Harold Chen

Harold328's activity

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

upvoted 2 papers about 6 hours ago

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published 1 day ago • 27

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 3 days ago • 109

upvoted a paper about 7 hours ago

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Paper • 2603.26599 • Published 5 days ago • 42

upvoted a paper 2 days ago

ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

Paper • 2603.25746 • Published 6 days ago • 149

upvoted 2 papers 5 days ago

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Paper • 2603.12254 • Published 20 days ago • 21

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

Paper • 2603.23500 • Published 8 days ago • 35

upvoted a paper 8 days ago

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 9 days ago • 119

upvoted a paper 9 days ago

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

Paper • 2603.17051 • Published 15 days ago • 106

upvoted 4 papers 12 days ago

MosaicMem: Hybrid Spatial Memory for Controllable Video World Models

Paper • 2603.17117 • Published 15 days ago • 87

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 15 days ago • 134

FASTER: Rethinking Real-Time Flow VLAs

Paper • 2603.19199 • Published 13 days ago • 57

ESPIRE: A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models

Paper • 2603.13033 • Published 19 days ago • 13

upvoted 2 papers 13 days ago

GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent

Paper • 2603.13875 • Published 18 days ago • 34

Demystifing Video Reasoning

Paper • 2603.16870 • Published 15 days ago • 367

upvoted 3 papers 15 days ago

Learning Latent Proxies for Controllable Single-Image Relighting

Paper • 2603.15555 • Published 16 days ago • 8

Panoramic Affordance Prediction

Paper • 2603.15558 • Published 16 days ago • 9

Attention Residuals

Paper • 2603.15031 • Published 16 days ago • 170

upvoted a paper 16 days ago

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Paper • 2603.12648 • Published 19 days ago • 14

liked a Space 19 days ago

Running on Zero

Featured

30

DVD

🦀

30

Official demo of DVD (https://dvd-project.github.io/)

authored a paper 19 days ago

DVD: Deterministic Video Depth Estimation with Generative Priors

Paper • 2603.12250 • Published 20 days ago • 26