Choosing the Trainable Geometry for Agentic RL https://www.trajectory.ai/field-notes/choosing-the-trainable-geometry-for-agentic-rl
Just links
That's just link aggregator of everything I consider interesting, especially DL and topological condensed matter physics. @EvgeniyZh
Динамика подписчиков
с 20 июля 2026 по 28 сентября 2026 · минимум 6 830 · максимум 6 910
Кто рекламировался за полгода
Рекламных размещений с маркировкой не найдено.
Публикации
https://fixupx.com/qingyu_shi_/status/2100181567666901052
https://github.com/rust-lang/rust/pull/156216 If you wanted to do for loop in const in Rust now you can (in nightly)
Dream-RSI: Recursive Self-Improvement through Evolving Worlds https://arxiv.org/abs/2609.14858
https://fixupx.com/creus_roger/status/2100080651214971017
Nature Is Our Learning Environment https://periodic.com/news/nature-is-our-learning-environment
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble https://arxiv.org/abs/2609.10883
CheatBench: Measuring Reward Gaming in AI Agents https://www.cheatbench.ai/
https://fixupx.com/jsuarez/status/2099512196304925161
https://fixupx.com/jsuarez/status/2099512196304925161