Barkin Dagda

Agile Loop Ltd.

Role: Research Scientist and Developer (Promoted to Senior Research Scientist)

I worked with LLMs and VLMs, applying techniques such as fine-tuning, RAG, function calling, and other advanced implementation methods. I developed autonomous software agents that integrated LLMs and VLMs for dynamic UI understanding and task execution.

I was promoted to Senior Research Scientist, leading the successful commercialization of SAM-Desktop, a proposal since adopted by Lenovo. My role included architectural planning, back-end development, and cross-functional leadership.

Video Demo

Cyclopic

Role: Robotics Researcher

Worked on advanced control systems and digital twin simulations for autonomous mobile robots in warehouse and nuclear applications. Developed AI-driven load balancing and localization systems in GPS-denied environments.

VLM-Guided Reinforcement Learning for Emergency Braking

This work investigates using vision-language models (VLMs) as semantic priors to guide reinforcement learning policies in high-risk traffic scenarios, specifically for occluded pedestrian crossings.

HighwayLLM: Decision-Making with RL-Informed Language Model

A novel approach integrating LLM, RL, and PID-based control to create interpretable, safe, and efficient navigation strategies. [View Paper]

Cyclopic AMR Digital Twin