Sarthak Kumar Maharana

PhD Candidate @ UT Dallas · sarthak.maharana@utdallas.edu

About

Portrait of Sarthak Kumar Maharana

I am a CS PhD Candidate at The University of Texas at Dallas, advised by Dr. Yunhui Guo. Prior to this, I earned my MS in Electrical Engineering from the University of Southern California. I completed my BTech in Electrical and Electronics Engineering at the International Institute of Information Technology (IIIT), Bhubaneswar, India.

I'm interested in building adaptive, efficient, and robust AI systems that keep learning when the world changes. My work spans continual learning, multimodal perception, and real-time motion planning and reasoning for autonomous driving.

Areas of interest: Computer Vision, Multimodal Learning, Physical AI.

Sub-areas: Continual Learning/Adaptation, Robust and Efficient Perception, On-Device AI, Autonomous Driving.

Open to research conversations & collaborations. Feel free to reach out!

Outside of my PhD, I try to stay active, consume unreasonable amounts of music, and maintain a completely healthy and proportionate obsession with cricket. I spend the rest of my free time contemplating life, the universe, consciousness, and other "lighthearted" topics. Open to random recs that I collect at a significantly faster rate than I can consume them, so naturally, do your deed!

News

Jul 2026Received an ECCV 2026 travel award; will also review for AAAI 2027.
Jun 2026Our continual test-time adaptation survey was accepted to TMLR.
Jun 2026AVReCAP was accepted to ECCV 2026.
Apr 2026I'll be joining NEC Laboratories America to work on real-time reasoning and planning for autonomous driving.
Apr 2026Returned to reviewing for NeurIPS 2026.
Feb 2026Variational Diffusion Unlearning was accepted to TMLR.
Sep 2025AVROBUSTBENCH was accepted to NeurIPS Datasets & Benchmarks.
Aug 2025Received a travel grant from the ICCV community!
Jun 2025BATCLIP was accepted to ICCV 2025.
May 2025We will organize the 1st Workshop on Multimodal Continual Learning at ICCV 2025.
Old news 2024 — 2026
May 2025Passed my qualifying examination and became a PhD candidate.
Mar 2025We will co-organize the 2nd Workshop on Test-Time Adaptation at ICML 2025.
Feb 2025I'll join Dolby Laboratories as a PhD Research Intern for Summer 2025.
Dec 2024PALM was accepted to AAAI 2025 as an oral presentation.
Nov 2024Served as a reviewer for CVPR 2025.
Oct 2024Variational Diffusion Unlearning was accepted to the NeurIPS SafeGenAI Workshop.
Sep 2024Our submodular optimization work for active 3D object detection was accepted to NeurIPS 2024.
Aug 2024Served as a reviewer for ICLR 2025.
Jul 2024Our work on DNN watermarking was accepted to ECCV 2024.

Publications

My full publication record is available on Google Scholar.

2026

arXiv

Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation

Chandler Timm C Doloriel, Yunbei Zhang, Sarthak Kumar Maharana, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah

arXiv, 2026

ECCV

Audio-Visual Continual Test-Time Adaptation without Forgetting

Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna, Yunhui Guo, Guan-Ming Su

European Conference on Computer Vision (ECCV), 2026

TMLR

Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

Sarthak Kumar Maharana*, Shambhavi Mishra*, Yunbei Zhang*, Shuaicheng Niu, Taki Hasan Rafi, Jihun Hamm, Marco Pedersoli, Jose Dolz, Yunhui Guo

Transactions on Machine Learning Research (TMLR), 2026

TMLR

Variational Diffusion Unlearning: A Variational Inference Framework for Unlearning in Diffusion Models under Data Constraints

Subhodip Panda, Varun M S, Shreyans Jain, Sarthak Kumar Maharana, Prathosh AP

Transactions on Machine Learning Research (TMLR), 2026

2025

NeurIPS

AVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time

Sarthak Kumar Maharana, Saksham Singh Kushwaha, Baoming Zhang, Adrian Rodriguez, Songtao Wei, Yapeng Tian, Yunhui Guo

Conference on Neural Information Processing Systems (NeurIPS) Datasets & Benchmarks, 2025

ICCV

BATCLIP: Bimodal Online Test-Time Adaptation for CLIP

Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Feris, Yunhui Guo

International Conference on Computer Vision (ICCV), 2025

AAAI

PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation

Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo

AAAI Conference on Artificial Intelligence (AAAI), 2025 · Oral

arXiv

SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation

Ruiyu Mao, Sarthak Kumar Maharana, Xulong Tang, Yunhui Guo

arXiv, 2025

2024

NeurIPS

STONE: A Submodular Optimization Framework for Active 3D Object Detection

Ruiyu Mao, Sarthak Kumar Maharana, Rishabh K Iyer, Yunhui Guo

Conference on Neural Information Processing Systems (NeurIPS), 2024

ECCV

Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data

Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo

European Conference on Computer Vision (ECCV), 2024

ICASSP

Acoustic-to-Articulatory Inversion for Dysarthric Speech: Are Pre-trained Self-Supervised Representations Favorable?

Sarthak Kumar Maharana, Krishna Kamal Adidam, Shoumik Nandi, Ajitesh Srivastava

ICASSP SASB Workshop, 2024

2021

ICASSP

Acoustic-to-Articulatory Inversion for Dysarthric Speech by Using Cross-Corpus Acoustic-Articulatory Data

Sarthak Kumar Maharana, Aravind Illa, Renuka Mannem, Yamini Belur, Preetie A. Shetty, Veeramani Preethish Kumar, Seena Vengalil, Kiran Polavarapu, Atchayaram Nalini, Prasanta Ghosh

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021

Miscellaneous

Experience

I work across academic and industrial research, connecting fundamental questions.

NEC Laboratories America, Inc.

Research Scientist Intern

Real-time reasoning and closed-loop trajectory planning for autonomous driving in long-tailed scenes.

Dolby Laboratories, Inc.

PhD Research Intern

Robust audio-visual learning in continual learning settings.

The University of Texas at Dallas

PhD Candidate · Computer Science

Advised by Dr. Yunhui Guo in the Data Efficient Intelligent Learning Lab.

Workshops

Contact

I’m always glad to discuss research collaborations and emerging ideas. I have a knack for finding interesting problems or digging into the teeny-tiny details of a paper. Feel free to contact!

Start a conversation