Cite
Notes
Only stored in your browser.
Attribution
PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
arXiv 2025
Value Gradient weighted Model-Based Reinforcement Learning
value-gradient-weighted-model-based
from 2 papers
Animesh Garg
Avery Ma
Claas Voelcker
Victor Liao
Yangchen Pan