Soumya Suvra Ghosal

36 papers A* 7C 1Journal 19Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models. EACL (Volume 1: Long Papers) Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande, Ashwin Kalyan, Dinesh Manocha
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`	VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models. CoRR Soumya Suvra Ghosal, Youngeun Kim, Zhuowei Li, Ritwick Chaudhry, Linghan Xu, Hongjing Zhang, Jakub Zablocki, Yifan Xing, Qin Zhang
2025	—	`conf`	Better Features, Better Calibration: A Simple Fix for Overconfident Networks. ECML/PKDD (1) Soumya Suvra Ghosal, Ramya Hebbalaguppe, Dinesh Manocha
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`	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`	Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models. CoRR Atharvan Dogra, Soumya Suvra Ghosal, Ameet Deshpande, Ashwin Kalyan, Dinesh Manocha
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	J	`jnl`	KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning. CoRR Vaibhav Singh, Soumya Suvra Ghosal, Kapu Nirmal Joshua, Soumyabrata Pal, Sayak Ray Chowdhury
2025	—	`conf`	PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from related Example Banks. NAACL (Long Papers) Soumya Suvra Ghosal, Soumyabrata Pal, Koyel Mukherjee, Dinesh Manocha
2025	—	`conf`	RELIC: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples. EMNLP (Findings) Soumya Suvra Ghosal, Vaibhav Singh, Akash Ghosh, Soumyabrata Pal, Subhadip Baidya, Sriparna Saha, Dinesh Manocha
2025	J	`jnl`	Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples. CoRR Soumya Suvra Ghosal, Vaibhav Singh, Akash Ghosh, Soumyabrata Pal, Subhadip Baidya, Sriparna Saha, Dinesh Manocha
2024	J	`jnl`	Are Vision Transformers Robust to Spurious Correlations? Int. J. Comput. Vis. Soumya Suvra Ghosal, Yixuan Li
2024	A*	`conf`	How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection? AAAI Soumya Suvra Ghosal, Yiyou Sun, Yixuan Li
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	A*	`conf`	IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning. EMNLP Soumya Suvra Ghosal, Samyadeep Basu, Soheil Feizi, Dinesh Manocha
2024	J	`jnl`	IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning. CoRR Soumya Suvra Ghosal, Samyadeep Basu, Soheil Feizi, Dinesh Manocha
2024	J	`jnl`	PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks. CoRR Soumya Suvra Ghosal, Soumyabrata Pal, Koyel Mukherjee, Dinesh Manocha
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	A*	`conf`	Distributionally Robust Optimization with Probabilistic Group. AAAI Soumya Suvra Ghosal, Yixuan Li
2023	J	`jnl`	Distributionally Robust Optimization with Probabilistic Group. CoRR Soumya Suvra Ghosal, Yixuan Li
2023	J	`jnl`	How to Overcome Curse-of-Dimensionality for Out-of-Distribution Detection? CoRR Soumya Suvra Ghosal, Yiyou Sun, Yixuan Li
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	—	`conf`	A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection Using Compounded Corruptions. ECML/PKDD (3) Ramya Hebbalaguppe, Soumya Suvra Ghosal, Jatin Prakash, Harshad Khadilkar, Chetan Arora
2022	J	`jnl`	Are Vision Transformers Robust to Spurious Correlations? CoRR Soumya Suvra Ghosal, Yifei Ming, Yixuan Li
2020	—	`conf`	Lung Nodule Classification Using Convolutional Autoencoder and Clustering Augmented Learning Method(CALM). HSDM@WSDM Soumya Suvra Ghosal, Indranil Sarkar, Issmail El Hallaoui
2020	—	`conf`	Novel Approach to Music Genre Classification using Clustering Augmented Learning Method (CALM). AAAI Spring Symposium: Combining Machine Learning with Knowledge Engineering (1) Soumya Suvra Ghosal, Indranil Sarkar
2020	C	`conf`	ReSCo-CC: Unsupervised Identification of Key Disinformation Sentences. iiWAS Soumya Suvra Ghosal, Deepak P, Anna Jurek-Loughrey
2020	J	`jnl`	ReSCo-CC: Unsupervised Identification of Key Disinformation Sentences. CoRR Soumya Suvra Ghosal, Deepak P, Anna Jurek-Loughrey
2019	—	`conf`	A Deep Learning Approach to Predict Parking Occupancy using Cluster Augmented Learning Method. ICDM Workshops Soumya Suvra Ghosal, Abderrahman Bani, Amine Amrouss, Issmail El Hallaoui
2019	—	`conf`	Travel Time Prediction of Taxis using Tensor Factorization. COMAD/CODS Soumya Suvra Ghosal