Mahesh Subedar

30 papers A* 3A 2B 2Misc 1Journal 14Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	SunPar: An Analytical Design Space Exploration Framework Modeling Performance Uncertainty in Sparse AI Accelerators. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. Jiacong Sun, Man Shi, Mahesh Subedar, Georges G. E. Gielen, Marian Verhelst
2025	J	`jnl`	DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators. CoRR Charles Hong, Qijing Huang, Grace Dinh, Mahesh Subedar, Yakun Sophia Shao
2025	J	`jnl`	EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs. CoRR Davide Ettori, Nastaran Darabi, Sina Tayebati, Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo, Amit Ranjan Trivedi
2025	Misc	`conf`	FUVAS: Few-shot Unsupervised Video Anomaly Segmentation via Low-Rank Factorization of Spatio-Temporal Features. ICASSP Jiaxiang Jiang, Ibrahima J. Ndiour, Mahesh Subedar, Omesh Tickoo
2025	J	`jnl`	PEFA-AI: Advancing Open-source LLMs for RTL generation using Progressive Error Feedback Agentic-AI. CoRR Athma Narayanan, Mahesh Subedar, Omesh Tickoo
2024	A	`conf`	Multi-Objective Software-Hardware Co-Optimization for HD-PIM via Noise-Aware Bayesian Optimization. ICCAD Chien-Yi Yang, Minxuan Zhou, Flavio Ponzina, Suraj Sathya Prakash, Raid Ayoub, Pietro Mercati, Mahesh Subedar, Tajana Rosing
2024	J	`jnl`	Parameter-Efficient Active Learning for Foundational models. CoRR Athmanarayanan Lakshmi Narayanan, Ranganath Krishnan, Amrutha Machireddy, Mahesh Subedar
2023	A*	`conf`	DOSA: Differentiable Model-Based One-Loop Search for DNN Accelerators. MICRO Charles Hong, Qijing Huang, Grace Dinh, Mahesh Subedar, Yakun Sophia Shao
2023	—	`conf`	Quantization for Bayesian Deep Learning: Low-Precision Characterization and Robustness. IISWC Jun-Liang Lin, Ranganath Krishnan, Keyur Ruganathbhai Ranipa, Mahesh Subedar, Vrushabh Sanghavi, Meena Arunachalam, Omesh Tickoo, Ravishankar Iyer, Mahmut Taylan Kandemir
2022	B	`conf`	Learning A Continuous and Reconstructible Latent Space for Hardware Accelerator Design. ISPASS Qijing Huang, Charles Hong, John Wawrzynek, Mahesh Subedar, Yakun Sophia Shao
2022	A	`conf`	Partially-Supervised Novel Object Captioning Using Context from Paired Data. BMVC Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo
2021	J	`jnl`	Data augmentation to improve robustness of image captioning solutions. CoRR Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo
2021	J	`jnl`	Improving Robustness and Efficiency in Active Learning with Contrastive Loss. CoRR Ranganath Krishnan, Nilesh A. Ahuja, Alok Sinha, Mahesh Subedar, Omesh Tickoo, Ravi Iyer
2021	J	`jnl`	Mitigating Sampling Bias and Improving Robustness in Active Learning. CoRR Ranganath Krishnan, Alok Sinha, Nilesh A. Ahuja, Mahesh Subedar, Omesh Tickoo, Ravi Iyer
2021	J	`jnl`	Partially-supervised novel object captioning leveraging context from paired data. CoRR Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo
2020	J	`jnl`	B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning. CoRR Shashank Bujimalla, Mahesh Subedar, Omesh Tickoo
2020	A*	`conf`	Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes. AAAI Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo
2019	J	`jnl`	Deep Probabilistic Models to Detect Data Poisoning Attacks. CoRR Mahesh Subedar, Nilesh A. Ahuja, Ranganath Krishnan, Ibrahima J. Ndiour, Omesh Tickoo
2019	—	`conf`	Efficient Priors for Scalable Variational Inference in Bayesian Deep Neural Networks. ICCV Workshops Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo
2019	J	`jnl`	MOPED: Efficient priors for scalable variational inference in Bayesian deep neural networks. CoRR Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo
2019	—	`conf`	Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference. CVPR Workshops Mahesh Subedar, Ranganath Krishnan, Paulo Lopez-Meyer, Omesh Tickoo, Jonathan Huang
2019	A*	`conf`	Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference. ICCV Mahesh Subedar, Ranganath Krishnan, Paulo Lopez-Meyer, Omesh Tickoo, Jonathan Huang
2018	J	`jnl`	BAR: Bayesian Activity Recognition using variational inference. CoRR Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo
2018	J	`jnl`	Uncertainty aware multimodal activity recognition with Bayesian inference. CoRR Mahesh Subedar, Ranganath Krishnan, Paulo Lopez-Meyer, Omesh Tickoo, Jonathan Huang
2017	—	`conf`	A Factorization Approach for Enabling Structure-from-Motion/SLAM Using Integer Arithmetic. ICCV Workshops Nilesh A. Ahuja, Mahesh Subedar, Omesh Tickoo, Yeongseon Lee
2015	—	`—`	Visual Quality with a Focus on 3D Blur Discrimination and Texture Granularity. Mahesh Subedar
2014	—	`conf`	Study of blur discrimination for 3D stereo viewing. SD&A Mahesh Subedar, Lina J. Karam
2008	—	`conf`	A Comparative Study of Color and Contrast Enhancement for Still Images and Consumer Video Applications. CIC Abhijit Sarkar, Mark D. Fairchild, Jorge E. Caviedes, Mahesh Subedar
2004	—	`conf`	An embedded scaling-based arbitrary shape region-of-interest coding method for JPEG2000. ICASSP (3) Mahesh Subedar, Lina J. Karam, Glen P. Abousleman
2004	B	`conf`	JPEG2000-based shape adaptive algorithm for the efficient coding of multiple regions-of interest. ICIP Mahesh Subedar, Lina J. Karam, Glen P. Abousleman