Souradip Chakraborty

74 papers A* 15A 1B 2Misc 1Journal 49Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Agentic Critical Training. CoRR Weize Liu, Minghui Liu, Sy-Tuyen Ho, Souradip Chakraborty, Xiyao Wang, Furong Huang
2026	J	`jnl`	BalancedDPO: Adaptive Multi-Metric Alignment. Trans. Mach. Learn. Res. Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare, Biplab Banerjee, Amrit Singh Bedi, Vaneet Aggarwal
2026	—	`conf`	Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs. EACL (Volume 1: Long Papers) James Beetham, Souradip Chakraborty, Mengdi Wang, Furong Huang, Amrit Singh Bedi, Mubarak Shah
2026	J	`jnl`	Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away. CoRR Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh, Furong Huang, Dinesh Manocha, Amrit Singh Bedi
2026	J	`jnl`	Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training. CoRR Anas Barakat, Souradip Chakraborty, Khushbu Pahwa, Amrit Singh Bedi
2025	—	`conf`	Active Preference Optimization for Sample Efficient RLHF. ECML/PKDD (5) Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury
2025	A*	`conf`	Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment. AAAI Prashant Trivedi, Souradip Chakraborty, Avinash Reddy, Vaneet Aggarwal, Amrit Singh Bedi, George K. Atia
2025	J	`jnl`	Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment. CoRR Prashant Trivedi, Souradip Chakraborty, Avinash Reddy, Vaneet Aggarwal, Amrit Singh Bedi, George K. Atia
2025	J	`jnl`	BalancedDPO: Adaptive Multi-Metric Alignment. CoRR Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare, Biplab Banerjee, Amrit Singh Bedi, Vaneet Aggarwal
2025	A*	`conf`	Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time. ICML Mohamad Fares El Hajj Chehade, Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Dinesh Manocha, Hao Zhu, Amrit Singh Bedi
2025	J	`jnl`	Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time. CoRR Mohamad Fares El Hajj Chehade, Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Dinesh Manocha, Hao Zhu, Amrit Singh Bedi
2025	A*	`conf`	Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
2025	A*	`conf`	Collab: Controlled Decoding using Mixture of Agents for LLM Alignment. ICLR Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag, Soumya Suvra Ghosal, Jiahao Qiu, Mengdi Wang, Dinesh Manocha, Furong Huang, Alec Koppel, Sumitra Ganesh
2025	J	`jnl`	Collab: Controlled Decoding using Mixture of Agents for LLM Alignment. CoRR Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag, Soumya Suvra Ghosal, Jiahao Qiu, Mengdi Wang, Dinesh Manocha, Furong Huang, Alec Koppel, Sumitra Ganesh
2025	J	`jnl`	Does Thinking More always Help? Understanding Test-Time Scaling in Reasoning Models. CoRR Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Yifu Lu, Mengdi Wang, Dinesh Manocha, Furong Huang, Mohammad Ghavamzadeh, Amrit Singh Bedi
2025	J	`jnl`	Enhancing Diversity in Large Language Models via Determinantal Point Processes. CoRR Yilei Chen, Souradip Chakraborty, Lorenz Wolf, Ioannis Ch. Paschalidis, Aldo Pacchiano
2025	J	`jnl`	Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity. CoRR Zaixi Zhang, Souradip Chakraborty, Amrit Singh Bedi, Emilin Mathew, Varsha Saravanan, Le Cong, Alvaro Velasquez, Sheng Lin-Gibson, Megan Blewett, Dan Hendrycs, Alex John London, Ellen Zhong, Ben Raphael, Jian Ma, Eric Xing, Russ Altman, George Church, Mengdi Wang
2025	J	`jnl`	HEART: Emotionally-driven test-time scaling of Language Models. CoRR Gabriela Pinto, Palash Goyal, Yiwen Song, Souradip Chakraborty, Zifeng Wang, Tomas Pfister, Hamid Palangi
