Rohin Shah

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 37

Top Topics

Dictionary Learning

Information From Multiple Sources

Bayesian Reinforcement Learning

Reactive Agents

Top Venues

NeurIPS (Competition and Demos)

Publications

Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda
Improving Dictionary Learning with Gated Sparse Autoencoders. CoRR (2024)
Mary Phuong, Matthew Aitchison, Elliot Catt, Sarah Cogan, Alexandre Kaskasoli, Victoria Krakovna, David Lindner, Matthew Rahtz, Yannis Assael, Sarah Hodkinson, Heidi Howard, Tom Lieberum, Ramana Kumar, Maria Abi Raad, Albert Webson, Lewis Ho, Sharon Lin, Sebastian Farquhar, Marcus Hutter, Grégoire Delétang, Anian Ruoss, Seliem El-Sayed, Sasha Brown, Anca D. Dragan, Rohin Shah, Allan Dafoe, Toby Shevlane
Evaluating Frontier Models for Dangerous Capabilities. CoRR (2024)
Zachary Kenton, Noah Y. Siegel, János Kramár, Jonah Brown-Cohen, Samuel Albanie, Jannis Bulian, Rishabh Agarwal, David Lindner, Yunhao Tang, Noah D. Goodman, Rohin Shah
On scalable oversight with weak LLMs judging strong LLMs. CoRR (2024)
János Kramár, Tom Lieberum, Rohin Shah, Neel Nanda
AtP*: An efficient and scalable method for localizing LLM behaviour to components. CoRR (2024)
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Sharada P. Mohanty, Byron Galbraith, Ke Chen, Yan Song, Tianze Zhou, Bingquan Yu, He Liu, Kai Guan, Yujing Hu, Tangjie Lv, Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik, Shu Ishida, João F. Henriques, Robert Klassert, Walter Laurito, Ellen R. Novoseller, Vinicius G. Goecks, Nicholas R. Waytowich, David Watkins, Josh Miller, Rohin Shah
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition. CoRR (2023)
Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan
SIRL: Similarity-based Implicit Representation Learning. CoRR (2023)
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks. NeurIPS (2023)
Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah
Challenges with unsupervised LLM knowledge discovery. CoRR (2023)
Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, Vladimir Mikulik
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla. CoRR (2023)
Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan
SIRL: Similarity-based Implicit Representation Learning. HRI (2023)
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks. CoRR (2023)
Vikrant Varma, Rohin Shah, Zachary Kenton, János Kramár, Ramana Kumar
Explaining grokking through circuit efficiency. CoRR (2023)
Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H. Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
An Empirical Investigation of Representation Learning for Imitation. CoRR (2022)
Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani, Anssi Kanervisto, Vinicius G. Goecks, Nicholas R. Waytowich, David Watkins-Valls, Bharat Prakash, Edmund Mills, Divyansh Garg, Alexander Fries, Alexandra Souly, Jun Shern Chan, Daniel del Castillo, Tom Lieberum
Retrospective on the 2021 BASALT Competition on Learning from Human Feedback. CoRR (2022)
Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, Zac Kenton
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals. CoRR (2022)
Dmitrii Krasheninnikov, Rohin Shah, Herke van Hoof
Combining Reward Information from Multiple Sources. CoRR (2021)
Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, Anca D. Dragan, Rohin Shah
Evaluating the Robustness of Collaborative Agents. AAMAS (2021)
Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli
Optimal Policies Tend To Seek Power. NeurIPS (2021)
Rachel Freedman, Rohin Shah, Anca D. Dragan
Choice Set Misspecification in Reward Inference. CoRR (2021)
Rohin Shah, Steven H. Wang, Cody Wild, Stephanie Milani, Anssi Kanervisto, Vinicius G. Goecks, Nicholas R. Waytowich, David Watkins-Valls, Bharat Prakash, Edmund Mills, Divyansh Garg, Alexander Fries, Alexandra Souly, Jun Shern Chan, Daniel del Castillo, Tom Lieberum
Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback. NeurIPS (Competition and Demos) (2021)
Rohin Shah, Cody Wild, Steven H. Wang, Neel Alex, Brandon Houghton, William H. Guss, Sharada P. Mohanty, Anssi Kanervisto, Stephanie Milani, Nicholay Topin, Pieter Abbeel, Stuart Russell, Anca D. Dragan
The MineRL BASALT Competition on Learning from Human Feedback. CoRR (2021)
David Lindner, Rohin Shah, Pieter Abbeel, Anca D. Dragan
Learning What To Do by Simulating the Past. CoRR (2021)
Cynthia Chen, Xin Chen, Sam Toyer, Cody Wild, Scott Emmons, Ian Fischer, Kuang-Huei Lee, Neel Alex, Steven H. Wang, Ping Luo, Stuart Russell, Pieter Abbeel, Rohin Shah
An Empirical Investigation of Representation Learning for Imitation. NeurIPS Datasets and Benchmarks (2021)
Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, Anca D. Dragan, Rohin Shah
Evaluating the Robustness of Collaborative Agents. CoRR (2021)
Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Sharada P. Mohanty, Byron Galbraith, Ke Chen, Yan Song, Tianze Zhou, Bingquan Yu, He Liu, Kai Guan, Yujing Hu, Tangjie Lv, Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik, Shu Ishida, João F. Henriques, Robert Klassert, Walter Laurito, Lucas Cazzonelli, Cedric Kulbach, Nicholas Popovic, Marvin Schweizer, Ellen R. Novoseller, Vinicius G. Goecks, Nicholas R. Waytowich, David Watkins, Josh Miller, Rohin Shah
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition. NeurIPS (Competition and Demos) (2021)
David Lindner, Rohin Shah, Pieter Abbeel, Anca D. Dragan
Learning What To Do by Simulating the Past. ICLR (2021)
Rachel Freedman, Rohin Shah, Anca D. Dragan
Choice Set Misspecification in Reward Inference. AISafety@IJCAI (2020)
Sam Toyer, Rohin Shah, Andrew Critch, Stuart Russell
The MAGICAL Benchmark for Robust Imitation. CoRR (2020)
Sam Toyer, Rohin Shah, Andrew Critch, Stuart Russell
The MAGICAL Benchmark for Robust Imitation. NeurIPS (2020)
Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca D. Dragan
Preferences Implicit in the State of the World. ICLR (Poster) (2019)
Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca D. Dragan
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference. CoRR (2019)
Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca D. Dragan
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference. ICML (2019)
Micah Carroll, Rohin Shah, Mark K. Ho, Thomas L. Griffiths, Sanjit A. Seshia, Pieter Abbeel, Anca D. Dragan
On the Utility of Learning about Humans for Human-AI Coordination. CoRR (2019)
Micah Carroll, Rohin Shah, Mark K. Ho, Tom Griffiths, Sanjit A. Seshia, Pieter Abbeel, Anca D. Dragan
On the Utility of Learning about Humans for Human-AI Coordination. NeurIPS (2019)
Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca D. Dragan
Preferences Implicit in the State of the World. CoRR (2019)
Sören Mindermann, Rohin Shah, Adam Gleave, Dylan Hadfield-Menell
Active Inverse Reward Design. CoRR (2018)
Rohin Shah, Emina Torlak, Rastislav Bodík
SIMPL: A DSL for Automatic Specialization of Inference Algorithms. CoRR (2016)
Phitchaya Mangpo Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla, Sarah E. Chasins, Rastislav Bodík
Chlorophyll: synthesis-aided compiler for low-power spatial architectures. PLDI (2014)