Information-Gain Reinforcement Learning
A reinforcement learning method that uses the information increment produced by the reasoning process, such as reduced uncertainty or improved predictive likelihood, as the reward signal, without relying on human-annotated final answers.
Timeline (last 90 days)
The LARC training pipeline is divided into two stages: curriculum supervised fine-tuning (curriculum SFT) and information-gain reinforcement learning (information-gain RL).
Information-gain RL uses the information increment brought by the reasoning process as the reward signal, enabling the model to self-improve on image generation tasks that lack paired supervision.
All Facts (2)
The LARC training pipeline is divided into two stages: curriculum supervised fine-tuning (curriculum SFT) and information-gain reinforcement learning (information-gain RL).
50%UnverifiedInformation-gain RL uses the information increment brought by the reasoning process as the reward signal, enabling the model to self-improve on image generation tasks that lack paired supervision.
50%