2025	A*	`conf`	Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment. CVPR Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh, Tianrui Guan, Mengdi Wang, Ahmad Beirami, Furong Huang, Alvaro Velasquez, Dinesh Manocha, Amrit Singh Bedi
2025	A*	`conf`	Is Poisoning a Real Threat to DPO? Maybe More So Than You Think. AAAI Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang
2025	J	`jnl`	MIRA: Towards Mitigating Reward Hacking in Inference-Time Alignment of T2I Diffusion Models. CoRR Kevin Zhai, Utsav Singh, Anirudh Thatipelli, Souradip Chakraborty, Anit Kumar Sahu, Furong Huang, Amrit Singh Bedi, Mubarak Shah
2025	A	`conf`	On the Vulnerability of LLM/VLM-Controlled Robotics. IROS Xiyang Wu, Souradip Chakraborty, Ruiqi Xian, Jing Liang, Tianrui Guan, Fuxiao Liu, Brian M. Sadler, Dinesh Manocha, Amrit Singh Bedi
2025	J	`jnl`	PROPS: Progressively Private Self-alignment of Large Language Models. CoRR Noel Teku, Fengwei Tian, Payel Bhattacharjee, Souradip Chakraborty, Amrit Singh Bedi, Ravi Tandon
2025	J	`jnl`	PROPS: Progressively Private Self-alignment of Large Language Models. Trans. Mach. Learn. Res. Noel Teku, Fengwei Tian, Payel Bhattacharjee, Souradip Chakraborty, Amrit Singh Bedi, Ravi Tandon
2025	J	`jnl`	Review, Refine, Repeat: Understanding Iterative Decoding of AI Agents with Dynamic Evaluation and Selection. CoRR Souradip Chakraborty, Mohammadreza Pourreza, Ruoxi Sun, Yiwen Song, Nino Scherrer, Furong Huang, Amrit Singh Bedi, Ahmad Beirami, Jindong Gu, Hamid Palangi, Tomas Pfister
2025	J	`jnl`	Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts. CoRR Jihoon Lee, Hoyeon Moon, Kevin Zhai, Arun Kumar Chithanar, Anit Kumar Sahu, Soummya Kar, Chul Lee, Souradip Chakraborty, Amrit Singh Bedi
2025	—	`conf`	Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems. EMNLP (Findings) Aakriti Agrawal, Rohith Aralikatti, Anirudh Satheesh, Souradip Chakraborty, Amrit Singh Bedi, Furong Huang
2025	J	`jnl`	Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systems. CoRR Aakriti Agrawal, Rohith Aralikatti, Anirudh Satheesh, Souradip Chakraborty, Amrit Singh Bedi, Furong Huang
2025	J	`jnl`	VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences. CoRR Anukriti Singh, Amisha Bhaskar, Peihong Yu, Souradip Chakraborty, Ruthwik Dasyam, Amrit Singh Bedi, Pratap Tokekar
2024	J	`jnl`	AIME: AI System Optimization via Multiple LLM Evaluators. CoRR Bhrij Patel, Souradip Chakraborty, Wesley A. Suttle, Mengdi Wang, Amrit Singh Bedi, Dinesh Manocha
2024	J	`jnl`	Beyond Text: Improving LLM's Decision Making for Robot Navigation via Vocal Cues. CoRR Xingpeng Sun, Haoming Meng, Souradip Chakraborty, Amrit Singh Bedi, Aniket Bera
2024	J	`jnl`	Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks. Trans. Mach. Learn. Res. Xingpeng Sun, Haoming Meng, Souradip Chakraborty, Amrit S. Bedi, Aniket Bera
2024	J	`jnl`	Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? CoRR Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
2024	J	`jnl`	Hierarchical Preference Optimization: Learning to achieve goals via feasible subgoals prediction. CoRR Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler, Anit Kumar Sahu, Mubarak Shah, Vinay P. Namboodiri, Amrit Singh Bedi
2024	J	`jnl`	Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment. CoRR Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh, Tianrui Guan, Mengdi Wang, Ahmad Beirami, Furong Huang, Alvaro Velasquez, Dinesh Manocha, Amrit Singh Bedi
2024	J	`jnl`	Is poisoning a real threat to LLM alignment? Maybe more so than you think. CoRR Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang
2024	J	`jnl`	LIAR: Leveraging Alignment (Best-of-N) to Jailbreak LLMs in Seconds. CoRR James Beetham, Souradip Chakraborty, Mengdi Wang, Furong Huang, Amrit Singh Bedi, Mubarak Shah
2024	A*	`conf`	MaxMin-RLHF: Alignment with Diverse Human Preferences. ICML Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Dinesh Manocha, Furong Huang, Amrit S. Bedi, Mengdi Wang
2024	J	`jnl`	MaxMin-RLHF: Towards Equitable Alignment of Large Language Models with Diverse Human Preferences. CoRR Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Furong Huang, Dinesh Manocha, Amrit Singh Bedi, Mengdi Wang
2024	J	`jnl`	On the Safety Concerns of Deploying LLMs/VLMs in Robotics: Highlighting the Risks and Vulnerabilities. CoRR Xiyang Wu, Ruiqi Xian, Tianrui Guan, Jing Liang, Souradip Chakraborty, Fuxiao Liu, Brian M. Sadler, Dinesh Manocha, Amrit Singh Bedi
2024	J	`jnl`	On the Sample Complexity of a Policy Gradient Algorithm with Occupancy Approximation for General Utility Reinforcement Learning. CoRR Anas Barakat, Souradip Chakraborty, Peihong Yu, Pratap Tokekar, Amrit Singh Bedi
2024	A*	`conf`	PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback. ICLR Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Huazheng Wang, Dinesh Manocha, Mengdi Wang, Furong Huang
2024	A*	`conf`	Position: On the Possibilities of AI-Generated Text Detection. ICML Souradip Chakraborty, Amrit S. Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, Furong Huang
2024	J	`jnl`	Provably Sample Efficient RLHF via Active Preference Optimization. CoRR Nirjhar Das, Souradip Chakraborty, Aldo Pacchiano, Sayak Ray Chowdhury
2024	A*	`conf`	Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL. ICLR Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang
2024	J	`jnl`	SAIL: Self-Improving Efficient Online Alignment of Large Language Models. CoRR Mucong Ding, Souradip Chakraborty, Vibhu Agrawal, Zora Che, Alec Koppel, Mengdi Wang, Amrit S. Bedi, Furong Huang
2024	J	`jnl`	Transfer Q Star: Principled Decoding for LLM Alignment. CoRR Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang
2024	A*	`conf`	Transfer Q-star : Principled Decoding for LLM Alignment. NeurIPS Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang
2023	J	`jnl`	A Survey on the Possibilities & Impossibilities of AI-generated Text Detection. Trans. Mach. Learn. Res. Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha, Amrit S. Bedi
2023	J	`jnl`	Aligning Agent Policy with Externalities: Reward Design via Bilevel RL. CoRR Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Dinesh Manocha, Huazheng Wang, Furong Huang, Mengdi Wang
2023	A*	`conf`	Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policy Optimization. ICRA Souradip Chakraborty, Amrit Singh Bedi, Kasun Weerakoon, Prithvi Poddar, Alec Koppel, Pratap Tokekar, Dinesh Manocha
2023	J	`jnl`	On the Possibilities of AI-Generated Text Detection. CoRR Souradip Chakraborty, Amrit Singh Bedi, Sicheng Zhu, Bang An, Dinesh Manocha, Furong Huang
2023	A*	`conf`	Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning. AAAI Souradip Chakraborty, Amrit Singh Bedi, Pratap Tokekar, Alec Koppel, Brian M. Sadler, Furong Huang, Dinesh Manocha
2023	J	`jnl`	RE-MOVE: An Adaptive Policy Design Approach for Dynamic Environments via Language-Based Feedback. CoRR Souradip Chakraborty, Kasun Weerakoon, Prithvi Poddar, Pratap Tokekar, Amrit Singh Bedi, Dinesh Manocha
