Sitaram Asur

PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning

LLM as a Classifier: Leveraging Large Language Models for Text and Vision Classification

PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning

UNA: Unifying Alignments of RLHF/PPO, DPO and KTO by a Generalized Implicit Reward Function