MAI-DS-R1 Collection MAI-DS-R1 is a DeepSeek-R1 reasoning model that has been post-trained by the Microsoft AI team. • 2 items • Updated 1 day ago • 6
view article Article Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖 5 days ago • 36
ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness Paper • 2504.10514 • Published 8 days ago • 43
Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability Paper • 2504.08003 • Published 9 days ago • 43
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models Paper • 2504.10479 • Published 4 days ago • 220
DataDecide Collection A suite of models, data, and evals over 25 corpora, 14 sizes, and 3 seeds to measure how accurately small experiments predict rankings at large scale. • 358 items • Updated 2 days ago • 11
SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning Paper • 2504.08600 • Published 7 days ago • 24
OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens Paper • 2504.07096 • Published 9 days ago • 69
Orpheus Multilingual Research Release Collection Beta Release of multilingual models. • 12 items • Updated 8 days ago • 76
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning Paper • 2504.07128 • Published 17 days ago • 79
view article Article Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC 10 days ago • 20
OmniSVG: A Unified Scalable Vector Graphics Generation Model Paper • 2504.06263 • Published 10 days ago • 143