Hejian Sang
- Scaling In-Context Online Learning Capability of LLMs via Cross-Episode Meta-RL
2026/02/03 by Xiaofeng Lin, Sirou Zhu, Yilei Chen +6 · 1 voice
Computer Science · #cs.AI #cs.CL #cs.LG
- SODA: Semi On-Policy Black-Box Distillation for Large Language Models
2026/04/04 by Xiwen Chen, Jingjing Wang, Wenhui Zhu +7 · 1 citation
Computer Science · #cs.CL #cs.LG