Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Understanding and Exploiting Anisotropy in Post-Training
Samyak Jha, Harshvardhan Saini, Yizhen Liao +2
LLM post-training combines supervised fine-tuning (SFT), a mode-covering forward-KL objective, with reinforcement learning (RL), a mode-seeking reverse-KL objective. Frequency-weig…
cs.LG2026
Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
Yiming Tang, Harshvardhan Saini, Samyak Jha +3
Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability, essential both for the scien…