Adam Gleave - RankMe

51 papers A* 11B 1Journal 38

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution. CoRR Matthew Kowal, Goncalo Paulo, Louis Jaburi, Tom Tseng, Lev E. McKinney, Stefan Heimersheim, Aaron David Tucker, Adam Gleave, Kellin Pelrine
2026	J	`jnl`	Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks. CoRR Lukas Struppek, Adam Gleave, Kellin Pelrine
2026	J	`jnl`	Large language models can effectively convince people to believe conspiracies. CoRR Thomas Costello, Kellin Pelrine, Matthew Kowal, Antonio A. Arechar, Jean-François Godbout, Adam Gleave, David Rand, Gordon Pennycook
2026	A*	`conf`	STACK: Adversarial Attacks on LLM Safeguard Pipelines. AAAI Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Xander Davies, Stephen Casper, Aaron David Tucker, Robert Kirk, Adam Gleave
2026	J	`jnl`	The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes. CoRR Mohammad Taufeeque, Stefan Heimersheim, Adam Gleave, Chris Cundy
2025	J	`jnl`	AI Companies Should Report Pre- and Post-Mitigation Safety Evaluations. CoRR Dillon Bowen, Ann-Kathrin Dombrowski, Adam Gleave, Chris Cundy
2025	A*	`conf`	Can Go AIs Be Adversarially Robust? AAAI Tom Tseng, Euan McLean, Kellin Pelrine, Tony Tong Wang, Adam Gleave
2025	J	`jnl`	Interpreting learned search: finding a transition model and value function in an RNN that plays Sokoban. CoRR Mohammad Taufeeque, Aaron David Tucker, Adam Gleave, Adrià Garriga-Alonso
2025	J	`jnl`	It's the Thought that Counts: Evaluating the Attempts of Frontier LLMs to Persuade on Harmful Topics. CoRR Matthew Kowal, Jasper Timm, Jean-François Godbout, Thomas Costello, Antonio A. Arechar, Gordon Pennycook, David Rand, Adam Gleave, Kellin Pelrine
2025	A*	`conf`	Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility. EMNLP Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Tom Tseng, Julius Broomfield, Adam Gleave, Kellin Pelrine
2025	J	`jnl`	Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility. CoRR Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Julius Broomfield, Adam Gleave, Kellin Pelrine
2025	J	`jnl`	Multi-Agent Risks from Advanced AI. CoRR Lewis Hammond, Alan Chan, Jesse Clifton, Jason Hoelscher-Obermaier, Akbir Khan, Euan McLean, Chandler Smith, Wolfram Barfuss, Jakob N. Foerster, Tomas Gavenciak, The Anh Han, Edward Hughes, Vojtech Kovarík, Jan Kulveit, Joel Z. Leibo, Caspar Oesterheld, Christian Schröder de Witt, Nisarg Shah, Michael P. Wellman, Paolo Bova, Theodor Cimpeanu, Carson Ezell, Quentin Feuillade-Montixi, Matija Franklin, Esben Kran, Igor Krawczuk, Max Lamparth, Niklas Lauffer, Alexander Meinke, Sumeet Motwani, Anka Reuel, Vincent Conitzer, Michael Dennis, Iason Gabriel, Adam Gleave, Gillian K. Hadfield, Nika Haghtalab, Atoosa Kasirzadeh, Sébastien Krier, Kate Larson, Joel Lehman, David C. Parkes, Georgios Piliouras, Iyad Rahwan
2025	J	`jnl`	Preference Learning with Lie Detectors can Induce Honesty or Evasion. CoRR Chris Cundy, Adam Gleave
2025	J	`jnl`	STACK: Adversarial Attacks on LLM Safeguard Pipelines. CoRR Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Xander Davies, Stephen Casper, Aaron D. Tucker, Robert Kirk, Adam Gleave
