UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations
Type
Publication
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics
Pei (Patrick) Chen
Applied Scientist at Amazon
Applied Scientist at Amazon working across the LLM training and evaluation stack — mid-training, post-training, RL, and rubric-based evaluation — on 400B+ MoE backbones for customer-facing agentic systems.