News
research updates, milestones, and paper news.
- EAGLE-4 is available! I am a core contributor and designed and implemented its Efficient LM Head.
- NeurIPS 2026 Spotlight TreeGraft was accepted to NeurIPS 2026 as a Spotlight paper.
- ICML 2026 Spotlight Rethinking LLM Ensembling from the Perspective of Mixture Models was accepted to ICML 2026 as a Spotlight presentation.
- GraphIC: A Graph-Based In-Context Example Retrieval Model for Multi-Step Reasoning was accepted to AAAI 2026.
- Fast Large Language Model Collaborative Decoding via Speculation was accepted to ICML 2025.
- Mimic In-Context Learning for Multimodal Tasks was accepted to CVPR 2025.
- Joined Southeast University and PALM Lab as a master’s student, focusing on efficient inference for large language models.