- ML Engineer at Huawei's "Hoah's Ark lab" 📚
- Master 🎓 in 🤓 Applied Math and Physics ⚛️
- ML and AI projects: LLMs and Diffusion models 🤗.
- Some of my paper highlights (including A and A* level): ⭐
- [InterSpeech 2024] PitchFlow - a Flow-matching TTS with fine-grained pitch control; 🪄
- [ICLR 2025] Improved Sampling Algorithms for Lévy-Itô Diffusion Models. 🧨
- Core contributor of Gamayun🪽, a cost efficient LLM fully pretrained on Ascend NPUs. ✍️
- My full Google Scholar profile. 🚀 My Huggingface profile. 🤗
- Skills: Python, ML, C/C++, Linux, Lua and Java, some SQL 🐍🍵
- I love doing art projects: AI, drawing, gamedev - whatever! 🤖✏️
- To contact me, send emails (see Scholar). Pronouns: he/him 💬
Pinned Loading
-
sd-webui-text2video
sd-webui-text2video PublicAuto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies
-
deforum/sd-webui-deforum
deforum/sd-webui-deforum PublicDeforum extension for AUTOMATIC1111's Stable Diffusion webui
-
video2scenario
video2scenario PublicRecursively writes descriptions of video scenes using Large Language Models and Image Captioners
-
abliterate.cpp
abliterate.cpp PublicAbliterate large quantized models at home using llama.cpp!
Python 1
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.





