view article Article NVIDIA Releases 3 Million Sample Dataset for OCR, Visual Question Answering, and Captioning Tasks By nvidia and 4 others • 13 days ago • 66
view article Article Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training By siro1 and 4 others • 17 days ago • 51
view article Article Vision Language Model Alignment in TRL ⚡️ By sergiopaniego and 4 others • 18 days ago • 71
view article Article Vision Language Model Alignment in TRL ⚡️ By sergiopaniego and 4 others • 18 days ago • 71
view article Article Introducing Command A Vision: Multimodal AI built for Business By CohereLabs and 3 others • 24 days ago • 63
EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Paper • 2507.21848 • Published 26 days ago • 7
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface Paper • 2507.18546 • Published about 1 month ago • 18
ULD Loss (Universal LLMs Distillation) Collection The ULD loss, based on optimal transport, enables distillation across different LLM families without requiring shared tokenizers. • 14 items • Updated Jul 15 • 2
Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization Paper • 2411.10442 • Published Nov 15, 2024 • 87
ThinkPRM Collection Process Reward Models that Think -- https://arxiv.org/abs/2504.16828 • 8 items • Updated 26 days ago • 3
view article Article Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure By jcudit • Jul 8 • 10