AI Shorts

Can a single AI stack plan like a researcher, cause over scenes, and switch motions throughout totally different robots—with out retraining from scratch? Google DeepMind’s Gemini Robotics 1.5 says sure, by splitting embodied intelligence into two fashions: Gemini Robotics-ER 1.5 for high-level embodied reasoning (spatial understanding, planning, progress/success estimation, tool-use) and Gemini Robotics 1.5 for…

Meta FAIR launched Code World Model (CWM), a 32-billion-parameter dense decoder-only LLM that injects world modeling into code era by coaching on execution traces and long-horizon agent–atmosphere interactions—not simply static supply textual content. What’s new: studying code by predicting execution? CWM mid-trains on two giant households of remark–motion trajectories: (1) Python interpreter traces that document…

Table of contents What pain point in forecasting is being eliminated? How does in-context fine-tuning work under the hood? What exactly is “few-shot” here? Does it actually match supervised fine-tuning? How is this different from Chronos-style approaches? What are the architectural specifics to watch? Summary FAQs Google Research introduces in-context fine-tuning (ICF) for time-series forecasting…

Can a 8B-parameter language mannequin produce provably legitimate multi-step plans as an alternative of believable guesses? MIT CSAIL researchers introduce PDDL-INSTRUCT, an instruction-tuning framework that {couples} logical chain-of-thought with exterior plan validation (VAL) to carry symbolic planning efficiency of LLMs. On PlanBench, a tuned Llama-3-8B reaches 94% legitimate plans on Blocksworld, with massive jumps on…

Meta researchers launched a technique that compresses repeated reasoning patterns into quick, named procedures—“behaviors”—after which circumstances fashions to make use of them at inference or distills them by way of fine-tuning. The end result: as much as 46% fewer reasoning tokens on MATH whereas matching or bettering accuracy, and as much as 10% accuracy positive…