fan xyz

fanzh03's activity

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

updated a model 4 days ago

fanzh03/lingbot-va

Updated 4 days ago • 1

upvoted a paper 10 days ago

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Paper • 2609.08084 • Published 14 days ago • 70

published a model 10 days ago

fanzh03/lingbot-va

Updated 4 days ago • 1

updated a model 11 days ago

fanzh03/robotwin_fewshot

Updated 11 days ago

updated a model 20 days ago

fanzh03/test_pi05

Updated 20 days ago

updated a model 22 days ago

fanzh03/fast-wam

Updated 22 days ago

upvoted 2 papers 26 days ago

TLive-Omni: An Omni-Modal Understanding Model for E-Commerce Live Streaming

Paper • 2608.20958 • Published Aug 21 • 58

On-policy Distillation with Verifiable Reward

Paper • 2608.24696 • Published 28 days ago • 17

published a model about 1 month ago

fanzh03/test_pi05

Updated 20 days ago

upvoted a paper about 1 month ago

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published Aug 17 • 151

updated a dataset about 1 month ago

fanzh03/FinPercep-RM

Updated Aug 14 • 255 • 1

upvoted a paper about 1 month ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published Aug 11 • 186

published a model about 1 month ago

fanzh03/fast-wam

Updated 22 days ago

upvoted a paper about 1 month ago

Addressable Memory for Video World Models

Paper • 2608.07408 • Published Aug 7 • 16

published a model about 1 month ago

fanzh03/robotwin_fewshot

Updated 11 days ago

upvoted 5 papers about 2 months ago

Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance

Paper • 2608.00782 • Published Aug 1 • 18

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

Paper • 2608.04530 • Published Aug 5 • 14

HelloWorld: Enabling Socially Interactive Characters in Video World Models

Paper • 2608.05070 • Published Aug 5 • 41

WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models

Paper • 2608.04964 • Published Aug 5 • 14

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

Paper • 2608.05131 • Published Aug 6 • 15