view article Article Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever. By MaziyarPanahi • 9 days ago • 116
view article Article TimeScope: How Long Can Your Video Large Multimodal Model Go? By orrzohar and 3 others • 3 days ago • 26
view article Article Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models By AI-MO and 17 others • 16 days ago • 45
view article Article Vibe coding for data science: how to label a dataset with Kimi K2 By dvilasuero • 4 days ago • 16
view article Article OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models By nvidia and 3 others • 7 days ago • 45
view article Article Preference Optimization for Vision Language Models By qgallouedec and 3 others • Jul 10, 2024 • 80
view article Article Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO) By ariG23498 • Jan 19 • 26
view article Article Introducing ColQwen-Omni: Retrieve in every modality By manu and 4 others • 9 days ago • 58
TC-Light: Temporally Consistent Relighting for Dynamic Long Videos Paper • 2506.18904 • Published Jun 23 • 10
view article Article Seeing Isn’t Understanding: The Spatial Reasoning Gap in Vision-Language Models By KBayoud • 13 days ago • 6
view article Article ScreenEnv: Deploy your full stack Desktop Agent By A-Mahla and 1 other • 16 days ago • 51
view article Article Asynchronous Robot Inference: Decoupling Action Prediction and Execution By fracapuano and 7 others • 16 days ago • 36
view article Article Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders By thomwolf and 1 other • 17 days ago • 608
Encoders vs Decoders: the Ettin Suite Collection A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 • 32 items • Updated 9 days ago • 14
AllTracker: Efficient Dense Point Tracking at High Resolution Paper • 2506.07310 • Published Jun 8 • 2