Kevin Zhang

Kevin-thu's activity

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

upvoted 2 papers 1 day ago

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory

Paper • 2606.16449 • Published 3 days ago • 3

Memento: Reconstruct to Remember for Consistent Long Video Generation

Paper • 2606.14667 • Published 6 days ago • 13

liked a model 2 days ago

youngsong305/MV-S2V

Updated 5 days ago • 66 • 9

upvoted a paper 3 days ago

MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation

Paper • 2606.09056 • Published 10 days ago • 5

upvoted 2 papers 10 days ago

Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation

Paper • 2606.04527 • Published 15 days ago • 28

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 17 days ago • 121

upvoted a paper 16 days ago

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published 22 days ago • 423

upvoted 2 papers 22 days ago

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Paper • 2605.23902 • Published 27 days ago • 46

SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

Paper • 2605.27367 • Published 23 days ago • 72

updated a model 24 days ago

Kevin-thu/StoryMem

Text-to-Video • Updated 24 days ago • 70 • 97

upvoted a paper 28 days ago

Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation

Paper • 2605.19833 • Published about 1 month ago • 134

upvoted a paper about 1 month ago

Flow-OPD: On-Policy Distillation for Flow Matching Models

Paper • 2605.08063 • Published May 8 • 101

upvoted a paper about 2 months ago

Video Analysis and Generation via a Semantic Progress Function

Paper • 2604.22554 • Published Apr 24 • 63

upvoted 4 papers 2 months ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 165

Lyra 2.0: Explorable Generative 3D Worlds

Paper • 2604.13036 • Published Apr 14 • 41

Self-Distilled RLVR

Paper • 2604.03128 • Published Apr 3 • 177

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 203

upvoted 3 papers 3 months ago

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

Paper • 2603.17051 • Published Mar 17 • 109

WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation

Paper • 2603.16871 • Published Mar 17 • 61

Demystifing Video Reasoning

Paper • 2603.16870 • Published Mar 17 • 373