Open sourceAIIntermediate
Transformers
Pretrained-model toolkit spanning text, vision, audio, and multimodal tasks.
Hugging FaceAbout 2 hrpythontransformers
Browse by topic
多模态
8 items
AI updateAI
Introducing Quine: An AI research system designed for the complexity of biology
Biology doesn't operate in silos, and neither should the AI representation of it. Quine is an early-stage research effort to create a multimodal world model of biology. By connecting insights across biological scales and modalities, Quine helps scientists computationally search a space far larger than intuition allows…
Microsoft ResearchPublished Sep 29, 2026
Official source · Microsoft ResearchVerified Oct 10, 2026
AI updateAI
EmbeddingGemma 2: an open, lightweight multimodal embedding model
We introduced EmbeddingGemma last year to provide a lightweight option for high-quality text embeddings, to help your apps organize, search, and connect information directly on consumer hardware. The developer community’s response blew past our expectations. With more than 20 million downloads, builders have used it t…
Google DeepMindPublished Oct 7, 2026
Official source · Google DeepMind BlogVerified Oct 10, 2026
AI updateAI
Introducing Gemma 4 12B: a unified, encoder-free multimodal model
Today, we are introducing Gemma 4 12B, our latest model designed to bring agentic multimodal intelligence directly to laptops. Bridging the gap between our edge-friendly E4B and our more advanced 26B Mixture of Experts (MoE), Gemma 4 12B packages powerful capabilities inside a reduced memory footprint. It is also our…
Google DeepMindPublished Jun 9, 2026
Official source · Google DeepMind BlogVerified Sep 6, 2026
AI updateAI
Accelerating vision-language models with LFM2.5-VL-DSpark
How does speculative decoding work for VLMs The vision drafter uses the same architecture as our text LFM2.5-DSpark drafters: it captures the target model's hidden states at a fixed set of tapped layers and conditions on them to draft a block of k candidate tokens. Image patches and text tokens are projected into a sh…
Hugging FacePublished Sep 24, 2026
Cross-checked · Hugging Face BlogVerified Oct 8, 2026
AI updateAI
Multimodal open d1 decision models for the edge
How we built decision models for the edge These open d1 decision models are built on our Liquid Foundation Models (LFMs). Unlike our generative models, decision models don’t produce tokens but answer in a single forward pass.
Hugging FacePublished Oct 8, 2026
Cross-checked · Hugging Face BlogVerified Oct 10, 2026
AI updateAI
NeoMME: an efficient Multimodal-native and Multilingual Encoder
TL;DR We introduce NeoMME , a family of 260M and 800M multilingual multimodal encoders. Unlike many generative visual language models, NeoMME does not use a separate pretrained vision tower or a causal language model. A single bidirectional Transformer processes both text tokens and raw image patches, and we train the…
Hugging FacePublished Sep 3, 2026
Cross-checked · Hugging Face BlogVerified Oct 1, 2026
AI updateAI
Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
To celebrate, we are shipping with Meta day-0 support in transformers , llama.cpp , vLLM , Inference Endpoints, and other libraries. We built a few cool things and explain our findings in this blog.
Hugging FacePublished Aug 10, 2026
Cross-checked · Hugging Face BlogVerified Sep 9, 2026