What we’re about
Learn, network, have fun, and thrive with AI!
Schedule a live session with Yan for career coaching and business consulting: schedule
For per case inquiry, contact houstonmachinelearning.ai@gmail.com
All recordings published on YanAITalk channel.
Upcoming events (2)
See all- Kaggle Winning Solution: Predict human preference in multilingual chatbot arenaLink visible for attendees
We are going to walk through the top winning solutions of the Kaggle competition on human preference prediction!
More info about the Kaggle competition: Kaggle link
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.
- LLM Multi-agent System: A real-world use case study for clinical simulationLink visible for attendees
AgentClinic: A multimodal agent benchmark to evaluate AI in simulated clinical environments.
Evaluating large language models (LLM) in clinical scenarios is crucial to assessing their potential clinical utility. Existing benchmarks rely heavily on static question-answering, which does not accurately depict the complex, sequential nature of clinical decision-making. Here, we introduce AgentClinic, a multimodal agent benchmark for evaluating LLMs in simulated clinical environments that include patient interactions, multimodal data collection under incomplete information, and the usage of various tools, resulting in an in-depth evaluation across nine medical specialties and seven languages.
Slides for past meetups posted: Github
Recordings have been posted at: YanAITalkFeel 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.
