Kimi-K2 Collection Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence β’ 2 items β’ Updated 9 days ago β’ 104
MADrive: Memory-Augmented Driving Scene Modeling Paper β’ 2506.21520 β’ Published 25 days ago β’ 36
Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models Paper β’ 2506.19103 β’ Published 28 days ago β’ 43
DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization Paper β’ 2505.20975 β’ Published May 27 β’ 36
Alchemist: Turning Public Text-to-Image Data into Generative Gold Paper β’ 2505.19297 β’ Published May 25 β’ 81
Alchemist Collection π Dataset and π checkpoints for paper π "Alchemist: Turning Public Text-to-Image Data into Generative Gold" β’ 7 items β’ Updated May 27 β’ 16
Hogwild! Inference: Parallel LLM Generation via Concurrent Attention Paper β’ 2504.06261 β’ Published Apr 8 β’ 110
Running 2.83k 2.83k The Ultra-Scale Playbook π The ultimate guide to training LLM on large GPU Clusters