789 • Published Feb 4 • 4

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

updated a model 6 months ago

DAGroup-PKU/MHLA

Updated Apr 17 • 3 • 4