Souradip Chakraborty

Venues

Frequent coauthors

Papers

1. Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs
   EACL 2026 ·

   James Beetham

   DBLP profile ↗ORCID search ↗
2. A Technical Report on "Erasing the Invisible": The 2024 NeurIPS Competition on Stress Testing Image Watermarks
   NeurIPS 2025 ·

   Mucong Ding

   DBLP profile ↗ORCID search ↗
3. Active Preference Optimization for Sample Efficient RLHF
   ECML-PKDD 2025 ·

   Nirjhar Das

   DBLP profile ↗ORCID search ↗
4. Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
   AAAI 2025 ·

   Prashant Trivedi

   DBLP profile ↗ORCID search ↗
5. Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
   ICML 2025 ·

   Mohamad Fares El Hajj Chehade

   DBLP profile ↗ORCID search ↗
6. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
   AAAI 2025 ·

   Michael-Andrei Panaitescu-Liess

   DBLP profile ↗ORCID search ↗
7. Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
   ICLR 2025 · Souradip Chakraborty
8. Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
   NeurIPS 2025 ·

   Soumya Suvra Ghosal

   DBLP profile ↗ORCID search ↗
9. Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
   CVPR 2025 ·

   Soumya Suvra Ghosal

   DBLP profile ↗ORCID search ↗
10. Is Poisoning a Real Threat to DPO? Maybe More So Than You Think
    AAAI 2025 ·

    Pankayaraj Pathmanathan

    DBLP profile ↗ORCID search ↗
11. On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
    NeurIPS 2025 ·

    Anas Barakat

    DBLP profile ↗ORCID search ↗
12. On the Vulnerability of LLM/VLM-Controlled Robotics
    IROS 2025 ·

    Xiyang Wu

    DBLP profile ↗ORCID search ↗
13. Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems
    EMNLP 2025 ·

    Aakriti Agrawal

    DBLP profile ↗ORCID search ↗
14. MaxMin-RLHF: Alignment with Diverse Human Preferences
    ICML 2024 · Souradip Chakraborty
15. PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
    ICLR 2024 · Souradip Chakraborty
16. Position: On the Possibilities of AI-Generated Text Detection
    ICML 2024 · Souradip Chakraborty
17. Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
    ICLR 2024 ·

    Xiangyu Liu

    DBLP profile ↗ORCID search ↗
18. Transfer Q-star : Principled Decoding for LLM Alignment
    NeurIPS 2024 · Souradip Chakraborty