Fangyuan Yu
AI Researcher (LLM) @Thoughtworks || PhD KAUST
This profile was put together from Fangyuan's public GitHub portfolio, and they haven't joined Vibetown yet, so reach them through their portfolio. Is this you? Contact us to update or remove it.
About
Fangyuan Yu works in AI engineering, based in Singapore (Thoughtworks). AI Researcher (LLM) @Thoughtworks || PhD KAUST. Public projects on GitHub include Mini-LLaVA (A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability), CoT-Reasoning-without-Prompting (Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting) and Repo Viewer (Visualize any repo or codebase into diagram or animation), mostly written in Python and Jupyter.
Projects 6
Mini-LLaVA
A minimal implementation of LLaVA-style VLM with interleaved image & text & video processing ability.
github.comCoT-Reasoning-without-Prompting
Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting
github.comRepo Viewer
Visualize any repo or codebase into diagram or animation
github.comSelective Attention Transformer
Unofficial Implementation of Selective Attention Transformer
github.comCharacterLM
vocabulary curriculum + LLM
github.comRuleAlign
Rule-Based Adherance evaluation for LLM Agent
github.com