精选

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

Introducing Gemini 3.8 Flash and 3.8 Flash Cyber

BenchMIRT: What are LLM benchmarks actually measuring?

Mapping global methane emissions from space with deep learning

Climate & Sustainability

Introducing Claude Fable 5.1 and Claude Mythos 5.1

TimesFM-3: A zero-shot foundation model for multivariate forecasting

Data Management

GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models

What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. The post GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models appeared first on Microsoft Research .

The Open ASR Leaderboard Adds Its First Global South Language

Planetary prediction engine: Automating global models via Earth AI

Earth AI

Gemini Omni 1.1 Flash lets you build with more control

Piloting the world's first double-blind AI evaluations

Piloting the world's first double-blind AI evaluations

GlucoFM: Foundation model for continuous glucose monitoring

Health & Bioscience

Intelligent transcription with Gemini 3.5 Transcribe

Now you can get more intelligent speech-to-text transcription with Gemini 3.5 Transcribe.

Release: v5.16.0

Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed residual architecture that combines Hyper-Connection with GatedNorm. It mixes multiple residual streams with fine-grained elementwise gating before each attention and Mixture-of-Experts (MoE) block, then controls how much of the block output is injected back into each stream. QSA uses multiple query heads to score compressed key blocks, selects the most relevant contiguous token blocks, and keeps the

Release v5.16.1

Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks. GLM-5.3-Flash starts from a newly trained base model, with its architecture and training recipe redesigned around capability and efficiency. For the first time in the GLM series, we introduce a hybrid architecture combining sparse and linear attention, sharply r

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

Granite 4.2 LLMs: How They're Built

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

An AI tool for prioritizing candidate biomarkers from wearable sensor data

Generative AI

From Atari to EVE Online: Building on 15 Years of AI Research in Games

Google DeepMind partners with game studios to prototype breakthrough AI gameplay.

How mobility gives language models a deeper understanding of place

Algorithms & Theory

Measuring benchmark optimization in speech recognition

Broadening access to Skala creates a faster path to predictive DFT

Skala 1.1, the updated deep-learning exchange-correlation functional from Microsoft Research, provides greater accuracy, expanded accessibility across the computational chemistry ecosystem, and a living benchmark to track computational performance. The post Broadening access to Skala creates a faster path to predictive DFT appeared first on Microsoft Research .

Patch release: v5.15.1

Patch release v5.15.1 This patch most notably solves a few issues with DFlash and MTP candidate generators, as well as an issue where images could sometimes not be processed on accelerator if using Lanczos filter. It contains the following commits: Fix DFlash candidate token device mismatch with device_map="auto" ( #47877 ) by @sywangyi and @Cyrilvallez Align logit distributions for CandidateGenerators using sampling ( #48007 ) by @Cyrilvallez Fix MTP config when mlp_layer_types is absent ( #48015 ) by @Cyrilvallez Fallback from 'lanczos' to 'bicubic' when on cuda ( #48026 ) by @zucchini-nlp Fix gemma4 video to device ( #47896 ) by @guarin

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

Seeing beyond BMI: Estimating cardiometabolic risk with smartphone imagery

General Science

Introducing Gemini 3.7 Flash

What We Learned by Reproducing 2,200 papers from ICML

Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

MindTopo reveals VLMs’ spatial reasoning abilities

A path, a fence, a knot. MindTopo sets a new benchmark for testing how AI understands topological relationships and highlights new opportunities to strengthen spatial reasoning and planning. The post MindTopo reveals VLMs’ spatial reasoning abilities appeared first on Microsoft Research .