Clarisse Wibault

Antiviral therapy design is myopic 🦠🙈 optimised only for the current strain. That's why you need a different Flu vaccine every year! Our #ICML2025 paper ADIOS proposes "shaper therapies" that steer viral evolution in our favour & remain effective. Work done @FLAIR_Ox 🧵👇

Theory of Mind (ToM) is crucial for next gen LLM Agents, yet current benchmarks suffer from multiple shortcomings. Enter 💽 Decrypto, an interactive benchmark for multi-agent reasoning and ToM in LLMs! Work done with @TimonWilli & @j_foerst at @AIatMeta & @FLAIR_Ox 🧵👇

Can an LLM be programmed? In our new preprint, we show that LLMs can learn to evaluate programs for a range of inputs by being trained on the program source code alone – a phenomenon we call Programming by Backprop (PBB). 🧵⬇️

How can we bypass the need for online hyper-parameter tuning in offline RL? @FLAIR_Ox is introducing two fully offline algorithms: SOReL, for accurate offline regret approximation, and TOReL, for offline hyper-parameter tuning! arxiv.org/html/2505.2244…