I build diagnostic frameworks that expose where and why Vision-Language Models fail on fine-grained visual understanding. My research sits at the intersection of VLM hallucination, explicit reasoning, and grounded evaluation with a focus on making visual reasoning traceable and verifiable. I am actively seeking new research opportunities, so if you're interested in collaborating or discussing potential projects, please feel free to reach out.
🎯
Focusing
AI researcher,
interested in Visual Reasoning · Vision-Language Models · Multimodal AI
Highlights
- Pro
Pinned Loading
-
-
foundation-models-implementation
foundation-models-implementation PublicModels implementations from scratch in Pytorch
Python 1
-
stock-market-price-prediction
stock-market-price-prediction PublicStock Market price prediction
-
-
detection-transformer
detection-transformer PublicA simple implementation of DETR in pytorch
Python
-
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.

