AI Engineer focusing on Computer Vision, Generative AI, and AI Agents.
I work on AI-powered image and video applications, with experience in multimodal AI, deep learning, and multi-agent systems.
A large-scale multimodal dataset and Multi-Agent framework for visual harmfulness understanding.
- Multi-Agent AI
- Multimodal AI
- Dataset construction
- Multi-Agent framework design
- Experimental analysis
- NeurIPS 2024 Datasets and Benchmarks Track
A Vision-Language Model based approach for detecting AI-generated and manipulated images.
- Vision-Language Models
- Deepfake Detection
- Prompt Tuning
- Generalization to unseen generative models
- Computer Vision
- Generative AI
- Multimodal AI
- AI Agents
- Deep Learning
Python PyTorch Git