Sarthak Kumar Maharana

Sarthak Kumar Maharana

sarthakmaharana9811@gmail.com

I'm a CS PhD candidate at the University of Texas at Dallas, advised by Dr. Yunhui Guo. I'm also a part of the Data Efficient Intelligent Learning Lab. I broadly study computer vision with an emphasis on continual learning. My research is grounded in the belief that AI systems must continually adapt to the world, and not be stagnant.

Current research interests:

  1. Efficient continual learning systems capable of modeling long sequence data. There's a dire need to architect AI systems that scale and behave as sub-quadratic alternatives to transformers.
  2. Reasoning, planning, and generalization for autonomous driving.

In the initial years of my PhD, I explored continual learning at test-time and designed efficient schemes to make models robust and adaptable in open and dynamic environments. I spent the Summer of 2025 at Dolby Laboratories working on robust audio-visual learning in continual learning settings.

Before my PhD, I completed my Master's in Electrical Engineering from USC and a Bachelor's degree from IIIT Bhubaneswar, India. I've been fortunate to work with Dr. Yonggang Shi (USC), Dr. Shri Narayanan (USC), Dr. Ren Hongliang (NUS), Dr. Prasanta Kumar Ghosh (IISc), and Dr. Aurobinda Routray (IIT-Kharagpur).

I have published at top-tier ML/computer vision/signal processing venues such as TMLR, ICCV, NeurIPS (3x), AAAI, ECCV, and ICASSP (2x).

If my research interests align with yours, I'd love to chat, discuss, and explore potential collaborations. Feel free to reach out!

News

Papers

Audio-Visual Continual Test-Time Adaptation without Forgetting
Sarthak Kumar Maharana, Akshay Mehra, Bhavya Ramakrishna, Yunhui Guo, Guan-Ming Su
ICML CATS Workshop, 2026
Continual Test-Time Adaptation: A Comprehensive Survey
Under Review
Variational Diffusion Unlearning: A Variational Inference Framework for Unlearning in Diffusion Models under Data Constraints
Subhodip Panda, MS Varun, Shreyans Jain, Sarthak Kumar Maharana, Prathosh AP
TMLR 2026 & NeurIPS SafeGenAI Workshop 2024
AVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
NeurIPS (Datasets and Benchmarks) 2025 & DataMFM Workshop @ CVPR 2026
SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation
Ruiyu Mao, Sarthak Kumar Maharana, Xulong Tang, Yunhui Guo
Under Review
BATCLIP: Bimodal Online Test-Time Adaptation for CLIP
Sarthak Kumar Maharana, Baoming Zhang, Leonid Karlinsky, Rogerio Schmidt Feris, Yunhui Guo
ICCV 2025
PALM: Pushing Adaptive Learning Rate Mechanisms for Continual Test-Time Adaptation
Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo
AAAI 2025 (Oral)
STONE: A Submodular Optimization Framework for Active 3D Object Detection
Ruiyu Mao, Sarthak Kumar Maharana, Rishabh K Iyer, Yunhui Guo
NeurIPS 2024
Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo
ECCV 2024
Acoustic-to-Articulatory Inversion for Dysarthric Speech: Are Pre-Trained Self-Supervised Representations Favorable?
ICASSP 2024 Workshop on Self-supervision in Audio, Speech, and Beyond (SASB)
Acoustic-to-Articulatory Inversion for Dysarthric Speech by Using Cross-Corpus Acoustic-Articulatory Data
Sarthak Kumar Maharana, Aravind Illa, Renuka Mannem, Yamini Bellur, Veeramani Preethish Kumar, Seena Vengalil, Kiran Polavarapu, Nalini Atchayaram, Prasanta Kumar Ghosh
ICASSP 2021

Academic & Volunteer Work

Random