ロボティクス

MN·

ニュースMIT News · Robotics·2026/09/29

Powered by muscle cells, a paper-thin robot swims through watery maze

MIT engineers’ new aquabot offers a way to design small, efficient “biohybrid” robots.

NMI

論文Nature Machine Intelligence·2026/10/01

Shifting from knowledge retrieval to evidence exploration and synthesis

Nature Machine Intelligence, Published online: 01 October 2026; doi:10.1038/s42256-026-01313-w Biomedical discovery has entered an era in which the limiting resource is no longer data, but our ability to integrate and interpret evidence. DeepEvidence, a new deep research agent, goes beyond retrieving facts and constructs explicit representations of scientific evidence.

NMI

論文Nature Machine Intelligence·2026/10/01

Large language models discover complementary heuristics for combinatorial optimization

Nature Machine Intelligence, Published online: 01 October 2026; doi:10.1038/s42256-026-01307-8 Huatian Gong and colleagues developed LACE, a large language model-based framework that designs optimization algorithms. It builds a verified problem contract, then evolves a portfolio of complementary heuristics that together solve problems that no single method can handle.

NMI

論文Nature Machine Intelligence·2026/09/30

Towards foundation-style models for energy-frontier heterogeneous neutrino detectors via self-supervised pretraining

Nature Machine Intelligence, Published online: 30 September 2026; doi:10.1038/s42256-026-01309-6 Alonso-Monsalve et al. demonstrate that self-supervised pretraining helps deep learning models to interpret complex neutrino detector events, improving classification, reconstruction and data efficiency while enabling transfer across different neutrino detector technologies.

NMI

論文Nature Machine Intelligence·2026/09/28

Minute-scale training for microrobot navigation

Nature Machine Intelligence, Published online: 28 September 2026; doi:10.1038/s42256-026-01305-w A vectorized simulator and structured reward framework enable microrobot navigation policies to be trained within minutes and transferred without retraining across robots and environments.

NMI

論文Nature Machine Intelligence·2026/09/28

Regional climate risk assessment from climate models using probabilistic machine learning

Nature Machine Intelligence, Published online: 28 September 2026; doi:10.1038/s42256-026-01308-7 A generative AI framework called GenFocal is introduced for climate downscaling, producing realistic fine-scale weather from coarse projections and improving regional risk estimates of compound extremes such as heatwaves and tropical cyclones.

NMI

論文Nature Machine Intelligence·2026/09/28

Task-structured modularity emerges in artificial networks and aligns with brain architecture

Nature Machine Intelligence, Published online: 28 September 2026; doi:10.1038/s42256-026-01306-9 Wu et al. show that neural networks learning multiple tasks organize into specialized modules, particularly under capacity constraints. Incremental multitask learning strengthens this modularity and produces architectures resembling brain networks.