Christian Schröder de Witt

79 papers A* 17A 4Journal 56Unranked 2

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction. CoRR Magnus Sesodia, Alina Petrova, John Armour, Thomas Lukasiewicz, Oana-Maria Camburu, Puneet K. Dokania, Philip Torr, Christian Schröder de Witt
2025	J	`jnl`	Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations. CoRR Ron F. Del Rosario, Klaudia Krawiecka, Christian Schröder de Witt
2025	J	`jnl`	DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection. CoRR Tala Aljaafari, Varun Kanade, Philip Torr, Christian Schröder de Witt
2025	A*	`conf`	Efficient Dictionary Learning with Switch Sparse Autoencoders. ICLR Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schröder de Witt
2025	J	`jnl`	Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research. CoRR Klaudia Krawiecka, Christian Schröder de Witt
2025	J	`jnl`	Fact-Checking with Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis. CoRR Arka Ujjal Dey, Muhammad Junaid Awan, Georgia Channing, Christian Schröder de Witt, John P. Collomosse
2025	J	`jnl`	Fundamental Limitations in Defending LLM Finetuning APIs. CoRR Xander Davies, Eric Winsor, Tomek Korbak, Alexandra Souly, Robert Kirk, Christian Schröder de Witt, Yarin Gal
2025	—	`conf`	Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs. IJCNLP-AACL (long papers) Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schröder de Witt, Dylan Cope, Nandi Schoots
2025	A*	`conf`	Mixture of Experts Made Intrinsically Interpretable. ICML Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
2025	J	`jnl`	Mixture of Experts Made Intrinsically Interpretable. CoRR Xingyi Yang, Constantin Venhoff, Ashkan Khakzar, Christian Schröder de Witt, Puneet K. Dokania, Adel Bibi, Philip Torr
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	A*	`conf`	Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems. AAAI Pierre Peigné, Mikolaj Kniejski, Filip Sondej, Matthieu David, Jason Hoelscher-Obermaier, Christian Schröder de Witt, Esben Kran
2025	J	`jnl`	Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems. CoRR Pierre Peigné, Mikolaj Kniejski, Filip Sondej, Matthieu David, Jason Hoelscher-Obermaier, Christian Schröder de Witt, Esben Kran
2025	J	`jnl`	Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents. CoRR Christian Schröder de Witt
2025	J	`jnl`	PSyDUCK: Training-Free Steganography for Latent Diffusion. CoRR Georgia Channing, Aqib Mahfuz, Mark van der Wilk, Philip Torr, Fabio Pizzati, Christian Schröder de Witt
2025	J	`jnl`	Sensitivity Analysis for Climate Science with Generative Flow Models. CoRR Alex Dobra, Jakiw Pidstrigach, Tim Reichelt, Christian Schröder de Witt, Philip Torr, Philip Stier
2025	J	`jnl`	h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning. CoRR Sumeet Ramesh Motwani, Alesia Ivanova, Ziyang Cai, Philip Torr, Riashat Islam, Shital Shah, Christian Schröder de Witt, Charles London
2024	A*	`conf`	Bayesian Exploration Networks. ICML Mattie Fellows, Brandon Kaplowitz, Christian Schröder de Witt, Shimon Whiteson
2024	J	`jnl`	Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US. CoRR Jon Chun, Christian Schröder de Witt, Katherine Elkins
2024	A	`conf`	Computing Low-Entropy Couplings for Large-Support Distributions. UAI Samuel Sokota, Dylan Sam, Christian Schröder de Witt, Spencer Compton, Jakob N. Foerster, J. Zico Kolter
2024	J	`jnl`	Computing Low-Entropy Couplings for Large-Support Distributions. CoRR Samuel Sokota, Dylan Sam, Christian Schröder de Witt, Spencer Compton, Jakob N. Foerster, J. Zico Kolter
2024	J	`jnl`	Delta-Influence: Unlearning Poisons via Influence Functions. CoRR Wenjie Li, Jiawei Li, Christian Schröder de Witt, Ameya Prabhu, Amartya Sanyal
2024	J	`jnl`	Efficient Dictionary Learning with Switch Sparse Autoencoders. CoRR Anish Mudide, Joshua Engels, Eric J. Michaud, Max Tegmark, Christian Schröder de Witt
