Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models

Huggy Lingo: Using Machine Learning to Improve Language Metadata on the Hugging Face Hub

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models

DuckDB: analyze 50,000+ datasets stored on the Hugging Face Hub

huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning

Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model

arXiv:2607. 26742v1 Announce Type: cross Abstract: Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.

Efficient training of language models to fill in the middle

Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia

Evaluating large language models trained on code

Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2

Emotion Recognition in Signers

arXiv:2512. 15376v2 Announce Type: replace-cross Abstract: Recognition of signers' emotions suffers from one theoretical challenge and one practical challenge, namely, the overlap between grammatical and affective facial expressions and the scarcity of data for model training.

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

arXiv:2608. 13517v1 Announce Type: cross Abstract: Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data.

Understanding and Accelerating the Training of Masked Diffusion Language Models

arXiv:2605. 13026v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling.