Shishir G Patil

large language model (2) question answering (1) chain-of-thought reasoning (1) instruction following (1) efficient computing (1) low-rank adaptation (1) supervised fine-tuning (1) reward shaping (1) parameter-efficient tuning (1) parameter-efficient finetuning (1) long context (1) context compression (1) rubric-based evaluation (1) reasoning structure (1) long chain-of-thought (1) reinforcement learning (1) reasoning demonstration (1)