2024	J	`jnl`	Foundational Challenges in Assuring Alignment and Safety of Large Language Models. Trans. Mach. Learn. Res. Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, Benjamin L. Edelman, Zhaowei Zhang, Mario Günther, Anton Korinek, José Hernández-Orallo, Lewis Hammond, Eric J. Bigelow, Alexander Pan, Lauro Langosco, Tomasz Korbak, Heidi Chenyu Zhang, Ruiqi Zhong, Seán Ó hÉigeartaigh, Gabriel Recchia, Giulio Corsi, Alan Chan, Markus Anderljung, Lilian Edwards, Aleksandar Petrov, Christian Schröder de Witt, Sumeet Ramesh Motwani, Yoshua Bengio, Danqi Chen, Philip Torr, Samuel Albanie, Tegan Maharaj, Jakob Nicolaus Foerster, Florian Tramèr, He He, Atoosa Kasirzadeh, Yejin Choi, David Krueger
2024	J	`jnl`	Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs. CoRR Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schröder de Witt, Dylan Cope, Nandi Schoots
2024	J	`jnl`	IDs for AI Systems. CoRR Alan Chan, Noam Kolt, Peter Wills, Usman Anwar, Christian Schröder de Witt, Nitarshan Rajkumar, Lewis Hammond, David Krueger, Lennart Heim, Markus Anderljung
2024	A*	`conf`	Illusory Attacks: Information-theoretic detectability matters in adversarial attacks. ICLR Tim Franzmeyer, Stephen Marcus McAleer, João F. Henriques, Jakob Nicolaus Foerster, Philip Torr, Adel Bibi, Christian Schröder de Witt
2024	A	`conf`	JaxMARL: Multi-Agent RL Environments and Algorithms in JAX. AAMAS Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Garðar Ingvarsson, Timon Willi, Akbir Khan, Christian Schröder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert T. Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktäschel, Chris Lu, Jakob N. Foerster
2024	A*	`conf`	JaxMARL: Multi-Agent RL Environments and Algorithms in JAX. NeurIPS Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Garðar Ingvarsson, Timon Willi, Ravi Hammond, Akbir Khan, Christian Schröder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert T. Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktäschel, Chris Lu, Jakob N. Foerster
2024	J	`jnl`	MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection. CoRR Kumud Lakara, Juil Sock, Christian Rupprecht, Philip Torr, John P. Collomosse, Christian Schröder de Witt
2024	J	`jnl`	MALT: Improving Reasoning with Multi-Agent LLM Training. CoRR Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das, Markian Rybchuk, Philip H. S. Torr, Ivan Laptev, Fabio Pizzati, Ronald Clark, Christian Schröder de Witt
2024	J	`jnl`	Near to Mid-term Risks and Opportunities of Open Source Generative AI. CoRR Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Thomas Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster
2024	A*	`conf`	Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI. ICML Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Botos Csaba, Fabro Steibel, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan A. Nolazco-Flores, Lori Landay, Matthew Thomas Jackson, Paul Röttger, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster
2024	A	`conf`	Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection. AAMAS Linas Nasvytis, Kai Sandbrink, Jakob N. Foerster, Tim Franzmeyer, Christian Schröder de Witt
2024	J	`jnl`	Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection. CoRR Linas Nasvytis, Kai Sandbrink, Jakob N. Foerster, Tim Franzmeyer, Christian Schröder de Witt
2024	J	`jnl`	Risks and Opportunities of Open-Source Generative AI. CoRR Francisco Eiras, Aleksandar Petrov, Bertie Vidgen, Christian Schröder de Witt, Fabio Pizzati, Katherine Elkins, Supratik Mukhopadhyay, Adel Bibi, Aaron Purewal, Botos Csaba, Fabro Steibel, Fazel Keshtkar, Fazl Barez, Genevieve Smith, Gianluca Guadagni, Jon Chun, Jordi Cabot, Joseph Marvin Imperial, Juan Arturo Nolazco, Lori Landay, Matthew Thomas Jackson, Philip H. S. Torr, Trevor Darrell, Yong Suk Lee, Jakob N. Foerster
2024	J	`jnl`	SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders. CoRR Constantin Venhoff, Anisoara Calinescu, Philip Torr, Christian Schröder de Witt
