Compact, Multilingual, and Built for the Edge
We’re excited to share Granite 4.0 1B Speech, the latest addition to…
Removing the Guesswork from Disaggregated Serving
Deploying and optimizing large language models (LLMs) for high-performance, cost-effective serving can…
FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design
arXiv:2603.05567v1 Announce Type: new Abstract: Dual-target structure-based drug design aims to generate…
DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality
arXiv:2603.05912v1 Announce Type: new Abstract: Search-augmented LLM agents can produce deep research…
Confounding factors and biases abound when predicting molecular biomarkers from histological images
Data and study designWe analysed the limitations of existing ML approaches for…
Critical minerals are hiding in plain sight in U.S. Mines
The United States may already be producing most of the critical minerals…
Scientists discover the brain protein that drives cocaine relapse
Relapsing into cocaine use is not simply a matter of weak willpower.…
Caltech’s massive 6,100-qubit array brings the quantum future closer
Quantum computers will need large numbers of qubits to tackle challenging problems…
The Complete Swift Client for Hugging Face
Today, we're announcing swift-huggingface, a new Swift package that provides a complete…
Enhancing Distributed Inference Performance with the NVIDIA Inference Transfer Library
Deploying large language models (LLMs) requires large-scale distributed inference, which spreads model…