Akhil Perincherry

Hello! I am a Ph.D. student at Oregon State University with Dr. Stefan Lee working generally in visual-language grounding and embodied AI. I am also an ML engineer at Ford Motor Company working primarily on perception features for automated driving mostly using camera images and LiDAR point clouds.
My research interests primarily lie in the intersection of vision and language learning. In general, I am interested in solving problems that stem from a lack of grounding, lack of annotated or domain-specific data, and problems where testing data is distributionally different from training data. Of late, I am particularly drawn to problems motivated by cognitive science, perhaps to my detriment.
Previously, I graduated from the University of Florida with my masters. Before that, I worked at the Indian Institute of Science under Prof. K R Ramakrishnan at the Computer Vision and Artificial Intelligence (CVAI) lab where I worked on table-top touch-interface applications using a projector-camera based setup.
In my free time (404), I enjoy playing/watching soccer, kickboxing, hiking (esp. waterfall hikes) and practically any outdoor sport.
news
Aug 01, 2025 | “Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control” was accepted to CoRL 2025 as an oral presentation. |
---|---|
Jun 25, 2025 | Harnessing Input-adaptive Inference for Efficient VLN was accepted to ICCV 2025. |
May 10, 2025 | I was named as an outstanding reviewer (top 5%) at CVPR 2025! |
Feb 26, 2025 | Do Visual Imaginations Improve Vision-and-Language Navigation Agents? was accepted to CVPR 2025 (22.1%). |