Souradip Chakraborty

6

Papers

28

Total Citations

Papers (6)

Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

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

Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

Position: On the Possibilities of AI-Generated Text Detection

MaxMin-RLHF: Alignment with Diverse Human Preferences