-
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper • 2601.00423 • Published • 11 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 229 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 71
Jongmin Kim
jmkim0309
AI & ML interests
None yet
Organizations
None yet
-
lightx2v/Hy1.5-Distill-Models
Text-to-Video • Updated • 169 • 29 -
Plan-X: Instruct Video Generation via Semantic Planning
Paper • 2511.17986 • Published • 18 -
In-Video Instructions: Visual Signals as Generative Control
Paper • 2511.19401 • Published • 32 -
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
Paper • 2511.20256 • Published • 28
-
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
Paper • 2601.00423 • Published • 11 -
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 229 -
Motion Attribution for Video Generation
Paper • 2601.08828 • Published • 71
-
lightx2v/Hy1.5-Distill-Models
Text-to-Video • Updated • 169 • 29 -
Plan-X: Instruct Video Generation via Semantic Planning
Paper • 2511.17986 • Published • 18 -
In-Video Instructions: Visual Signals as Generative Control
Paper • 2511.19401 • Published • 32 -
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
Paper • 2511.20256 • Published • 28
models 0
None public yet
datasets 0
None public yet