Christian Schröder de Witt

Orcid: 0000-0003-4245-1179

According to our database1, Christian Schröder de Witt authored at least 83 papers between 2014 and 2026.

Collaborative distances:

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Fact-Checking With Contextual Narratives: Leveraging Retrieval-Augmented LLMs for Social Media Analysis.
IEEE Trans. Comput. Soc. Syst., June, 2026

Architecture Matters for Multi-Agent Security.
CoRR, April, 2026

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning.
CoRR, April, 2026

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability.
CoRR, April, 2026

OpenSanctions Pairs: Large-Scale Entity Matching with LLMs.
CoRR, March, 2026

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring.
CoRR, February, 2026

Towards Understanding Multimodal Fine-Tuning: Spatial Features.
CoRR, February, 2026

Delta-Influence: Identifying Poisons via Influence Functions.
Trans. Mach. Learn. Res., 2026

VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces.
Proceedings of the ACM Asia Conference on Computer and Communications Security, 2026

2025
Sensitivity Analysis for Climate Science with Generative Flow Models.
CoRR, November, 2025

DEEDEE: Fast and Scalable Out-of-Distribution Dynamics Detection.
CoRR, October, 2025

h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning.
CoRR, October, 2025

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations.
CoRR, September, 2025

Extending the OWASP Multi-Agentic System Threat Modeling Guide: Insights from Multi-Agent Security Research.
CoRR, August, 2025

Mitigating Goal Misgeneralization via Minimax Regret.
CoRR, July, 2025

Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents.
CoRR, May, 2025

REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites.
CoRR, April, 2025

AnnoCaseLaw: A Richly-Annotated Dataset For Benchmarking Explainable Legal Judgment Prediction.
CoRR, March, 2025

Fundamental Limitations in Defending LLM Finetuning APIs.
CoRR, February, 2025

Multi-Agent Risks from Advanced AI.
CoRR, February, 2025

PSyDUCK: Training-Free Steganography for Latent Diffusion.
CoRR, January, 2025

PSyDUCK: Hiding Information in the Denoising Process of Latent Diffusion Models.
Proceedings of the IEEE International Workshop on Information Forensics and Security, 2025

REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs.
Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

Mixture of Experts Made Intrinsically Interpretable.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Efficient Dictionary Learning with Switch Sparse Autoencoders.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems.
Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024
Foundational Challenges in Assuring Alignment and Safety of Large Language Models.
Trans. Mach. Learn. Res., 2024

MALT: Improving Reasoning with Multi-Agent LLM Training.
CoRR, 2024

Delta-Influence: Unlearning Poisons via Influence Functions.
CoRR, 2024

Comparative Global AI Regulation: Policy Perspectives from the EU, China, and the US.
CoRR, 2024

MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection.
CoRR, 2024

SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders.
CoRR, 2024

Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap.
CoRR, 2024

IDs for AI Systems.
CoRR, 2024

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits.
CoRR, 2024

Risks and Opportunities of Open-Source Generative AI.
CoRR, 2024

Near to Mid-term Risks and Opportunities of Open Source Generative AI.
CoRR, 2024

Secret Collusion Among Generative AI Agents.
CoRR, 2024

The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games.
CoRR, 2024

Computing Low-Entropy Couplings for Large-Support Distributions.
Proceedings of the Uncertainty in Artificial Intelligence, 2024

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Unelicitable Backdoors via Cryptographic Transformer Circuits.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Bayesian Exploration Networks.
Proceedings of the Forty-first International Conference on Machine Learning, 2024


Illusory Attacks: Information-theoretic detectability matters in adversarial attacks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Can reinforcement learning model learning across development? Online lifelong learning through adaptive intrinsic motivation.
Proceedings of the 46th Annual Meeting of the Cognitive Science Society, 2024


Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection.
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

2023
JaxMARL: Multi-Agent RL Environments in JAX.
CoRR, 2023

Perfectly Secure Steganography Using Minimum Entropy Coupling.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
Revealing Robust Oil and Gas Company Macro-Strategies using Deep Multi-Agent Reinforcement Learning.
CoRR, 2022

Illusionary Attacks on Sequential Decision Makers and Countermeasures.
CoRR, 2022

Biological Evolution and Genetic Algorithms: Exploring the Space of Abstract Tile Self-Assembly.
CoRR, 2022

(Private)-Retroactive Carbon Pricing [(P)ReCaP]: A Market-based Approach for Climate Finance and Risk Assessment.
CoRR, 2022

Equivariant Networks for Zero-Shot Coordination.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Discovered Policy Optimisation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Communicating via Markov Decision Processes.
Proceedings of the International Conference on Machine Learning, 2022

Generalized Beliefs for Cooperative AI.
Proceedings of the International Conference on Machine Learning, 2022

Model-Free Opponent Shaping.
Proceedings of the International Conference on Machine Learning, 2022

Mirror Learning: A Unifying Framework of Policy Optimisation.
Proceedings of the International Conference on Machine Learning, 2022

Amortized Rejection Sampling in Universal Probabilistic Programming.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS.
CoRR, 2021

Implicit Communication as Minimum Entropy Coupling.
CoRR, 2021

A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings.
CoRR, 2021

FACMAC: Factored Multi-Agent Centralised Policy Gradients.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

RainBench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
J. Mach. Learn. Res., 2020

RainBench: Towards Global Precipitation Forecasting from Satellite Imagery.
CoRR, 2020

Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?
CoRR, 2020

AI-QMIX: Attention and Imagination for Dynamic Multi-Agent Reinforcement Learning.
CoRR, 2020

Simulation-Based Inference for Global Health Decisions.
CoRR, 2020

Deep Multi-Agent Reinforcement Learning for Decentralized Continuous Cooperative Control.
CoRR, 2020

2019
Hijacking Malaria Simulators with Probabilistic Programming.
CoRR, 2019

Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem.
CoRR, 2019

Multi-Agent Common Knowledge Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

The StarCraft Multi-Agent Challenge.
Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019

2018
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
Proceedings of the 35th International Conference on Machine Learning, 2018

2014
The ZX calculus is incomplete for quantum mechanics.
Proceedings of the 11th workshop on Quantum Physics and Logic, 2014


  Loading...