Theodore R. Sumers

33 papers A* 7B 6Journal 20

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Are Large Language Models Sensitive to the Motives Behind Communication? CoRR Addison J. Wu, Ryan Liu, Kerem Oktar, Theodore R. Sumers, Thomas L. Griffiths
2025	J	`jnl`	Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming. CoRR Mrinank Sharma, Meg Tong, Jesse Mu, Jerry Wei, Jorrit Kruthoff, Scott Goodfriend, Euan Ong, Alwin Peng, Raj Agarwal, Cem Anil, Amanda Askell, Nathan Bailey, Joe Benton, Emma Bluemke, Samuel R. Bowman, Eric Christiansen, Hoagy Cunningham, Andy Dau, Anjali Gopal, Rob Gilson, Logan Graham, Logan Howard, Nimit Kalra, Taesung Lee, Kevin Lin, Peter Lofgren, Francesco Mosconi, Clare O'Hara, Catherine Olsson, Linda Petrini, Samir Rajani, Nikhil Saxena, Alex Silverstein, Tanya Singh, Theodore R. Sumers, Leonard Tang, Kevin K. Troy, Constantin Weisser, Ruiqi Zhong, Giulio Zhou, Jan Leike, Jared Kaplan, Ethan Perez
2025	J	`jnl`	What Should Embeddings Embed? Autoregressive Models Represent Latent Generating Distributions. Trans. Mach. Learn. Res. Liyi Zhang, Michael Y. Li, R. Thomas McCoy, Theodore R. Sumers, Jian-Qiao Zhu, Thomas L. Griffiths
2024	B	`conf`	A Rational Model of Vigilance in Motivated Communication. CogSci Kerem Oktar, Theodore R. Sumers, Tom Griffiths
2024	J	`jnl`	Clio: Privacy-Preserving Insights into Real-World AI Use. CoRR Alex Tamkin, Miles McCain, Kunal Handa, Esin Durmus, Liane Lovitt, Ankur Rathi, Saffron Huang, Alfred Mountfield, Jerry Hong, Stuart J. Ritchie, Michael Stern, Brian Clarke, Landon Goldberg, Theodore R. Sumers, Jared Mueller, William McEachen, Wes Mitchell, Shan Carter, Jack Clark, Jared Kaplan, Deep Ganguli
2024	J	`jnl`	Cognitive Architectures for Language Agents. Trans. Mach. Learn. Res. Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths
2024	A*	`conf`	How do Large Language Models Navigate Conflicts between Honesty and Helpfulness? ICML Ryan Liu, Theodore R. Sumers, Ishita Dasgupta, Thomas L. Griffiths
2024	J	`jnl`	How do Large Language Models Navigate Conflicts between Honesty and Helpfulness? CoRR Ryan Liu, Theodore R. Sumers, Ishita Dasgupta, Thomas L. Griffiths
2024	A*	`conf`	Learning with Language-Guided State Abstractions. ICLR Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie Shah
2024	J	`jnl`	Learning with Language-Guided State Abstractions. CoRR Andi Peng, Ilia Sucholutsky, Belinda Z. Li, Theodore R. Sumers, Thomas L. Griffiths, Jacob Andreas, Julie A. Shah
2024	A*	`conf`	Preference-Conditioned Language-Guided Abstraction. HRI Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah
2024	J	`jnl`	Preference-Conditioned Language-Guided Abstraction. CoRR Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah
2024	B	`conf`	Publish or Perish: Simulating the Impact of Publication Policies on Science. CogSci Marina Mancoridis, Theodore R. Sumers, Tom Griffiths
2024	J	`jnl`	Rational Metareasoning for Large Language Models. CoRR Nicolò De Sabbata, Theodore R. Sumers, Thomas L. Griffiths
2024	J	`jnl`	Representational Alignment Supports Effective Machine Teaching. CoRR Ilia Sucholutsky, Katherine M. Collins, Maya Malaviya, Nori Jacoby, Weiyang Liu, Theodore R. Sumers, Michalis Korakakis, Umang Bhatt, Mark K. Ho, Joshua B. Tenenbaum, Bradley C. Love, Zachary A. Pardos, Adrian Weller, Thomas L. Griffiths
2023	J	`jnl`	Cognitive Architectures for Language Agents. CoRR Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, Thomas L. Griffiths
2023	J	`jnl`	Deep de Finetti: Recovering Topic Distributions from Large Language Models. CoRR Liyi Zhang, R. Thomas McCoy, Theodore R. Sumers, Jian-Qiao Zhu, Thomas L. Griffiths
2023	A*	`conf`	Distilling Internet-Scale Vision-Language Models into Embodied Agents. ICML Theodore R. Sumers, Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta
2023	J	`jnl`	Distilling Internet-Scale Vision-Language Models into Embodied Agents. CoRR Theodore R. Sumers, Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta
2023	A*	`conf`	Words are all you need? Language as an approximation for human similarity judgments. ICLR Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
2022	A*	`conf`	How to talk so AI will learn: Instructions, descriptions, and autonomy. NeurIPS Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Tom Griffiths, Dylan Hadfield-Menell
2022	J	`jnl`	How to talk so your robot will learn: Instructions, descriptions, and pragmatics. CoRR Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
2022	J	`jnl`	Linguistic communication as (inverse) reward design. CoRR Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell
2022	B	`conf`	Playing the Lottery of a Lifetime: The Effect of Socially Induced Aspiration on Q-Learning Agents. CogSci Yosi Hatekar, Rachit Dubey, Theodore R. Sumers, Ilia Sucholutsky
2022	B	`conf`	Predicting Human Similarity Judgments Using Large Language Models. CogSci Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers, Nori Jacoby, Tom Griffiths
2022	J	`jnl`	Predicting Human Similarity Judgments Using Large Language Models. CoRR Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers, Nori Jacoby, Thomas L. Griffiths
2022	J	`jnl`	Words are all you need? Capturing human sensory similarity with textual descriptors. CoRR Raja Marjieh, Pol van Rijn, Ilia Sucholutsky, Theodore R. Sumers, Harin Lee, Thomas L. Griffiths, Nori Jacoby
2021	B	`conf`	Extending rational models of communication from beliefs to actions. CogSci Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Tom Griffiths
2021	J	`jnl`	Extending rational models of communication from beliefs to actions. CoRR Theodore R. Sumers, Robert X. D. Hawkins, Mark K. Ho, Thomas L. Griffiths
2021	A*	`conf`	Learning Rewards From Linguistic Feedback. AAAI Theodore R. Sumers, Mark K. Ho, Robert X. D. Hawkins, Karthik Narasimhan, Thomas L. Griffiths
2020	J	`jnl`	Learning Rewards from Linguistic Feedback. CoRR Theodore R. Sumers, Mark K. Ho, Robert X. D. Hawkins, Karthik Narasimhan, Thomas L. Griffiths
2020	B	`conf`	Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation. CogSci Theodore R. Sumers, Mark K. Ho, Tom Griffiths
2020	J	`jnl`	Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation. CoRR Theodore R. Sumers, Mark K. Ho, Thomas L. Griffiths