Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Tianzhe Chu, Yuexiang Zhai, Jihan Yang +6
Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization…
cs.AI2024
V-IRL: Grounding Virtual Intelligence in Real Life
Jihan Yang, Runyu Ding, Ellis Brown +2
There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created. To develop AI agents that can sense, think, and act as f…