USTC

UmiSonoda16

·

drx-code

AI & ML interests

Computer Vision; Image and Video Generation

Recent Activity

liked a model 11 days ago

deepseek-ai/DeepSeek-V4-Flash-0731

upvoted a paper 12 days ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

upvoted a paper 2 months ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

View all activity

Organizations

None yet

upvoted a paper 12 days ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published 13 days ago • 116

upvoted a paper 2 months ago

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Paper • 2606.13432 • Published Jun 11 • 113

upvoted 3 papers over 1 year ago

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Paper • 2504.15279 • Published Apr 21, 2025 • 78

Optimal Stepsize for Diffusion Sampling

Paper • 2503.21774 • Published Mar 27, 2025 • 13

Equivariant Image Modeling

Paper • 2503.18948 • Published Mar 24, 2025 • 15