Souvik Kundu

According to our database, Souvik Kundu authored at least 18 papers between 2023 and 2024.

Collaborative distances:

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

2024

Bit-by-Bit: Investigating the Vulnerabilities of Binary Neural Networks to Adversarial Bit Flipping.

Shamik Kundu, Sanjay Das, Sayar Karmakar, Arnab Raha, Souvik Kundu, Yiorgos Makris, Kanad Basu

Trans. Mach. Learn. Res., 2024

AttentionBreaker: Adaptive Evolutionary Optimization for Unmasking Vulnerabilities in LLMs through Bit-Flip Attacks.

Sanjay Das, Swastik Bhattacharya, Souvik Kundu, Shamik Kundu, Anand Menon, Arnab Raha, Kanad Basu

CoRR, 2024

MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization.

Akshat Ramachandran, Souvik Kundu, Tushar Krishna

CoRR, 2024

LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding.

Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sungyub Kim, Eunho Yang

CoRR, 2024

Metron: Holistic Performance Evaluation Framework for LLM Inference Systems.

Amey Agrawal, Anmol Agarwal, Nitin Kedia, Jayashree Mohan, Souvik Kundu, Nipun Kwatra, Ramachandran Ramjee, Alexey Tumanov

CoRR, 2024

CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs.

Akshat Ramachandran, Souvik Kundu, Tushar Krishna

CoRR, 2024

ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization.

Haoran You, Yipin Guo, Yichao Fu, Wei Zhou, Huihong Shi, Xiaofan Zhang, Souvik Kundu, Amir Yazdanbakhsh, Yingyan Lin

CoRR, 2024

Demystifying Platform Requirements for Diverse LLM Inference Use Cases.

Abhimanyu Bambhaniya, Ritik Raj, Geonhwa Jeong, Souvik Kundu, Sudarshan Srinivasan, Midhilesh Elavazhagan, Madhu Kumar, Tushar Krishna

CoRR, 2024

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao

CoRR, 2024

Junk DNA Hypothesis: Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMs.

Lu Yin, Ajay Kumar Jaiswal, Shiwei Liu, Souvik Kundu, Zhangyang Wang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Fusing Models with Complementary Expertise.

Hongyi Wang, Felipe Maia Polo, Yuekai Sun, Souvik Kundu, Eric P. Xing, Mikhail Yurochkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Analyzing Adversarial Vulnerabilities of Graph Lottery Tickets.

Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, Souvik Kundu, Pierluigi Nuzzo

Proceedings of the IEEE International Conference on Acoustics, 2024

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data.

Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets.

Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, Souvik Kundu, Pierluigi Nuzzo

CoRR, 2023

Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity.

Lu Yin, Shiwei Liu, Ajay Jaiswal, Souvik Kundu, Zhangyang Wang

CoRR, 2023

Don't just prune by magnitude! Your mask topology is a secret weapon.

Duc Hoang, Souvik Kundu, Shiwei Liu, Zhangyang Wang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations.

Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan Celine Lin

Proceedings of the International Conference on Machine Learning, 2023

Vision HGNN: An Image is More than a Graph of Nodes.

Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023