AI.info

Guanjun Jiang

Explore Guanjun Jiang on AI.info.

• SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm
• Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
• ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning
• Search Self-play: Pushing the Frontier of Agent Capability without Supervision