[Jan 2026] One co-first author paper was accepted to ICRA 2026, focusing on
end-to-end VLMs for Vision-Language Navigation (VLN) tasks. Looking forward to meeting fellow
researchers and robots in Vienna! 🎉
Research
My research focuses on enabling intelligent agents, particularly humanoid robots, to perceive,
reason, and physically interact with the world.
We propose an end-to-end VLM for Vision-Language Navigation that integrates topology-aware spatial reasoning with global action decision, achieving competitive performance on R2R benchmarks with models as small as 0.5B parameters.
Software
I enjoy the craft of bringing ideas to life with code, especially through front-end development. I
frequently share my thoughts and projects on my blog.