News
| Apr 24, 2025 | I will attend ICLR in Singapore to present, Palu our awesome low-rank KV-Cache compression paper. Come find me for a coffee chat! |
|---|---|
| Mar 24, 2025 | Check out our latest work, xKV, which can compress DeepSeek MLA’s KV-Cache for another 3x. |
| Mar 14, 2025 | I successfully defended my PhD final exam. What a journey! Cannot wait for the next ;). |
| Mar 02, 2025 | The preprint of TeleRAG, our new paper on RAG inference acceleration, is out on ArXiv! |
| Jan 22, 2025 | Our KV-Cache compression framework, Palu, is accepted to ICLR 2025! You’re welcome to use our code to make your LLM more efficient. See you in Singapore! |
| Jan 10, 2025 |  I am on the job market for research positions in both academic and industry. Drop me an email if you have opportunities! |
| Jan 02, 2025 | I’m visiting Taiwan for three weeks. Hit me up if you want to chat about research! |
| Dec 14, 2024 | I’m attending NeurIPs 2024 in vancouver! |
| Oct 29, 2024 | Gave a talk on Palu KV-Cache compression at UW CSE research day. |