- Google DeepMind (United Kingdom)GB2 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR1 paper
- Czech Technical University in PragueCZ1 paper
- École Normale Supérieure de LyonFR1 paper
- École PolytechniqueFR1 paper
- École Polytechnique Fédérale de LausanneCH1 paper
- Hugging FaceUS1 paper
- ITERFR1 paper
- Laboratoire de Mathématiques d'OrsayFR1 paper
- Max Planck Institute for Plasma PhysicsDE1 paper
- Mohamed bin Zayed University of Artificial IntelligenceAE1 paper
- National Research University Higher School of EconomicsRU1 paper
3 papers
cs.AI2026
Synthetic Counteradaptation: A Principle of Human-AI Co-evolution
Ivar Frisch, Jackie Kay, Philip Moreira Tomei
In this paper, we introduce the concept of synthetic counteradaptation, a process where human and AI systems co-evolve by adapting to each other's strategies and behaviors. Synthet…
physics.plasm-ph2026
Applications of a novel model-based real-time observer for electron density profile control experiments in TCV
F. Pastore, O. Sauter, F. Felici +12
Real-time control of tokamak plasmas encompasses sustaining a high-performance stationary state, avoiding disruptions, and managing ramp-up and ramp-down phases. Real-time estimati…
stat.ML2026
Proximal Point Nash Learning from Human Feedback
Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5
Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…