I am an AI/ML enthusiast with a strong passion for bridging technology and social impact. I love solving complex problems whether it's solving confusion on any AI/ML concept or building LLM systems for real-world applications.
AI/ML Research & Development, Object Detection & Vision-Language Integration, LLM Training & Evaluation
Sep 11, 2025 · 5 min read · After months of development, the DeepForest Agent with spatial analysis capabilities is now complete. This multi-agent system transforms raw ecological image detection into comprehensive spatial narratives, making complex computer vision results acce...
Join discussion
Aug 30, 2025 · 18 min read · Moving forward, I will lay out the workflow of our DeepForest Multi-Agent system. According to the workflow the orchestrator along with all the agent is implemented. The Gradio interface supports uploading image and shows a chatbot. Underneath it the...
Join discussion
Aug 12, 2025 · 9 min read · Moving forward, I added a tile manager to handle image tiling for the visual agent and distribute detections across those tiles. Finally, I implemented a JSON manager where all responses and results are stored, which will also serve as input to the e...
Join discussion
Aug 1, 2025 · 15 min read · Moving forward, I worked on the next steps I mentioned in my last blog post. I added a session-based state manager using a thread ID to keep track of conversation history, agent outputs, and image context. To improve efficiency, I implemented a cache...
Join discussion
Jul 21, 2025 · 10 min read · Moving forward, I am shifting from using commercial APIs to open-source models based on mentor feedback. This shift requires implementing a multi-agent architecture because HuggingFace models. I focused on preparing the foundations for that system. I...
Join discussion
