Deepak Ramachandran

75 papers A* 20A 1Journal 32Unranked 19

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Best Policy Learning from Trajectory Preference Feedback. CoRR Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Zheng Wen
2025	J	`jnl`	Distributionally Robust Direct Preference Optimization. CoRR Zaiyan Xu, Sushil Vemuri, Kishan Panaganti, Dileep Kalathil, Rahul Jain, Deepak Ramachandran
2025	J	`jnl`	EraseBench: Understanding The Ripple Effects of Concept Erasure Techniques. CoRR Ibtihel Amara, Ahmed Imtiaz Humayun, Ivana Kajic, Zarana Parekh, Natalie Harris, Sarah Young, Chirag Nagpal, Najoung Kim, Junfeng He, Cristina Nader Vasconcelos, Deepak Ramachandran, Golnoosh Farnadi, Katherine A. Heller, Mohammad Havaei, Negar Rostamzadeh
2025	A*	`conf`	Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation. CVPR Xiaoying Xing, Avinab Saha, Junfeng He, Susan Hao, Paul Vicol, Moonkyung Ryu, Gang Li, Sahil Singla, Sarah Young, Yinxiao Li, Feng Yang, Deepak Ramachandran
2025	J	`jnl`	Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation. CoRR Xiaoying Xing, Avinab Saha, Junfeng He, Susan Hao, Paul Vicol, Moonkyung Ryu, Gang Li, Sahil Singla, Sarah Young, Yinxiao Li, Feng Yang, Deepak Ramachandran
2025	J	`jnl`	Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models. CoRR Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Zheng Wen
2025	A*	`conf`	Preference Adaptive and Sequential Text-to-Image Generation. ICML Ofir Nabati, Guy Tennenholtz, Chih-Wei Hsu, Moonkyung Ryu, Deepak Ramachandran, Yinlam Chow, Xiang Li, Craig Boutilier
2025	A*	`conf`	What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models. ICLR Ahmed Imtiaz Humayun, Ibtihel Amara, Cristina Nader Vasconcelos, Deepak Ramachandran, Candice Schumann, Junfeng He, Katherine A. Heller, Golnoosh Farnadi, Negar Rostamzadeh, Mohammad Havaei
2024	—	`conf`	Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation. AIES (1) Katherine M. Collins, Najoung Kim, Yonatan Bitton, Verena Rieser, Shayegan Omidshafiei, Yushi Hu, Sherol Chen, Senjuti Dutta, Minsuk Chang, Kimin Lee, Youwei Liang, Georgina Evans, Sahil Singla, Gang Li, Adrian Weller, Junfeng He, Deepak Ramachandran, Krishnamurthy Dj Dvijotham
2024	J	`jnl`	Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation. CoRR Katherine M. Collins, Najoung Kim, Yonatan Bitton, Verena Rieser, Shayegan Omidshafiei, Yushi Hu, Sherol Chen, Senjuti Dutta, Minsuk Chang, Kimin Lee, Youwei Liang, Georgina Evans, Sahil Singla, Gang Li, Adrian Weller, Junfeng He, Deepak Ramachandran, Krishnamurthy Dj Dvijotham
2024	A*	`conf`	Demystifying Embedding Spaces using Large Language Models. ICLR Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Jihwan Jeong, Lior Shani, Azamat Tulepbergenov, Deepak Ramachandran, Martin Mladenov, Craig Boutilier
2024	J	`jnl`	Discovering Personalized Semantics for Soft Attributes in Recommender Systems Using Concept Activation Vectors. Trans. Recomm. Syst. Christina Göpfert, Alex Haig, Chih-Wei Hsu, Yinlam Chow, Ivan Vendrov, Tyler Lu, Deepak Ramachandran, Hubert Pham, Mohammad Ghavamzadeh, Craig Boutilier
2024	J	`jnl`	Online Bandit Learning with Offline Preference Data. CoRR Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Zheng Wen
2024	J	`jnl`	Personalized and Sequential Text-to-Image Generation. CoRR Ofir Nabati, Guy Tennenholtz, Chih-Wei Hsu, Moonkyung Ryu, Deepak Ramachandran, Yinlam Chow, Xiang Li, Craig Boutilier
2024	—	`conf`	Prompt Expansion for Adaptive Text-to-Image Generation. ACL (1) Siddhartha Datta, Alexander Ku, Deepak Ramachandran, Peter Anderson
