News

I am honored to join Tencent Hunyuan and to have been selected for Tencent’s Qingyun Talent Program.

Our paper “BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache! See you in Sydney!

Our paper “Seerattention: Learning intrinsic sparse attention in your llms.” and “MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems” have been accepted to NeurIPS 2025. Congratulations!

I am honored to receive a PhD offer from the School of Informatics at the University of Edinburgh, supported by ARIA funding! I will begin the program in January 2025 and look forward to this exciting new chapter.

Our paper “BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation” has been accepted to ACL 2024 main conference! See you in Thailand!