2025	A*	`conf`	Scaling Trends for Data Poisoning in LLMs. AAAI Dillon Bowen, Brendan Murphy, Will Cai, David Khachaturov, Adam Gleave, Kellin Pelrine
2025	A*	`conf`	Scaling Trends in Language Model Robustness. ICML Nikolaus H. R. Howe, Ian R. McKenzie, Oskar John Hollinsworth, Michal Zajac, Tom Tseng, Aaron David Tucker, Pierre-Luc Bacon, Adam Gleave
2025	J	`jnl`	The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models. CoRR Ann-Kathrin Dombrowski, Dillon Bowen, Adam Gleave, Chris Cundy
2025	J	`jnl`	The Singapore Consensus on Global AI Safety Research Priorities. CoRR Yoshua Bengio, Tegan Maharaj, Luke Ong, Stuart Russell, Dawn Song, Max Tegmark, Lan Xue, Ya-Qin Zhang, Stephen Casper, Wan Sie Lee, Sören Mindermann, Vanessa Wilfred, Vidhisha Balachandran, Fazl Barez, Michael Belinsky, Imane Bello, Malo Bourgon, Mark Brakel, Siméon Campos, Duncan Cass-Beggs, Jiahao Chen, Rumman Chowdhury, Kuan Chua Seah, Jeff Clune, Juntao Dai, Agnès Delaborde, Nouha Dziri, Francisco Eiras, Joshua Engels, Jinyu Fan, Adam Gleave, Noah Goodman, Fynn Heide, Johannes Heidecke, Dan Hendrycks, Cyrus Hodes, Bryan Low Kian Hsiang, Minlie Huang, Sami Jawhar, Wang Jingyu, Adam Tauman Kalai, Meindert Kamphuis, Mohan S. Kankanhalli, Subhash Kantamneni, Mathias Bonde Kirk, Thomas Kwa, Jeffrey Ladish, Kwok-Yan Lam, Wan Lee Sie, Taewhi Lee, Xiaojian Li, Jiajun Liu, Chaochao Lu, Yifan Mai, Richard Mallah, Julian Michael, Nick Moës, Simon Möller, Kihyuk Nam, Kwan Yee Ng, Mark Nitzberg, Besmira Nushi, Seán Ó hÉigeartaigh, Alejandro Ortega, Pierre Peigné, James Petrie, Benjamin Prud'homme, Reihaneh Rabbany, Nayat Sánchez-Pi, Sarah Schwettmann, Buck Shlegeris, Saad Siddiqui, Aradhana Sinha, Martín Soto, Cheston Tan, Dong Ting, William-Chandra Tjhi, Robert Trager, Brian Tse, Anthony Tung K. H., John Willes, Denise Wong, Wei Xu, Rongwu Xu, Yi Zeng, HongJiang Zhang, Djordje Zikelic
2024	J	`jnl`	Can Go AIs be adversarially robust? CoRR Tom Tseng, Euan McLean, Kellin Pelrine, Tony T. Wang, Adam Gleave
2024	J	`jnl`	Exploring Scaling Trends in LLM Robustness. CoRR Nikolaus H. R. Howe, Michal Zajac, Ian R. McKenzie, Oskar John Hollinsworth, Tom Tseng, Pierre-Luc Bacon, Adam Gleave
2024	J	`jnl`	Planning behavior in a recurrent neural network that plays Sokoban. CoRR Adrià Garriga-Alonso, Mohammad Taufeeque, Adam Gleave
2024	A*	`conf`	STARC: A General Framework For Quantifying Differences Between Reward Functions. ICLR Joar Max Viktor Skalse, Lucy Farnik, Sumeet Ramesh Motwani, Erik Jenner, Adam Gleave, Alessandro Abate
2024	J	`jnl`	Scaling Laws for Data Poisoning in LLMs. CoRR Dillon Bowen, Brendan Murphy, Will Cai, David Khachaturov, Adam Gleave, Kellin Pelrine
2024	J	`jnl`	Uncovering Latent Human Wellbeing in Language Model Embeddings. CoRR Pedro Freire, ChengCheng Tan, Adam Gleave, Dan Hendrycks, Scott Emmons
2023	A*	`conf`	Adversarial Policies Beat Superhuman Go AIs. ICML Tony Tong Wang, Adam Gleave, Tom Tseng, Kellin Pelrine, Nora Belrose, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell
2023	J	`jnl`	Exploiting Novel GPT-4 APIs. CoRR Kellin Pelrine, Mohammad Taufeeque, Michal Zajac, Euan McLean, Adam Gleave
2023	A*	`conf`	Invariance in Policy Optimisation and Partial Identifiability in Reward Learning. ICML Joar Max Viktor Skalse, Matthew Farrugia-Roberts, Stuart Russell, Alessandro Abate, Adam Gleave
