Stars
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
a thin wrapper of chatgpt for improving paper writing.
A unified diffusers implementation for MVDream and ImageDream
A diffuser implementation of Zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV23)
Rembg is a tool to remove images background
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.