9 papers
Computer Use at the Edge of the Statistical Precipice
Pierluca D'Oro, Sneha Silwal, William Wong +6
Evaluating Computer Use Agents (CUAs) on interactive environments is fraught with methodological pitfalls that the field has yet to systematically address. We show that a 1MB repla…
Hierarchical Behaviour Spaces
Michael Tryfan Matthews, Anssi Kanervisto, Jakob Foerster +3
Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option reward functions. We show tha…
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons
Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin +3
When training neural networks, dying neurons -- units becoming inactive or saturated -- are traditionally seen as harmful. This paper sheds new light on this phenomenon. By explori…
DigiData: Training and Evaluating General-Purpose Mobile Control Agents
Yuxuan Sun, Manchen Wang, Shengyi Qian +18
AI agents capable of controlling user interfaces have the potential to transform human interaction with digital devices. To accelerate this transformation, two fundamental building…
Controlling Multimodal LLMs via Reward-guided Decoding
Oscar Mañas, Pierluca D'Oro, Koustuv Sinha +3
As Multimodal Large Language Models (MLLMs) gain widespread applicability, it is becoming increasingly desirable to adapt them for diverse user needs. In this paper, we study the a…
Mol-MoE: Training Preference-Guided Routers for Molecule Generation
Diego Calanzone, Pierluca D'Oro, Pierre-Luc Bacon
Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on single-objective reinforcement learning…