2023	J	`jnl`	REBEL: A Regularization-Based Solution for Reward Overoptimization in Reinforcement Learning from Human Feedback. CoRR Souradip Chakraborty, Amisha Bhaskar, Anukriti Singh, Pratap Tokekar, Dinesh Manocha, Amrit Singh Bedi
2023	J	`jnl`	Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in Multi-Agent RL. CoRR Xiangyu Liu, Souradip Chakraborty, Yanchao Sun, Furong Huang
2023	A*	`conf`	STEERING : Stein Information Directed Exploration for Model-Based Reinforcement Learning. ICML Souradip Chakraborty, Amrit S. Bedi, Alec Koppel, Mengdi Wang, Furong Huang, Dinesh Manocha
2023	J	`jnl`	STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning. CoRR Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Mengdi Wang, Furong Huang, Dinesh Manocha
2023	J	`jnl`	Towards Possibilities & Impossibilities of AI-generated Text Detection: A Survey. CoRR Soumya Suvra Ghosal, Souradip Chakraborty, Jonas Geiping, Furong Huang, Dinesh Manocha, Amrit Singh Bedi
2022	J	`jnl`	Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies. CoRR Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Pratap Tokekar, Dinesh Manocha
2022	Misc	`conf`	HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm. CoRL Kasun Weerakoon, Souradip Chakraborty, Nare Karapetyan, Adarsh Jagan Sathyamoorthy, Amrit S. Bedi, Dinesh Manocha
2022	J	`jnl`	HTRON: Efficient Outdoor Navigation with Sparse Rewards via Heavy Tailed Adaptive Reinforce Algorithm. CoRR Kasun Weerakoon, Souradip Chakraborty, Nare Karapetyan, Adarsh Jagan Sathyamoorthy, Amrit Singh Bedi, Dinesh Manocha
2022	A*	`conf`	On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces. ICML Amrit Singh Bedi, Souradip Chakraborty, Anjaly Parayil, Brian M. Sadler, Pratap Tokekar, Alec Koppel
2022	J	`jnl`	On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces. CoRR Amrit Singh Bedi, Souradip Chakraborty, Anjaly Parayil, Brian M. Sadler, Pratap Tokekar, Alec Koppel
2022	J	`jnl`	Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning. CoRR Souradip Chakraborty, Amrit Singh Bedi, Alec Koppel, Brian M. Sadler, Furong Huang, Pratap Tokekar, Dinesh Manocha
2020	B	`conf`	BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR. COLING Souradip Chakraborty, O. Ekaba Bisong, Shweta Bhatt, Thomas Wagner, Riley Elliott, Francesco Mosconi
2020	J	`jnl`	FairMixRep : Self-supervised Robust Representation Learning for Heterogeneous Data with Fairness constraints. CoRR Souradip Chakraborty, Ekansh Verma, Saswata Sahoo, Jyotishka Datta
2020	—	`conf`	FairMixRep: Self-supervised Robust Representation Learning for Heterogeneous Data with Fairness constraints. ICDM (Workshops) Souradip Chakraborty, Ekansh Verma, Saswata Sahoo, Jyotishka Datta
2020	J	`jnl`	G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling. CoRR Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul
2020	—	`conf`	G-SimCLR: Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling. ICDM (Workshops) Souradip Chakraborty, Aritra Roy Gosthipaty, Sayak Paul
2020	B	`conf`	Graph Spectral Feature Learning for Mixed Data of Categorical and Numerical Type. ICPR Saswata Sahoo, Souradip Chakraborty
2020	J	`jnl`	Graph Spectral Feature Learning for Mixed Data of Categorical and Numerical Type. CoRR Saswata Sahoo, Souradip Chakraborty
2020	J	`jnl`	Learning Representation for Mixed Data Types with a Nonlinear Deep Encoder-Decoder Framework. CoRR Saswata Sahoo, Souradip Chakraborty
2020	—	`conf`	Transformers at SemEval-2020 Task 11: Propaganda Fragment Detection Using Diversified BERT Architectures Based Ensemble Learning. SemEval@COLING Ekansh Verma, Vinodh Motupalli, Souradip Chakraborty