Cite
Notes
Only stored in your browser.
Attribution
Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
arXiv 2025
Non-Markovian Reward Modelling from Trajectory Labels via Interpretable Multiple Instance Learning
arXiv 2022
from 2 papers
Christine Evers
Jinwei Hu
Joseph Early
Shuang Ao
Tom Bewley
Yi Dong
researcher