Jie Cheng

4

Papers

15

Total Citations

Papers (4)

Ada-K Routing: Boosting the Efficiency of MoE-based LLMs

Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining

SC-Tune: Unleashing Self-Consistent Referential Comprehension in Large Vision Language Models

RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences