commit-rewriter 0.2
Simon Willison released commit-rewriter 0.2. The tool relates to git, but the original text does not explain its specific functionality or update details.
#Open source
#Open source
0 todaySep 25
Sep 22
llm-typesafe 0.1a0
Simon Willison released the LLM plugin llm-typesafe 0.1a0 to connect TypeSafe AI's new Jev model to the LLM tool.
Sep 21
Improving synthesis prediction of small molecules at scale with RetroChimera
Microsoft published RetroChimera, a retrosynthesis prediction framework, in Nature and open-sourced its implementation and weights. It combines the Transformer model R-SMILES 2 with GNN-based NeuralLoc, using a learned ensemble to rerank predictions. Chemists preferred its single-step reaction predictions in blind testing.
tokenizers v1: encode, decode and scaling, measured
Hugging Face released tokenizers v1, preserving token IDs, APIs, vocabularies and merge ranks from v0.23 while increasing speed by up to tens of times.
Sep 19
MilleMiglia: A realistic instance generator for middle-mile logistics
Google Research released MilleMiglia, a C++ generator of realistic, privacy-preserving benchmark instances for middle-mile logistics delivery. Source and documentation are public on GitHub.
Sep 15
Heart of the Matter: How a Major Children’s Hospital Uses Open Source NVIDIA AI for Cardiac Care
Children's Hospital of Philadelphia (CHOP) uses MONAI, the open-source medical imaging framework co-founded by NVIDIA, to reduce paediatric heart modelling from four hours to seconds, already supporting complex ventricular septal defect surgical planning. CHOP is working with NVIDIA to integrate Newton, an open-source physics engine based on NVIDIA Warp, into SlicerHeart, reducing cardiac-device simulation from up to four hours to near real time.
Sep 3
NeoMME: an efficient Multimodal-native and Multilingual Encoder
Hugging Face launched NeoMME in 260M and 800M sizes. A single bidirectional Transformer handles text tokens and 32×32 image patches, trained from scratch with a masked discrete diffusion objective rather than pretrained vision towers or causal language models.
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
A public low-cost approach fine-tunes LFM2.5-350M with TRL GRPO using around 500 samples and 100 steps, raising IFStruct from 22.6% to 29.7%. Training fits free Colab or Kaggle GPUs, with local llama.cpp evaluation on a MacBook and code open on GitHub.
Sep 1
GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models
Microsoft Research introduced GigaPath-Flash and GigaTIME-Flash, greatly reducing pathology compute requirements with a 22M-parameter ViT-S backbone distilled from the billion-parameter GigaPath encoder, open-source under Apache 2.0.
Aug 24
Import AI 470: No rights for machines; automating environment generation with SPADE; and building better GPU kernels with Hawkeye
METR research shows AI's effects on scientific discovery are uneven: cybersecurity vulnerability reporting accelerated sharply in 2026 compared with 2025, mathematics accelerated only modestly, and algorithmic progress in AI research itself showed no significant acceleration. A multi-university team proposed SPADE, alternating LLM generation of executable training environments with solving them. Qwen3-30B-A3B averaged 58.3 on the game-environment suite, 8.1 above baseline.
Aug 13
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
Hugging Face's OlmoEarth Studio now computes and exports embeddings. Users choose an area, period, encoder variant and resolution through UI or API and receive Cloud-Optimized GeoTIFF (COG) results.
Jul 21
Grabette: an open system to record robot-manipulation data
Hugging Face released Grabette, an open-source system recording manipulation demonstrations with a handheld gripper and two cameras, producing robot-ready datasets without robots or teleoperation equipment. The handheld hardware costs about €490 in materials, with the accompanying motorised Gripette gripper around €120. Hardware CAD, Raspberry Pi collection software and browser-based processing are all open-source.
Jul 1
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Hugging Face released ScarfBench (Self-Contained Application Refactoring Benchmark) to evaluate AI agents migrating enterprise Java applications between Spring, Jakarta EE and Quarkus.
Jun 30
DiScoFormer: One transformer for density and score, across distributions
Hugging Face proposed DiScoFormer (Density and Score Transformer), estimating a distribution's density and score simultaneously in one forward pass from a set of data points, without retraining for new distributions.
May 18
Import AI 457: AI stuxnet; cursed Muon optimizer; and positive alignment
Import AI 457 focuses on three studies. SentinelOne analysed fast16.sys, malware from over 20 years ago that sabotages engineering and physics simulations by altering in-memory results from precision software such as LS-DYNA 970, PKPM and MOHID.
Apr 16
AI-generated synthetic neurons speed up brain mapping
Google Research proposed MoGen (Neuronal Morphology Generation), using PointInfinity point-cloud flow matching to generate synthetic neuronal shapes and supplement PATHFINDER reconstruction training. It reduced reconstruction error by 4.4% on held-out mouse axons, mainly by reducing merge errors.