2025
Toward Synthetic Data for LLM Post-training. Research Talk @Anuttacon. - February 2025
2024
A Brief and Partial Summary of RLHF Algorithms.
Reading Group @UCLA SCAI lab. - November 2024
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.
Reading Group @UCLA-NLP lab. ****- March 2024
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
. Reading Group @UCLA-AGI lab. - February 2024
2023
Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
. Invited talk at Beijing Academy of Artificial Intelligence (BAAI) & AI-Lab NLP Tech Seminar, ByteDance. - November 2023
Large Vision-Language Models
. Reading Group @UCLA-AGI lab. - June 2023