Houston Machine Learning

We are going to walk through the concepts on Model Context Protocol (MCP) and how it integrates in Agent AI workflow, including a hands-on tutorial on how to run an AI agent with MCP with AWS BedRock: Harness the power of MCP servers with Amazon Bedrock Agents.

Slides for past meetups posted: Github
Recordings have been posted at: YanAITalk

Feel free to reach out if you want to present a paper or a use case at upcoming meetups!

Note: You must have a Zoom account to login (free account is sufficient). Link and password will be shared three days before the meeting.

Registration required: register

Join virtually for the livestream of the AWS Summit keynote on July 16, 2025, at 11:00 ET, featuring the Vice President of AWS Agentic AI, Swami Sivasubramanian. Discover how Amazon Web Services (AWS) is revolutionizing the industry with breakthrough innovations and major AI launches.

Swami will unveil how cutting-edge innovations in compute, storage, and generative AI are accelerating modern business transformation across global industries. Learn how the convergence of data, analytics, and AI is enabling new possibilities, and find out how agentic AI is automating manual tasks and processes.

LAW: Legal Agentic Workflows for Custody and Fund Services Contracts

Legal contracts in the custody and fund services domain govern critical aspects such as key provider responsibilities, fee schedules, and indemnification rights. However, it is challenging for an off-the-shelf Large Language Model (LLM) to ingest these contracts due to the lengthy unstructured streams of text, limited LLM context windows, and complex legal jargon. To address these challenges, we introduce LAW (Legal Agentic Workflows for Custody and Fund Services Contracts). LAW features a modular design that responds to user queries by orchestrating a suite of domain-specific tools and text agents. Our experiments demonstrate that LAW, by integrating multiple specialized agents and tools, significantly outperforms the baseline. LAW excels particularly in complex tasks such as calculating a contract’s termination date, surpassing the baseline by 92.9% points. Furthermore, LAW offers a cost-effective alternative to traditional fine-tuned legal LLMs by leveraging reusable, domain-specific tools.

Slides for past meetups posted: Github
Recordings have been posted at: YanAITalk

Feel free to reach out if you want to present a paper or a use case at upcoming meetups!

Note: You must have a Zoom account to login (free account is sufficient). Link and password will be shared three days before the meeting.

We are introducing the V-JEPA 2, the first world model and new benchmarks for physical reasoning from Meta:
Meta introduced V-JEPA 2 in June 2025, the first world model trained on video that enables state-of-the-art understanding and prediction, as well as zero-shot planning and robot control in new environments. As we work toward our goal of achieving advanced machine intelligence (AMI), it will be important that we have AI systems that can learn about the world as humans do, plan how to execute unfamiliar tasks, and efficiently adapt to the ever-changing world around us.

Slides for past meetups posted: Github
Recordings have been posted at: YanAITalk

Feel free to reach out if you want to present a paper or a use case at upcoming meetups!

Note: You must have a Zoom account to login (free account is sufficient). Link and password will be shared three days before the meeting.