SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion Paper โข 2503.11576 โข Published 13 days ago โข 75 โข 9
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis Paper โข 2502.04128 โข Published Feb 6 โข 25 โข 4