Interpretability and Safety for Robot Foundation Models

ℹ️ EPISODE INFO

Released

August 6, 2026

Duration

5m

Channel

YC Root Access

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with Bear Häon about applying interpretability and AI safety techniques to vision-language-action models. The work examines activations inside a vision-language-action model, groups neurons associated with concepts such as speed or caution, and then steers the robot's behavior by amplifying those groups. This provides a way to better understand and control how robots translate language into physical actions. The broader goal is to develop safety methods for physical AI, where failures can have direct consequences in the real world. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs

🎤 SPEAKERS

• Ankit Gupta

  host

  Host at YC Root Access (Y Combinator) who interviews guests about machine learning and startups.

• Bear Häon

  guest

  Founder of the Physical AI Safety Institute and researcher focused on interpretability and safety for robot foundation models.

🧾 EPISODE SUMMARY

In this episode of YC Root Access, featuring Ankit Gupta and Bear Häon, Interpretability and Safety for Robot Foundation Models explores Interpreting robot foundation models to control behavior and improve safety The discussion presents one of the first interpretability papers for Robot Foundation Models (RFMs), adapting AI-safety interpretability techniques to embodied, physically acting systems.

🔗 RELATED EPISODES

ChartNet: Training Vision-Language Models to Understand Charts

Any-Horizon Reasoning for Video Agents

Diamond Maps: Efficient Reward Alignment for Generative Models

Improving Small Language Model Reasoning With A* Search

LeanAgent: Lifelong Learning for Formal Theorem Proving

The First Dedicated YC GPU Cluster - With Together AI