OpenMind(@openmind_agi):Robots should not care about your lighting. Our paper on Domain-Invariant Latent Lookahead (DILL) was selected for a presentation at RSS 2026. VLA policies quietly learn visual shortcuts: change the camera angle, the background, or the light, and they execute the wrong task. DILL teaches the policy to predict a domain-invariant future, not the pixels. This is the work behind the promise: OpenMind builds robot experiences that stay reliable in the real world, where the lights, the layout, and the cameras never match the lab. Huge thanks to our partners at @SeoulNatlUni, @Hyundai, Ajou University, and Tommoro Robotics. Stay tuned for more from OpenMind Research.

2026.07.22 19:25

Robots should not care about your lighting. Our paper on Domain-Invariant Latent Lookahead (DILL) was selected for a presentation at RSS 2026. VLA policies quietly learn visual shortcuts: change the camera angle, the background, or the light, and they execute the wrong task. DILL teaches the policy to predict a domain-invariant future, not the pixels. This is the work behind the promise: OpenMind builds robot experiences that stay reliable in the real world, where the lights, the layout, and the cameras never match the lab. Huge thanks to our partners at @SeoulNatlUni, @Hyundai, Ajou University, and Tommoro Robotics. Stay tuned for more from OpenMind Research.