Sarthak Kumar Maharana

sarthak.maharana@utdallas.edu

Portrait of Sarthak Kumar Maharana

PhD Candidate

The University of Texas at Dallas

Email Google Scholar GitHub LinkedIn Twitter / X CV

I am a PhD Candidate in Computer Science at The University of Texas at Dallas, advised by Dr. Yunhui Guo.

I have spent quality time in research groups at NEC Laboratories America (with Yi-Wen Chen, Francesco Pittaluga, and Manmohan Chandraker) and Dolby Laboratories (with Akshay Mehra and Guan-Ming Su). I helped organize the 1st Workshop on Multimodal Continual Learning at ICCV 2025 and co-organized the 2nd Workshop on Test-Time Adaptation at ICML 2025.

Prior to my PhD, I earned my MS in Electrical Engineering from the University of Southern California in 2023 and my BTech in Electrical and Electronics Engineering from the IIIT, Bhubaneswar, India in 2020. During my undergrad, I interned at IISc Bangalore and IIT Kharagpur where I worked on amazing problems on speech production. A great start to my research career!

I am open to research conversations and collaborations. Feel free to reach out!

Outside research

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!

Recent news

Scroll to explore all updates.

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

Research

My full publication record is available on Google Scholar.

2027

WACV 2027

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

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027

Paper Code
WACV 2027

Reliable Continual Test-Time Adaptation under Long-Tailed Distributions

Taki Hasan Rafi, Sarthak Kumar Maharana, Chandler Timm C Doloriel, Wei Li, Junegak Joung, Dong-Kyu Chae

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2027

2026

ECCV 2026

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 & ICML 2026 Workshop on Continual Adaptation at Scale: Towards Sustainable AI

Paper Code Project
TMLR 2026

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

Paper Awesome CTTA
TMLR 2026

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

Paper

2025

NeurIPS D&B 2025

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 & CVPR 2026 Workshop on Emerging Directions in Data for Multimodal Foundation Models

Paper Code Project
ICCV 2025

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

Paper Code Project
AAAI 2025 · Oral

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

Paper Code Project
arXiv 2025

SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation

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

arXiv, 2025

arXiv

2024

NeurIPS 2024

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

Paper Code
ECCV 2024

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

Paper Code

2021

ICASSP 2021

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

Paper Poster Slides

Let's discuss research (or anything)!

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

Affiliations