Canyu Zhao

Canyu's activity

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

authored a paper 2 days ago

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Paper • 2602.06422 • Published 6 days ago • 41

upvoted a paper 3 days ago

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Paper • 2602.06422 • Published 6 days ago • 41

submitted a paper to Daily Papers 3 days ago

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Paper • 2602.06422 • Published 6 days ago • 41

upvoted a paper about 1 month ago

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Paper • 2601.07351 • Published Jan 12 • 26

upvoted a paper 2 months ago

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

Paper • 2512.07951 • Published Dec 8, 2025 • 50

upvoted a paper 3 months ago

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published Nov 25, 2025 • 48

authored a paper 3 months ago

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Paper • 2510.05057 • Published Oct 6, 2025 • 13

upvoted a paper 3 months ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 110

New activity in Canyu/DICEPTION 4 months ago

Remove library name

#2 opened 4 months ago by

nielsr

Improve model card: add metadata, links, and detailed usage

#1 opened 4 months ago by

nielsr

commented a paper 4 months ago

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Paper • 2510.05057 • Published Oct 6, 2025 • 13 •

3

upvoted a paper 4 months ago

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Paper • 2510.05057 • Published Oct 6, 2025 • 13

updated a model 5 months ago

Canyu/DICEPTION

Image-to-Image • Updated Oct 11, 2025 • 2

liked a model 5 months ago

Canyu/DICEPTION

Image-to-Image • Updated Oct 11, 2025 • 2

published a model 5 months ago

Canyu/DICEPTION

Image-to-Image • Updated Oct 11, 2025 • 2

upvoted a paper 5 months ago

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published Sep 15, 2025 • 106

upvoted a paper 6 months ago

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

Paper • 2508.08240 • Published Aug 11, 2025 • 45

authored a paper 6 months ago

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

Paper • 2508.14811 • Published Aug 20, 2025 • 42

upvoted a paper 6 months ago

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

Paper • 2508.14811 • Published Aug 20, 2025 • 42

commented a paper 6 months ago

Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization

Paper • 2508.14811 • Published Aug 20, 2025 • 42 •

2