Rohin Shah

According to our database, Rohin Shah authored at least 33 papers between 2014 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking.

Sebastian Farquhar, Vikrant Varma, David Lindner, David Elson, Caleb Biddulph, Ian Goodfellow, Rohin Shah

CoRR, January, 2025

2024

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Tom Lieberum, Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Nicolas Sonnerat, Vikrant Varma, János Kramár, Anca D. Dragan, Rohin Shah, Neel Nanda

CoRR, 2024

Improving Dictionary Learning with Gated Sparse Autoencoders.

Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda

CoRR, 2024

Evaluating Frontier Models for Dangerous Capabilities.

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

CoRR, 2024

AtP*: An efficient and scalable method for localizing LLM behaviour to components.

János Kramár, Tom Lieberum, Rohin Shah, Neel Nanda

CoRR, 2024

Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders.

Senthooran Rajamanoharan, Arthur Conmy, Lewis Smith, Tom Lieberum, Vikrant Varma, János Kramár, Rohin Shah, Neel Nanda

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

On scalable oversight with weak LLMs judging strong LLMs.

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

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Challenges with unsupervised LLM knowledge discovery.

Sebastian Farquhar, Vikrant Varma, Zachary Kenton, Johannes Gasteiger, Vladimir Mikulik, Rohin Shah

CoRR, 2023

Explaining grokking through circuit efficiency.

Vikrant Varma, Rohin Shah, Zachary Kenton, János Kramár, Ramana Kumar

CoRR, 2023

Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

Tom Lieberum, Matthew Rahtz, János Kramár, Neel Nanda, Geoffrey Irving, Rohin Shah, Vladimir Mikulik

CoRR, 2023

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition.

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

CoRR, 2023

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks.

Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Rohin Shah

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

SIRL: Similarity-based Implicit Representation Learning.

Andreea Bobu, Yi Liu, Rohin Shah, Daniel S. Brown, Anca D. Dragan

Proceedings of the 2023 ACM/IEEE International Conference on Human-Robot Interaction, 2023

2022

Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals.

Rohin Shah, Vikrant Varma, Ramana Kumar, Mary Phuong, Victoria Krakovna, Jonathan Uesato, Zac Kenton

CoRR, 2022

An Empirical Investigation of Representation Learning for Imitation.

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

CoRR, 2022

Retrospective on the 2021 BASALT Competition on Learning from Human Feedback.

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

CoRR, 2022

2021

The MineRL BASALT Competition on Learning from Human Feedback.

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

CoRR, 2021

Combining Reward Information from Multiple Sources.

Dmitrii Krasheninnikov, Rohin Shah, Herke van Hoof

CoRR, 2021

Optimal Policies Tend To Seek Power.

Alexander Matt Turner, Logan Smith, Rohin Shah, Andrew Critch, Prasad Tadepalli

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback.

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

Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition.

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

Proceedings of the NeurIPS 2022 Competition Track, 2021

An Empirical Investigation of Representation Learning for Imitation.

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

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Learning What To Do by Simulating the Past.

David Lindner, Rohin Shah, Pieter Abbeel, Anca D. Dragan

Proceedings of the 9th International Conference on Learning Representations, 2021

Evaluating the Robustness of Collaborative Agents.

Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, Anca D. Dragan, Rohin Shah

Proceedings of the AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, 2021

2020

Extracting and Using Preference Information from the State of the World.

Rohin Shah

PhD thesis, 2020

The MAGICAL Benchmark for Robust Imitation.

Sam Toyer, Rohin Shah, Andrew Critch, Stuart Russell

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Choice Set Misspecification in Reward Inference.

Rachel Freedman, Rohin Shah, Anca D. Dragan

Proceedings of the Workshop on Artificial Intelligence Safety 2020 co-located with the 29th International Joint Conference on Artificial Intelligence and the 17th Pacific Rim International Conference on Artificial Intelligence (IJCAI-PRICAI 2020), 2020

2019

On the Utility of Learning about Humans for Human-AI Coordination.

Micah Carroll, Rohin Shah, Mark K. Ho, Tom Griffiths, Sanjit A. Seshia, Pieter Abbeel, Anca D. Dragan

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference.

Rohin Shah, Noah Gundotra, Pieter Abbeel, Anca D. Dragan

Proceedings of the 36th International Conference on Machine Learning, 2019

Preferences Implicit in the State of the World.

Rohin Shah, Dmitrii Krasheninnikov, Jordan Alexander, Pieter Abbeel, Anca D. Dragan

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Active Inverse Reward Design.

Sören Mindermann, Rohin Shah, Adam Gleave, Dylan Hadfield-Menell

CoRR, 2018

2016

SIMPL: A DSL for Automatic Specialization of Inference Algorithms.

Rohin Shah, Emina Torlak, Rastislav Bodík

CoRR, 2016

2014

Chlorophyll: synthesis-aided compiler for low-power spatial architectures.

Phitchaya Mangpo Phothilimthana, Tikhon Jelvis, Rohin Shah, Nishant Totla, Sarah E. Chasins, Rastislav Bodík

Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation, 2014