2023	J	`jnl`	On The Fragility of Learned Reward Functions. CoRR Lev McKinney, Yawen Duan, David Krueger, Adam Gleave
2023	J	`jnl`	STARC: A General Framework For Quantifying Differences Between Reward Functions. CoRR Joar Skalse, Lucy Farnik, Sumeet Ramesh Motwani, Erik Jenner, Adam Gleave, Alessandro Abate
2022	J	`jnl`	A Primer on Maximum Causal Entropy Inverse Reinforcement Learning. CoRR Adam Gleave, Sam Toyer
2022	J	`jnl`	Adversarial Policies Beat Professional-Level Go AIs. CoRR Tony Tong Wang, Adam Gleave, Nora Belrose, Tom Tseng, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell
2022	J	`jnl`	Calculus on MDPs: Potential Shaping as a Gradient. CoRR Erik Jenner, Herke van Hoof, Adam Gleave
2022	J	`jnl`	Invariance in Policy Optimisation and Partial Identifiability in Reward Learning. CoRR Joar Skalse, Matthew Farrugia-Roberts, Stuart Russell, Alessandro Abate, Adam Gleave
2022	J	`jnl`	Preprocessing Reward Functions for Interpretability. CoRR Erik Jenner, Adam Gleave
2022	J	`jnl`	Reducing Exploitability with Population Based Training. CoRR Pavel Czempin, Adam Gleave
2022	—	`—`	Towards Trustworthy Machine Learning Adam Gleave
2022	J	`jnl`	Uncertainty Estimation for Language Reward Models. CoRR Adam Gleave, Geoffrey Irving
2022	J	`jnl`	imitation: Clean Imitation Learning Implementations. CoRR Adam Gleave, Mohammad Taufeeque, Juan Rocamonde, Erik Jenner, Steven H. Wang, Sam Toyer, Maximilian Ernestus, Nora Belrose, Scott Emmons, Stuart Russell
2021	A*	`conf`	Quantifying Differences in Reward Functions. ICLR Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike
2021	J	`jnl`	Stable-Baselines3: Reliable Reinforcement Learning Implementations. J. Mach. Learn. Res. Antonin Raffin, Ashley Hill, Adam Gleave, Anssi Kanervisto, Maximilian Ernestus, Noah Dormann
2020	A*	`conf`	Adversarial Policies: Attacking Deep Reinforcement Learning. ICLR Adam Gleave, Michael Dennis, Cody Wild, Neel Kant, Sergey Levine, Stuart Russell
2020	J	`jnl`	DERAIL: Diagnostic Environments for Reward And Imitation Learning. CoRR Pedro Freire, Adam Gleave, Sam Toyer, Stuart Russell
2020	J	`jnl`	Quantifying Differences in Reward Functions. CoRR Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike
2020	J	`jnl`	Understanding Learned Reward Functions. CoRR Eric J. Michaud, Adam Gleave, Stuart Russell
2019	J	`jnl`	Adversarial Policies: Attacking Deep Reinforcement Learning. CoRR Adam Gleave, Michael Dennis, Neel Kant, Cody Wild, Sergey Levine, Stuart Russell
2018	J	`jnl`	Active Inverse Reward Design. CoRR Sören Mindermann, Rohin Shah, Adam Gleave, Dylan Hadfield-Menell
2018	J	`jnl`	Inverse reinforcement learning for video games. CoRR Aaron Tucker, Adam Gleave, Stuart Russell
2018	J	`jnl`	Multi-task Maximum Entropy Inverse Reinforcement Learning. CoRR Adam Gleave, Oliver Habryka
2017	B	`conf`	Making Compression Algorithms for Unicode Text. DCC Adam Gleave, Christian Steinruecken
2017	J	`jnl`	Making compression algorithms for Unicode text. CoRR Adam Gleave, Christian Steinruecken
2016	A*	`conf`	Firmament: Fast, Centralized Cluster Scheduling at Scale. OSDI Ionel Gog, Malte Schwarzkopf, Adam Gleave, Robert N. M. Watson, Steven Hand