Aadarsh Sahoo — Caltech Ph.D. Student

Aadarsh Sahoo

I am a Ph.D. student at Caltech advised by Prof. Georgia Gkioxari and Prof. Pietro Perona.

Prior to this, I was a student researcher at the MIT-IBM Watson AI Lab pretraining Large Language Models along with research on Vision-Language Models with Dr. Rameswar Panda, Dr. Rogerio Feris, and Prof. Yoon Kim. I completed my dual-degree (B.Tech + M.Tech) from IIT Kharagpur where I worked as an undergraduate researcher at the Computer Vision and Intelligence Research Lab under the supervision of Prof. Abir Das.

In the summer of 2021, I was fortunate to get an opportunity to work under the guidance of Prof. Kate Saenko (Boston University) and Prof. Trevor Darrell (UC Berkeley), as a research intern for the DARPA LwLL Project.

Email  /  Google Scholar  /  Resume  /  LinkedIn  /  Github

• [Jun'25] Preprint “Aligning Text, Images, and 3D Structure Token-by-Token (Kyvo)” released on arXiv (project page).
• [Jul'24] “XPL: A Cross-Model framework for Semi-Supervised Prompt Learning in VLMs” accepted by TMLR.
• [Jan'23] Paper on Anytime Domain Adaptation accepted at ICLR 2023.
• [Jan'23] Select, Label, and Mix (SLM) received the Best Paper Honorable Mention Award at WACV 2023!
• [Oct'22] Paper on Partial Domain Adaptation accepted at WACV 2023.
• [Jul'22] Started working as a student researcher at the MIT-IBM Watson AI Lab at Cambridge, MA.
• [Oct'21] Extended Abstract on Partial Domain Adaptation accepted at NeurIPS DistShift Workshop 2021.
• [Sept'21] Paper on Domain Adaptation in Action Recognition accepted at NeurIPS 2021.
• [Jun'21] Volunteer at the workshop on Dynamic Neural Networks Meets Computer Vision (DNetCV) at CVPR 2021.
• [May'21] Started my internship at UC Berkeley and Boston University.
• [Aug'20] One paper accepted at the ECCV 2020 Workshop on Imbalance Problems in Computer Vision (IPCV).
• [May'19] Joined CVIR, IIT Kharagpur as an undergraduate researcher in Computer Vision.
• [Jul'18] Got Computer Science and Engineering as my major. (less than 1% acceptance)
• [Jul'17] Got accepted into IIT Kharagpur for my undergraduate studies through the JEE Advanced 2017.

My research interests lie in understanding the principles of learning from multiple modalities and exploring how knowledge from one modality can be transferred to applications in others, with a goal to design embodied multimodal agents benefiting humanity. Obtaining answers to questions like - "Do toddlers use the same principles in learning new languages as they do in learning how to walk?" - should be fun!

We present a unified LLM that aligns language, images, and structured 3D scenes and demonstrate it across rendering, recognition, instruction-following, and 3D QA.

A semi-supervised prompt learning framework that leverages unlabeled data to improve VLM adaptation via cross-model consistency.

We introduce a novel approach for anytime domain adaptation by considering domain alignment with switchable depth, width and input resolutions to achieve accuracy-efficiency trade-offs in the target domain for different resource constraints.

We introduce a novel temporal contrastive learning approach for unsupervised video domain adaptation, achieved by jointly leveraging video speed, background mixing, and target pseudo-labels.

We develop a novel 'Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation.

We introduce a joint dataset repairment strategy by combining a classifier with a GAN that makes up for the deficit of training examples from the minority class by producing additional examples.

• Reviewer: CVPR, NeurIPS, ICLR, ICCV, WACV, TPAMI.
• Student Volunteer and Reviewer: Dynamic Neural Networks Meets Computer Vision (DNetCV) at CVPR 2022.
• Student Volunteer and Reviewer: Dynamic Neural Networks Meets Computer Vision (DNetCV) at CVPR 2021.

Webpage template courtesy: Jon Barron