Skip to content
conftrace_

Christian Schroeder de Witt

19 papers · 2019–2025 · 7 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+10 more ↓ πŸ—ΊοΈ Taxonomy Completionist (39) 🌍 Conference Polyglot Β· Silver πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Silver 🐣 Hot Topic Early Bird
πŸ† Grand Slam 🧬 Topic Evolution πŸ‘‘ Triple Crown πŸ‘₯ Mega-Team Β· Squad ⚑ Prolific Year Β· Productive πŸ”₯ Unstoppable Β· Bronze πŸ’Ž Century Club Β· Bronze 🌈 Renaissance Researcher (5) πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (93)

Venues

NeurIPS (7) ICLR (4) ICML (3) AAAI (2) IJCNLP (1) JMLR (1) UAI (1)

Top co-authors

Shimon Whiteson (7) Jakob Foerster (6) Philip Torr (5) Jakob Nicolaus Foerster (4) Samuel Sokota (3) Adel Bibi (3) Gregory Farquhar (2) Mikayel Samvelyan (2) Chris Lu (2) Sumeet Ramesh Motwani (2)

Research topics

Artificial Intelligence (14) Core AI (13) Machine Learning (9) Reinforcement Learning (9) Methods (8) Deep Learning (6) Optimization & Theory Β· Machine Learning (4) Applications (3) Learning Types Β· Machine Learning (3) Learning Types Β· Deep Learning (3) Mathematics & Optimization (2) Natural Language Processing (2) Optimization & Theory Β· Deep Learning (2) Computer Vision (1) Application Areas (1)

Keywords

multi-agent reinforcement learning (5) large language model (4) multi-agent system (4) reinforcement learning (3) minimum entropy coupling (2) ai safety (2) language model (2) decentralized policy (2) adversarial learning (2) information theory (2) policy optimization (1) sequential decision making (1) multimodal learning (1) deep learning (1) interpretability (1) model security (1) epistemic uncertainty (1) adversarial attack (1) bayesian reinforcement learning (1) backdoor attack (1)

Papers

Efficient Dictionary Learning with Switch Sparse Autoencoders ICLR 2025 Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs IJCNLP 2025 Mixture of Experts Made Intrinsically Interpretable ICML 2025 Multi-Agent Security Tax: Trading Off Security and Collaboration Capabilities in Multi-Agent Systems AAAI 2025 Bayesian Exploration Networks ICML 2024 Computing Low-Entropy Couplings for Large-Support Distributions UAI 2024 Illusory Attacks: Information-theoretic detectability matters in adversarial attacks ICLR 2024 JaxMARL: Multi-Agent RL Environments and Algorithms in JAX NeurIPS 2024 Position: Near to Mid-term Risks and Opportunities of Open-Source Generative AI ICML 2024 Secret Collusion among AI Agents: Multi-Agent Deception via Steganography NeurIPS 2024 Unelicitable Backdoors via Cryptographic Transformer Circuits NeurIPS 2024 Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning ICLR 2023 Perfectly Secure Steganography Using Minimum Entropy Coupling ICLR 2023 Discovered Policy Optimisation NeurIPS 2022 Equivariant Networks for Zero-Shot Coordination NeurIPS 2022 FACMAC: Factored Multi-Agent Centralised Policy Gradients NeurIPS 2021 RainBench: Towards Data-Driven Global Precipitation Forecasting from Satellite Imagery AAAI 2021 Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning JMLR 2020 Multi-Agent Common Knowledge Reinforcement Learning NeurIPS 2019