Research

tinyboxes is a AI research lab that uses physical testbeds to study the behavior of AI systems and allow AI agents to interact with the physical world, learning from it. We actively publish research and are a team of researchers working on the intersection of AI and physics.

tinyboxes as a real-world physical testbed for AI methodology

Juan L. Gamella, Jonas Peters and Peter Bühlmann

Nature Machine Intelligence

Context is Key: A Benchmark for Forecasting with Essential Textual Information

Arjun Ashok, Andrew Robert Williams, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin

NeurIPS 2024 Workshop on Time Series in the Age of Large Models

An Asymptotically Optimal Coordinate Descent Algorithm for Learning Bayesian Networks from Gaussian Models

Tong Xu, Armeen Taeb, Simge Kuccukyavuz, Ali Shojaie

arXiv preprint arXiv:2408.11977

The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications

Philippe Brouillard, Chandler Squires, Jonas Wahl, Konrad P. Kording, Karen Sachs, Alexandre Drouin, Dhanya Sridhar

arXiv preprint arXiv:2412.01953

Sortability of Time Series Data

Christopher Lohse and Jonas Wahl

CI4TS Workshop @ UAI 2024

Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning

Yihong Gu, Cong Fang, Peter Bühlmann and Jianqing Fan

arXiv preprint arXiv:2405.04715

Addressing Misspecification in Simulation-based Inference through Data-driven Calibration

Antoine Wehenkel, Ozan Sener, Jens Behrmann, Guillermo Sapiro, Marco Cuturi and Jörn-Henrik Jacobsen

arXiv preprint arXiv:2405.08719

Invariant Subspace Decomposition

Margherita Lazzaretto, Jonas Peters, Niklas Pfister

arXiv preprint arXiv:2404.09962

Sanity Checking Causal Representation Learning on a Simple Real-World System

tinyboxes team, Simon Bing, Jakob Runge

arXiv preprint arXiv:2502.20099