Yi Ma

Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model

Efficient Offline Reinforcement Learning via Peer-Influenced Constraint

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

Don't Guess the Future, Find the Bottleneck: Spectral Subgoals for Offline Goal-Conditioned RL

ScaleMoE: Mixture-of-Experts for Scalable Continuous Control in Actor–Critic Reinforcement Learning

ScaleAC: Scale Actor-Critic by Replay Ratio

FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning