https://aibrief.vivsla.com/stories/story-791f5a2edd53fcd8/ aibrief en 2026-10-18T08:57:03.282Z v0.32.0 https://aibrief.vivsla.com/stories/story-f4b4729087bccf06/ aibrief en 2026-10-18T08:57:03.282Z Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing https://aibrief.vivsla.com/stories/story-18b4cdedf7c78b12/ aibrief en 2026-10-17T20:19:50.993Z b11714 https://aibrief.vivsla.com/stories/story-19e43f49824eb872/ aibrief en 2026-10-17T20:19:50.993Z Knowledge That Is Linear Before Fine-Tuning Generalizes After It