Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Multimodal Agents with RL Feedback
This talk covers building a multimodal multi-agent chatbot using open-source tools, integrating text, image, and audio inputs with reinforcement learning and feedback loops for improvement.
This presentation demonstrates the development of a multimodal, multi-agent chatbot using open-source models to handle text, image, and audio inputs without proprietary APIs. It integrates tools like LangGraph and ReactJsonAgent for agent orchestration and leverages feedback mechanisms for continuous improvement.
As a relevant part 2 - A brief overview (and sample project) to show the power of reinforcement learning techniques like RLHF with PPO (and some custom results of improvement on another project’s data) to utilize human feedback to further fine-tune models