VLM SFT - Annotation - Coding
I specialize in SFT and RLHF for Vision-Language Models, specifically for coding and technical tasks. My work involves analyzing visual inputs (UIs, diagrams, flowcharts) and verifying the accuracy of the corresponding code generated by the AI. I provide manual corrections for syntax errors, logical fallacies, and "hallucinations" where the model fails to align with the provided image. Expert in Python, React, and debugging multimodal datasets.