Rosy

rosywang

·

AI & ML interests

motion modelling

Recent Activity

liked a dataset 4 days ago

TimS-ml/kabr-video-diffusion

liked a model 4 days ago

nvidia/Cosmos-1.0-Diffusion-14B-Video2World

liked a model 4 days ago

divya55/YouTube_Video_Trending_Prediction_using_BERT_and_Multimodal

View all activity

Organizations

None yet

upvoted a paper 4 days ago

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Paper • 2610.13912 • Published 9 days ago • 47

upvoted 2 papers 5 days ago

Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction

Paper • 2610.12299 • Published 10 days ago • 70

Reasoning-Informed Visual Editing

Paper • 2610.12343 • Published 10 days ago • 24

upvoted 2 papers 8 days ago

RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning

Paper • 2610.09455 • Published 11 days ago • 46

AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model

Paper • 2610.08773 • Published 12 days ago • 18

upvoted 3 papers 14 days ago

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

Paper • 2609.35954 • Published 20 days ago • 54

LongLive-Plug: Once-for-All Distillation for Video Generation

Paper • 2609.38154 • Published 19 days ago • 42

MaLiang-Harness: A Programmable Path to Image and Video Generation

Paper • 2609.34309 • Published 20 days ago • 397

upvoted 2 papers 18 days ago

D-JEPA: A Decision-Aligned Latent World Model

Paper • 2609.24749 • Published 27 days ago • 18

FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance

Paper • 2609.25716 • Published 26 days ago • 24

upvoted 3 papers 23 days ago

Streaming Video Editing with Easy Adaptation

Paper • 2609.24788 • Published 27 days ago • 15

Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms

Paper • 2609.23658 • Published 28 days ago • 31

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 27 days ago • 161

upvoted 3 papers 25 days ago

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published Sep 17 • 79

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

Paper • 2609.18323 • Published Sep 16 • 121

RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation

Paper • 2609.16900 • Published Sep 15 • 49