Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
FORGE: Fused On-Register Gradient Elimination for Memory-Efficient LLM Training
Dikshant Kukreja, Kritarth Prasad, Avinash Anand +6
Reverse-mode differentiation computes every weight gradient, writes it to memory, and only then lets the optimizer read it back. This two-phase schedule sets the memory ceiling of…
cs.LG2024
Enhancing LLMs for Physics Problem-Solving using Reinforcement Learning with Human-AI Feedback
Avinash Anand, Kritarth Prasad, Chhavi Kirtani +6
Large Language Models (LLMs) have demonstrated strong capabilities in text-based tasks but struggle with the complex reasoning required for physics problems, particularly in advanc…