Achleshwar Luthra

I am a CS PhD student at Texas A&M University, advised by Prof. Tomer Galanti. My research focuses on the intersection of Self-Supervised Learning (SSL) and Multimodal Learning. I am particularly interested in developing best practices for training SSL models and creating methods that enable these models to learn general-purpose representations and adapt to various modalities.

Previously, I worked at the intersection of 3D Computer Vision and AI, focusing on Neural Scene Representations and 3D Scene Understanding. I earned my Master’s degree in Computer Vision from the Robotics Institute, CMU, where I was advised by Prof. David Held and Ben Eisner on 3D Scene Understanding. During my undergraduate studies at BITS Pilani, I collaborated with Prof. Narendra Ahuja on 3D Reconstruction of Animals and with Prof. Jitendra Malik’s group on Single-View 3D Reconstruction of inanimate objects.

news

Jan 2, 2025 Started Ph.D. in Computer Science at Texas A&M University. :sparkles:
Feb 12, 2024 Joined Futurewei as a Resarch Engineer (Graphics Rendering) working on Generalizable Radiance Fields.
Jan 9, 2024 Presented Deblur-NSFF at WACV 2024.
May 15, 2023 Started research internship at Futurewei Technologies, Inc. (earlier Huawei R&D) on NeRFs for Dynamic Scenes!
Aug 28, 2022 Started MS in Computer Vision at Carnegie Mellon University. :sparkles: