Akshay L. Chandra
Papers
1
Total Citations
4
H-Index
1
About
Akshay L. Chandra is a rising researcher at the intersection of robotics, imitation learning, and language-conditioned control. His primary contributions center on enabling robots to learn complex, long-horizon tasks by combining world models with natural language instructions. In his highly cited work, "LUMOS: Language-Conditioned Imitation Learning with World Models" (2025), Chandra introduces a framework that allows robots to practice skills through on-policy rollouts in a learned latent space, then transfer those skills zero-shot to physical hardware. This approach bridges the gap between simulation and real-world deployment, significantly reducing the need for costly real-world data collection. While early in his career, his work has already garnered attention for its practical impact on multi-task robot learning. Chandra’s research pushes toward more generalist robots that can understand human commands and adapt to new environments without explicit retraining—a key step toward embodied AI. His contributions are shaping how researchers think about scalable, language-guided skill acquisition in robotics.
Research Focus
Key Achievements
Top Papers
- 1LUMOS: Language-Conditioned Imitation Learning with World Models4 citations · 2025