StructRL turns reinforcement-learning experience into an explicit replay graph. Once the g…
This adversarial machine learning position paper argues that the ε-ball, defined through ℓ…
This work presents an asynchronous federated learning platform for grading lung adenocarci…
Zugwise reframes handwritten chess digitization as global game reconstruction rather than …
CAFIN targets the GPU execution overhead of the AdaFisher optimizer by progressively fusin…
Ropedia has introduced Ropedia Xperience 2, a physical-AI dataset comprising 1,589 release…
NAVER AI introduces FOAM, a lightweight second-order optimizer designed to retain the conv…
UniSpark-9B is a unified multimodal model built on a Mixture-of-Transformer-Experts backbo…
WorldDraft reframes video generation models as generative renderers for 4D worlds construc…
PhysLoop introduces a physics-aware self-improvement harness for video generation models. …
This work converts a large language model into a fast “System One” decision model through …