-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Paper • 2508.20751 • Published • 88 -
TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
Paper • 2508.17445 • Published • 80 -
VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
Paper • 2508.19247 • Published • 40 -
VibeVoice Technical Report
Paper • 2508.19205 • Published • 123
Bugai L
BugaiL
AI & ML interests
None yet
Recent Activity
updated
a collection
18 days ago
Bugai's Collection
upvoted
a
paper
18 days ago
From Editor to Dense Geometry Estimator
updated
a collection
19 days ago
Bugai's Collection
Organizations
None yet