2024	J	`jnl`	Secret Collusion Among Generative AI Agents. CoRR Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H. S. Torr, Lewis Hammond, Christian Schröder de Witt
2024	A*	`conf`	Secret Collusion among AI Agents: Multi-Agent Deception via Steganography. NeurIPS Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip Torr, Lewis Hammond, Christian Schröder de Witt
2024	J	`jnl`	The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games. CoRR Jake Levi, Chris Lu, Timon Willi, Christian Schröder de Witt, Jakob N. Foerster
2024	J	`jnl`	Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap. CoRR Georgia Channing, Juil Sock, Ronald Clark, Philip Torr, Christian Schröder de Witt
2024	J	`jnl`	Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits. CoRR Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani, Charlie Rogers-Smith, Jeffrey Ladish, Christian Schröder de Witt
2024	A*	`conf`	Unelicitable Backdoors via Cryptographic Transformer Circuits. NeurIPS Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani, Christian Schröder de Witt
2023	J	`jnl`	Bayesian Exploration Networks. CoRR Mattie Fellows, Brandon Kaplowitz, Christian Schröder de Witt, Shimon Whiteson
2023	A*	`conf`	Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning. ICLR Yat Long Lo, Christian Schröder de Witt, Samuel Sokota, Jakob Nicolaus Foerster, Shimon Whiteson
2023	J	`jnl`	Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning. CoRR Yat Long Lo, Christian Schröder de Witt, Samuel Sokota, Jakob Nicolaus Foerster, Shimon Whiteson
2023	J	`jnl`	JaxMARL: Multi-Agent RL Environments in JAX. CoRR Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Garðar Ingvarsson, Timon Willi, Akbir Khan, Christian Schröder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktäschel, Chris Lu, Jakob Nicolaus Foerster
2023	A*	`conf`	Perfectly Secure Steganography Using Minimum Entropy Coupling. ICLR Christian Schröder de Witt, Samuel Sokota, J. Zico Kolter, Jakob Nicolaus Foerster, Martin Strohmeier
2022	J	`jnl`	(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment. CoRR Yoshua Bengio, Prateek Gupta, Dylan R. Radovic, Maarten Scholl, Andrew Williams, Christian Schröder de Witt, Tianyu Zhang, Yang Zhang
2022	J	`jnl`	Biological Evolution and Genetic Algorithms: Exploring the Space of Abstract Tile Self-Assembly. CoRR Christian Schröder de Witt
2022	A*	`conf`	Discovered Policy Optimisation. NeurIPS Chris Lu, Jakub Grudzien Kuba, Alistair Letcher, Luke Metz, Christian Schröder de Witt, Jakob N. Foerster
2022	J	`jnl`	Discovered Policy Optimisation. CoRR Chris Lu, Jakub Grudzien Kuba, Alistair Letcher, Luke Metz, Christian Schröder de Witt, Jakob N. Foerster
2022	A*	`conf`	Equivariant Networks for Zero-Shot Coordination. NeurIPS Darius Muglich, Christian Schröder de Witt, Elise van der Pol, Shimon Whiteson, Jakob N. Foerster
2022	J	`jnl`	Equivariant Networks for Zero-Shot Coordination. CoRR Darius Muglich, Christian Schröder de Witt, Elise van der Pol, Shimon Whiteson, Jakob N. Foerster
2022	J	`jnl`	Generalized Beliefs for Cooperative AI. CoRR Darius Muglich, Luisa M. Zintgraf, Christian Schröder de Witt, Shimon Whiteson, Jakob N. Foerster
2022	J	`jnl`	Illusionary Attacks on Sequential Decision Makers and Countermeasures. CoRR Tim Franzmeyer, João F. Henriques, Jakob N. Foerster, Philip H. S. Torr, Adel Bibi, Christian Schröder de Witt
2022	J	`jnl`	Mirror Learning: A Unifying Framework of Policy Optimisation. CoRR Jakub Grudzien Kuba, Christian Schröder de Witt, Jakob N. Foerster
2022	J	`jnl`	Model-Free Opponent Shaping. CoRR Christopher Lu, Timon Willi, Christian Schröder de Witt, Jakob N. Foerster
2022	J	`jnl`	Perfectly Secure Steganography Using Minimum Entropy Coupling. CoRR Christian Schröder de Witt, Samuel Sokota, J. Zico Kolter, Jakob N. Foerster, Martin Strohmeier
2022	J	`jnl`	Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning. CoRR Dylan R. Radovic, Lucas Kruitwagen, Christian Schröder de Witt, Ben Caldecott, Shane Tomlinson, Mark Workman
2021	A*	`conf`	FACMAC: Factored Multi-Agent Centralised Policy Gradients. NeurIPS Bei Peng, Tabish Rashid, Christian Schröder de Witt, Pierre-Alexandre Kamienny, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson
2021	J	`jnl`	Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS. CoRR Christian Schröder de Witt, Yongchao Huang, Philip H. S. Torr, Martin Strohmeier
2021	J	`jnl`	Implicit Communication as Minimum Entropy Coupling. CoRR Samuel Sokota, Christian Schröder de Witt, Maximilian Igl, Luisa M. Zintgraf, Philip H. S. Torr, Shimon Whiteson, Jakob N. Foerster
2021	A*	`conf`	RainBench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery. AAAI Christian Schröder de Witt, Catherine Tong, Valentina Zantedeschi, Daniele De Martini, Alfredo Kalaitzis, Matthew Chantry, Duncan Watson-Parris, Piotr Bilinski
2020	J	`jnl`	Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control. CoRR Christian Schröder de Witt, Bei Peng, Pierre-Alexandre Kamienny, Philip H. S. Torr, Wendelin Böhmer, Shimon Whiteson
2020	J	`jnl`	Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? CoRR Christian Schröder de Witt, Tarun Gupta, Denys Makoviichuk, Viktor Makoviychuk, Philip H. S. Torr, Mingfei Sun, Shimon Whiteson
2020	J	`jnl`	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. CoRR Tabish Rashid, Mikayel Samvelyan, Christian Schröder de Witt, Gregory Farquhar, Jakob N. Foerster, Shimon Whiteson
2020	J	`jnl`	Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. J. Mach. Learn. Res. Tabish Rashid, Mikayel Samvelyan, Christian Schröder de Witt, Gregory Farquhar, Jakob N. Foerster, Shimon Whiteson
2020	J	`jnl`	RainBench: Towards Global Precipitation Forecasting from Satellite Imagery. CoRR Christian Schröder de Witt, Catherine Tong, Valentina Zantedeschi, Daniele De Martini, Freddie Kalaitzis, Matthew Chantry, Duncan Watson-Parris, Piotr Bilinski
2020	J	`jnl`	Simulation-Based Inference for Global Health Decisions. CoRR Christian Schröder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Robert Zinkov, Puneet K. Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip H. S. Torr, Atilim Günes Baydin
2019	J	`jnl`	Amortized Rejection Sampling in Universal Probabilistic Programming. CoRR Saeid Naderiparizi, Adam Scibior, Andreas Munk, Mehrdad Ghadiri, Atilim Günes Baydin, Bradley Gram-Hansen, Christian Schröder de Witt, Robert Zinkov, Philip H. S. Torr, Tom Rainforth, Yee Whye Teh, Frank Wood
2019	J	`jnl`	Hijacking Malaria Simulators with Probabilistic Programming. CoRR Bradley Gram-Hansen, Christian Schröder de Witt, Tom Rainforth, Philip H. S. Torr, Yee Whye Teh, Atilim Günes Baydin
2019	A*	`conf`	Multi-Agent Common Knowledge Reinforcement Learning. NeurIPS Christian Schröder de Witt, Jakob N. Foerster, Gregory Farquhar, Philip H. S. Torr, Wendelin Boehmer, Shimon Whiteson
2019	J	`jnl`	Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem. CoRR Christian Schröder de Witt, Thomas Hornigold
2019	A	`conf`	The StarCraft Multi-Agent Challenge. AAMAS Mikayel Samvelyan, Tabish Rashid, Christian Schröder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob N. Foerster, Shimon Whiteson
2019	J	`jnl`	The StarCraft Multi-Agent Challenge. CoRR Mikayel Samvelyan, Tabish Rashid, Christian Schröder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob N. Foerster, Shimon Whiteson
2018	A*	`conf`	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. ICML Tabish Rashid, Mikayel Samvelyan, Christian Schröder de Witt, Gregory Farquhar, Jakob N. Foerster, Shimon Whiteson
2018	J	`jnl`	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. CoRR Tabish Rashid, Mikayel Samvelyan, Christian Schröder de Witt, Gregory Farquhar, Jakob N. Foerster, Shimon Whiteson
2014	—	`conf`	The ZX calculus is incomplete for quantum mechanics. QPL Christian Schröder de Witt, Vladimir Zamdzhiev