2024	A*	`conf`	Rich Human Feedback for Text-to-Image Generation. CVPR Youwei Liang, Junfeng He, Gang Li, Peizhao Li, Arseniy Klimovskiy, Nicholas Carolan, Jiao Sun, Jordi Pont-Tuset, Sarah Young, Feng Yang, Junjie Ke, Krishnamurthy Dj Dvijotham, Katherine M. Collins, Yiwen Luo, Yang Li, Kai J. Kohlhoff, Deepak Ramachandran, Vidhya Navalpakkam
2024	A*	`conf`	TaskLAMA: Probing the Complex Task Understanding of Language Models. AAAI Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran
2024	J	`jnl`	Understanding Subjectivity through the Lens of Motivational Context in Model-Generated Image Satisfaction. CoRR Senjuti Dutta, Sherol Chen, Sunny Mak, Amnah Ahmad, Katherine Maeve Collins, Alena Butryna, Deepak Ramachandran, Krishnamurthy Dvijotham, Ellie Pavlick, Ravi Rajakumar
2024	J	`jnl`	Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic. CoRR Connor Pryor, Quan Yuan, Jeremiah Z. Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, Lise Getoor
2024	A*	`conf`	e-COP : Episodic Constrained Optimization of Policies. NeurIPS Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Sahil Singla
2024	J	`jnl`	e-COP : Episodic Constrained Optimization of Policies. CoRR Akhil Agnihotri, Rahul Jain, Deepak Ramachandran, Sahil Singla
2023	A*	`conf`	BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information. NeurIPS Mehran Kazemi, Quan Yuan, Deepti Bhatia, Najoung Kim, Xin Xu, Vaiva Imbrasaite, Deepak Ramachandran
2023	J	`jnl`	BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information. CoRR Mehran Kazemi, Quan Yuan, Deepti Bhatia, Najoung Kim, Xin Xu, Vaiva Imbrasaite, Deepak Ramachandran
2023	J	`jnl`	Demystifying Embedding Spaces using Large Language Models. CoRR Guy Tennenholtz, Yinlam Chow, Chih-Wei Hsu, Jihwan Jeong, Lior Shani, Azamat Tulepbergenov, Deepak Ramachandran, Martin Mladenov, Craig Boutilier
2023	J	`jnl`	Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking. CoRR Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D'Amour, Dj Dvijotham, Adam Fisch, Katherine A. Heller, Stephen Pfohl, Deepak Ramachandran, Peter Shaw, Jonathan Berant
2023	A*	`conf`	KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals. ICLR Sandeep Silwal, Sara Ahmadian, Andrew Nystrom, Andrew McCallum, Deepak Ramachandran, Seyed Mehran Kazemi
2023	—	`conf`	KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals. SustaiNLP Sandeep Silwal, Sara Ahmadian, Andrew Nystrom, Andrew McCallum, Deepak Ramachandran, Seyed Mehran Kazemi
2023	—	`conf`	LAMBADA: Backward Chaining for Automated Reasoning in Natural Language. ACL (1) Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, Deepak Ramachandran
2023	J	`jnl`	Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities. CoRR Senjuti Dutta, Sid Mittal, Sherol Chen, Deepak Ramachandran, Ravi Rajakumar, Ian Kivlichan, Sunny Mak, Alena Butryna, Praveen K. Paritosh
2023	J	`jnl`	Prompt Expansion for Adaptive Text-to-Image Generation. CoRR Siddhartha Datta, Alexander Ku, Deepak Ramachandran, Peter Anderson
2023	A*	`conf`	Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play. ICLR Jeremiah Zhe Liu, Krishnamurthy (Dj) Dvijotham, Jihyeon Lee, Quan Yuan, Balaji Lakshminarayanan, Deepak Ramachandran
2023	J	`jnl`	Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play. CoRR Jeremiah Zhe Liu, Krishnamurthy (Dj) Dvijotham, Jihyeon Lee, Quan Yuan, Martin Strobel, Balaji Lakshminarayanan, Deepak Ramachandran
2023	—	`conf`	Realistic but Non-Identifiable Synthetic User Data Generation. EvalRS@KDD Isaac Noble, Ivan Vendrov, Xin Xu, Deepak Ramachandran
2023	J	`jnl`	Rich Human Feedback for Text-to-Image Generation. CoRR Youwei Liang, Junfeng He, Gang Li, Peizhao Li, Arseniy Klimovskiy, Nicholas Carolan, Jiao Sun, Jordi Pont-Tuset, Sarah Young, Feng Yang, Junjie Ke, Krishnamurthy Dj Dvijotham, Katie Collins, Yiwen Luo, Yang Li, Kai J. Kohlhoff, Deepak Ramachandran, Vidhya Navalpakkam
