Multimodal models

ATLAS: Agentic Test-time Learning-to-Allocate Scaling

Test-time scaling has become a major way to improve large language model reasoning, but its orchestration has remained designer-engineered: a fixed sample budget, a fixed refinement loop, a fixed scoring rule, or a fixed search policy decides how compute is spent, leaving the model in charge of solving but not of orchestration. We introduce ATLAS, an agentic test-time scaling framework in which an LLM orchestrator owns the control loop end-to-end.

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

Multimodal Embedding & Reranker Models with Sentence Transformers

Welcome Gemma 4: Frontier multimodal intelligence on device

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

Speaking of Voxtral

Voxtral TTS: A frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents.

Introducing GPT-5.4 mini and nano

GPT-5. 4 mini and nano are smaller, faster versions of GPT-5.

Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks

MedGemma: Our most capable open models for health AI development

We’re announcing new multimodal models in the MedGemma collection, our most capable open models for health AI development.

Get your VLM running in 3 simple steps on Intel CPUs

TimeScope: How Long Can Your Video Large Multimodal Model Go?

Invideo AI uses OpenAI models to create videos 10x faster

Invideo AI uses OpenAI’s GPT-4. 1, gpt-image-1, and text-to-speech models to transform creative ideas into professional videos in minutes.

Efficient MultiModal Data Pipeline

Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

nanoVLM: The simplest repository to train your VLM in pure PyTorch

Blazingly fast whisper transcriptions with Inference Endpoints

Visual Salamandra: Pushing the Boundaries of Multimodal Understanding