GenAI Invited Talk
Azure GenAI team (led by Weizhu Chen) organizes LLM talk series to discuss advance on LLM. Please contact Shuohang Wang, shuowa@microsoft.com, if you need more details : ) Our most popular talk has 151 researchers attended : )
Presenter | Affiliation | Date | Title |
Hao Zhang | UCSD | Sep 27, 2024 | Chatbot Arena: Serving and Evaluating LLMs in the Wild |
Danqi Chen | Princeton University | June 20, 2024 | Less & SimPO |
Corby Rosset | Microsoft | May 3, 2024 | Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences |
Guangxuan Xiao | MIT | Mar 29, 2024 | StreamLLM & SmoothQuant |
Rafael Rafailov | Stanford | Feb 23, 2024 | Direct Preference Optimization: Your Language Model is Secretly a Reward Model |
Trevor Gale | Stanford/Google | Jan 26, 2024 | MegaBlocks: Efficient Sparse Training with Mixture-of-Experts, Speaker |
Xupeng Miao | CMU | Nov 17, 2023 | SpecInfer: Accelerating Generative LLM Serving with Tree-based Speculative Inference and Token Verification |
Tri Dao | Together.AI & Princeton Univerisity | Oct 20, 2023 | FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness |
Woosuk Kwon and Zhuohan Li | UC Berkeley | Sep 22, 2023 | PagedAttention / vLLM |