A machine learning project demonstrating Deep Counterfactual Regret Minimization (Deep CFR) applied to the card game Hearts, training a superhuman-level AI by using neural networks to approximate game strategy tables for imperfect information games with large game trees.
A philosophical essay arguing that complex systems (like climate, economics, and human language) require billion-parameter AI models as theories because their true compression ratio is simply very large, unlike the elegantly compact theories that worked for complicated systems. The author contends that modern deep learning finally provides the tools to operationalize theories of complex phenomena that were previously beyond reach.
LoGeR is a novel deep learning architecture from DeepMind and UC Berkeley for 3D geometric reconstruction from extremely long videos (up to 19,000 frames) using a hybrid memory module that combines Sliding Window Attention for local precision with Test-Time Training for global consistency, achieving state-of-the-art results on KITTI, 7-Scenes, and long-sequence benchmarks while maintaining sub-quadratic complexity.