2023	J	`jnl`	Tackling Provably Hard Representative Selection via Graph Neural Networks. Trans. Mach. Learn. Res. Mehran Kazemi, Anton Tsitsulin, Hossein Esfandiari, MohammadHossein Bateni, Deepak Ramachandran, Bryan Perozzi, Vahab Mirrokni
2023	J	`jnl`	TaskLAMA: Probing the Complex Task Understanding of Language Models. CoRR Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran
2023	J	`jnl`	Understanding Finetuning for Factual Knowledge Extraction from Language Models. CoRR Mehran Kazemi, Sid Mittal, Deepak Ramachandran
2023	—	`conf`	Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic. ACL (1) Connor Pryor, Quan Yuan, Jeremiah Z. Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, Lise Getoor
2022	A*	`conf`	Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors. WWW Christina Göpfert, Yinlam Chow, Chih-Wei Hsu, Ivan Vendrov, Tyler Lu, Deepak Ramachandran, Craig Boutilier
2022	J	`jnl`	Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors. CoRR Christina Göpfert, Yinlam Chow, Chih-Wei Hsu, Ivan Vendrov, Tyler Lu, Deepak Ramachandran, Craig Boutilier
2022	A*	`conf`	FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue. EMNLP Alon Albalak, Yi-Lin Tuan, Pegah Jandaghi, Connor Pryor, Luke Yoffe, Deepak Ramachandran, Lise Getoor, Jay Pujara, William Yang Wang
2022	J	`jnl`	FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue. CoRR Alon Albalak, Yi-Lin Tuan, Pegah Jandaghi, Connor Pryor, Luke Yoffe, Deepak Ramachandran, Lise Getoor, Jay Pujara, William Yang Wang
2022	J	`jnl`	LAMBADA: Backward Chaining for Automated Reasoning in Natural Language. CoRR Seyed Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, Deepak Ramachandran
2022	A*	`conf`	Subjective Attributes in Conversational Recommendation Systems: Challenges and Opportunities. AAAI Filip Radlinski, Craig Boutilier, Deepak Ramachandran, Ivan Vendrov
2022	J	`jnl`	Tackling Provably Hard Representative Selection via Graph Neural Networks. CoRR Seyed Mehran Kazemi, Anton Tsitsulin, Hossein Esfandiari, MohammadHossein Bateni, Deepak Ramachandran, Bryan Perozzi, Vahab S. Mirrokni
2022	—	`ed.`	Transfer Learning for Natural Language Processing Workshop, 03 December 2022, New Orleans, Louisiana, USA TL4NLP Alon Albalak, Chunting Zhou, Colin Raffel, Deepak Ramachandran, Sebastian Ruder, Xuezhe Ma
2021	—	`conf`	Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering. ACL/IJCNLP (1) Najoung Kim, Ellie Pavlick, Burcu Karagol Ayan, Deepak Ramachandran
2021	J	`jnl`	Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering. CoRR Najoung Kim, Ellie Pavlick, Burcu Karagol Ayan, Deepak Ramachandran
2020	J	`jnl`	Do Language Embeddings Capture Scales? CoRR Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, Dan Roth
2020	—	`conf`	Do Language Embeddings capture Scales? BlackboxNLP@EMNLP Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, Dan Roth
2020	—	`conf`	Do Language Embeddings capture Scales? EMNLP (Findings) Xikun Zhang, Deepak Ramachandran, Ian Tenney, Yanai Elazar, Dan Roth
2020	J	`jnl`	The Association for the Advancement of Artificial Intelligence 2020 Workshop Program. AI Mag. Grace Bang, Guy Barash, Ryan Beal, Jacques Calì, Mauricio Castillo-Effen, Xin Cynthia Chen, Niyati Chhaya, Rachel Cummings, Rohan Dhoopar, Sebastijan Dumancic, Huáscar Espinoza, Eitan Farchi, Ferdinando Fioretto, Raquel Fuentetaja, Christopher William Geib, Odd Erik Gundersen, José Hernández-Orallo, Xiaowei Huang, Kokil Jaidka, Sarah Keren, Seokhwan Kim, Michel Galley, Xiaomo Liu, Tyler Lu, Zhiqiang Ma, Richard Mallah, John A. McDermid, Martin Michalowski, Reuth Mirsky, Seán Ó hÉigeartaigh, Deepak Ramachandran, Javier Segovia-Aguas, Onn Shehory, Arash Shaban-Nejad, Vered Shwartz, Siddharth Srivastava, Kartik Talamadupula, Jian Tang, Pascal Van Hentenryck, Dell Zhang, Jian Zhang
