most citedMechanistic interpretability for steering vision-language-action models

1 citations · 1 across the 3 of their papers we have counts for

collaborators

6 papers

eess.SY2025

A Hamilton-Jacobi Reachability Framework with Soft Constraints for Safety-Critical Systems

Chams Eddine Mballo, Donggun Lee, Claire J. Tomlin

Traditional reachability methods provide formal guarantees of safety under bounded disturbances. However, they strictly enforce state constraints as inviolable, which can result in…

cs.RO20251 cited

Mechanistic interpretability for steering vision-language-action models

Bear Häon, Kaylene Stocking, Ian Chuang +1

Vision-Language-Action (VLA) models are a promising path to realizing generalist embodied agents that can quickly adapt to new tasks, modalities, and environments. However, methods…

eess.SY2025

When are safety filters safe? On minimum phase conditions of control barrier functions

Jason J. Choi, Claire J. Tomlin, Shankar Sastry +1

In emerging control applications involving multiple and complex tasks, safety filters are gaining prominence as a modular approach to enforcing safety constraints. Among various me…

cs.RO2025

Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety

Jason J. Choi, Jasmine Jerry Aloor, Jingqi Li +3

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning…

eess.SY2025

Data-Driven Hamiltonian for Direct Construction of Safe Set from Trajectory Data

Jason J. Choi, Christopher A. Strong, Koushil Sreenath +2

In continuous-time optimal control, evaluating the Hamiltonian requires solving a constrained optimization problem using the system's dynamics model. Hamilton-Jacobi reachability a…

cs.RO2024

Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker

Xingpeng Xia, Jason J. Choi, Ayush Agrawal +3

Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine…