Sarthak Kumar Maharana

According to our database, Sarthak Kumar Maharana authored at least 12 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Audio-Visual Continual Test-Time Adaptation without Forgetting.

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

CoRR, February, 2026

Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach.

Subhodip Panda, MS Varun, Shreyans Jain, Sarthak Kumar Maharana, Prathosh AP

Trans. Mach. Learn. Res., 2026

2025

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 A. P.

CoRR, October, 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

CoRR, June, 2025

SELECT: A Submodular Approach for Active LiDAR Semantic Segmentation.

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

CoRR, May, 2025

BATCLIP: Bimodal Online Test-Time Adaptation for CLIP.

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

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

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

Sarthak Kumar Maharana, Baoming Zhang, Yunhui Guo

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Enhancing Robustness of CLIP to Common Corruptions through Bimodal Test-Time Adaptation.

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

CoRR, 2024

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

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

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Acoustic-to-Articulatory Inversion for Dysarthric Speech: are Pre-Trained Self-Supervised Representations Favorable?

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

Proceedings of the IEEE International Conference on Acoustics, 2024

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

Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo

Proceedings of the Computer Vision - ECCV 2024, 2024

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 Shetty, Preethish-Kumar Veeramani, Seena Vengalil, Kiran Polavarapu, Atchayaram Nalini, Prasanta Kumar Ghosh

Proceedings of the IEEE International Conference on Acoustics, 2021