2019	—	`conf`	How Large Are Lions? Inducing Distributions over Quantitative Attributes. ACL (1) Yanai Elazar, Abhijit Mahabal, Deepak Ramachandran, Tania Bedrax-Weiss, Dan Roth
2019	J	`jnl`	How Large Are Lions? Inducing Distributions over Quantitative Attributes. CoRR Yanai Elazar, Abhijit Mahabal, Deepak Ramachandran, Tania Bedrax-Weiss, Dan Roth
2015	—	`conf`	A TV Program Discovery Dialog System using recommendations. SIGDIAL Conference Deepak Ramachandran, Mark A. Fanty, Ronald Provine, Peter Z. Yeh, William Jarrold, Adwait Ratnaparkhi, Benjamin Douglas
2015	J	`jnl`	An End-to-End Conversational Second Screen Application for TV Program Discovery. AI Mag. Peter Z. Yeh, Deepak Ramachandran, Benjamin Douglas, Adwait Ratnaparkhi, William Jarrold, Ronald Provine, Peter F. Patel-Schneider, Stephen Laverty, Nirvana Tikku, Sean Brown, Jeremy Mendel, Adam Emfield
2015	—	`conf`	Belief Tracking with Stacked Relational Trees. SIGDIAL Conference Deepak Ramachandran, Adwait Ratnaparkhi
2014	A*	`conf`	A Speech-Driven Second Screen Application for TV Program Discovery. AAAI Peter Z. Yeh, Benjamin Douglas, William Jarrold, Adwait Ratnaparkhi, Deepak Ramachandran, Peter F. Patel-Schneider, Stephen Laverty, Nirvana Tikku, Sean Brown, Jeremy Mendel
2014	—	`conf`	An end-to-end dialog system for TV program discovery. SLT Deepak Ramachandran, Peter Z. Yeh, William Jarrold, Benjamin Douglas, Adwait Ratnaparkhi, Ronald Provine, Jeremy Mendel, Adam Emfield
2014	J	`jnl`	The Dialog State Tracking Challenge Series. AI Mag. Jason D. Williams, Matthew Henderson, Antoine Raux, Blaise Thomson, Alan W. Black, Deepak Ramachandran
2013	—	`conf`	Driver familiarity modeling for generating navigation directions. ITSC Deepak Ramachandran, Igor V. Karpov, Rakesh Gupta, Antoine Raux
2013	—	`conf`	The Dialog State Tracking Challenge. SIGDIAL Conference Jason D. Williams, Antoine Raux, Deepak Ramachandran, Alan W. Black
2012	A*	`conf`	Improving Hybrid Vehicle Fuel Efficiency Using Inverse Reinforcement Learning. AAAI Adam Vogel, Deepak Ramachandran, Rakesh Gupta, Antoine Raux
2012	—	`conf`	Landmark-Based Location Belief Tracking in a Spoken Dialog System. SIGDIAL Conference Yi Ma, Antoine Raux, Deepak Ramachandran, Rakesh Gupta
2011	—	`—`	Knowledge and Ignorance in Reinforcement Learning Deepak Ramachandran
2010	A	`conf`	Dynamic language modeling using Bayesian networks for spoken dialog systems. INTERSPEECH Antoine Raux, Neville Mehta, Deepak Ramachandran, Rakesh Gupta
2010	—	`conf`	Probabilistic Ontology Trees for Belief Tracking in Dialog Systems. SIGDIAL Conference Neville Mehta, Rakesh Gupta, Antoine Raux, Deepak Ramachandran, Stefan Krawczyk
2009	A*	`conf`	Smoothed Sarsa: Reinforcement learning for robot delivery tasks. ICRA Deepak Ramachandran, Rakesh Gupta
2009	—	`ch.`	Trust and Online Reputation Systems. Computing with Social Trust Ming Kwan, Deepak Ramachandran
2008	A*	`conf`	ManifoldBoost: stagewise function approximation for fully-, semi- and un-supervised learning. ICML Nicolas Loeff, David A. Forsyth, Deepak Ramachandran
2007	A*	`conf`	Bayesian Inverse Reinforcement Learning. IJCAI Deepak Ramachandran, Eyal Amir
2007	—	`conf`	Using Common Sense for Decision Making in an Adventure Game. AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning Deepak Ramachandran
2006	—	`conf`	Towards Scaleable and Adaptive Document Routing Services. IEEE SCC Deepak Ramachandran, Neil H. Boyette, Isaac K. Cheng, Vikas Krishna, Savitha Srinivasan
2005	A*	`conf`	Compact Propositional Encodings of First-Order Theories. AAAI Deepak Ramachandran, Eyal Amir
2005	A*	`conf`	Compact Propositional Encodings of First-Order Theories. IJCAI Deepak Ramachandran, Eyal Amir