Amrit Singh Bedi

7

Papers

0

Total Citations

Papers (7)

Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

Position: On the Possibilities of AI-Generated Text Detection

PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling

MaxMin-RLHF: Alignment with Diverse Human Preferences

Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles