Kundu, Souvik

47 publications

TMLR 2025 Assortment of Attention Heads: Accelerating Federated PEFT with Head Pruning and Strategic Client Selection Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda

TMLR 2025 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

TMLR 2025 Fast and Cost-Effective Speculative Edge-Cloud Decoding with Early Exits Yeshwanth Venkatesha, Souvik Kundu, Priyadarshini Panda

ICLRW 2025 LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-Regressive Models Sihwan Park, Doohyuk Jang, Sung-Yub Kim, Souvik Kundu, Eunho Yang

ICLR 2025 LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding Doohyuk Jang, Sihwan Park, June Yong Yang, Yeonsung Jung, Jihun Yun, Souvik Kundu, Sung-Yub Kim, Eunho Yang

ICLR 2025 MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram

WACV 2025 MaskVD: Region Masking for Efficient Video Object Detection Sreetama Sarkar, Gourav Datta, Souvik Kundu, Kai Zheng, Chirayata Bhattacharyya, Peter A. Beerel

ICML 2025 On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving Yeonju Ro, Zhenyu Zhang, Souvik Kundu, Zhangyang Wang, Aditya Akella

ICCV 2025 OuroMamba: A Data-Free Quantization Framework for Vision Mamba Akshat Ramachandran, Mingyu Lee, Huan Xu, Souvik Kundu, Tushar Krishna

ICLRW 2025 PRISM: Enhancing Protein Inverse Folding Through Fine-Grained Retrieval on Structure-Sequence Multimodal Representations Sazan Mahbub, Souvik Kundu, Eric P. Xing

TMLR 2025 Pushing the Limits of Sparsity: A Bag of Tricks for Extreme Pruning Andy Li, Aiden Durrant, Milan Markovic, Tianjin Huang, Souvik Kundu, Tianlong Chen, Lu Yin, Georgios Leontidis

ICLRW 2025 QMambaExtend: Improving Long-Context Extension of Memory-Efficient Mamba Models Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram

ICLR 2025 Scaling Long Context Training Data by Long-Distance Referrals Yonghao Zhuang, Lanxiang Hu, Longfei Yun, Souvik Kundu, Zhengzhong Liu, Eric P. Xing, Hao Zhang

NeurIPS 2025 Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu, Massoud Pedram

TMLR 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

CVPRW 2024 Block Selective Reprogramming for On-Device Training of Vision Transformers Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel

NeurIPSW 2024 CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing Wenhao Zheng, Yixiao Chen, Weitong Zhang, Souvik Kundu, Yun Li, Zhengzhong Liu, Eric P. Xing, Hongyi Wang, Huaxiu Yao

ECCV 2024 CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs Akshat Ramachandran, Souvik Kundu, Tushar Krishna

CVPRW 2024 DIA: Diffusion Based Inverse Network Attack on Collaborative Inference Dake Chen, Shiduo Li, Yuke Zhang, Chenghao Li, Souvik Kundu, Peter A. Beerel

ICLR 2024 Fusing Models with Complementary Expertise Hongyi Wang, Felipe Maia Polo, Yuekai Sun, Souvik Kundu, Eric Xing, Mikhail Yurochkin

ECCV 2024 GenQ: Quantization in Low Data Regimes with Generative Synthetic Data Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda

ICML 2024 Junk DNA Hypothesis: Pruning Small Pre-Trained Weights $\textit{Irreversibly}$ and $\textit{Monotonically}$ Impairs “Difficult" Downstream Tasks in LLMs Lu Yin, Ajay Kumar Jaiswal, Shiwei Liu, Souvik Kundu, Zhangyang Wang

ICLRW 2024 Linearizing Models for Efficient yet Robust Private Inference Sreetama Sarkar, Souvik Kundu, Peter Anthony Beerel

CVPRW 2024 RLNet: Robust Linearized Networks for Efficient Private Inference Sreetama Sarkar, Souvik Kundu, Peter A. Beerel

NeurIPS 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

TMLR 2024 Unveiling Adversarially Robust Graph Lottery Tickets Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, Souvik Kundu, Pierluigi Nuzzo

NeurIPS 2023 Don’t Just Prune by Magnitude! Your Mask Topology Is a Secret Weapon Duc Hoang, Souvik Kundu, Shiwei Liu, Zhangyang "Atlas" Wang

WACV 2023 FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-Off Between Accuracy and Robustness Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel

ICCVW 2023 FireFly: A Synthetic Dataset for Ember Detection in Wildfire Yue Hu, Xinan Ye, Yifei Liu, Souvik Kundu, Gourav Datta, Srikar Mutnuri, Namo Asavisanu, Nora Ayanian, Konstantinos Psounis, Peter A. Beerel

NeurIPSW 2023 Fusing Models with Complementary Expertise Hongyi Wang, Felipe Maia Polo, Yuekai Sun, Souvik Kundu, Eric P. Xing, Mikhail Yurochkin

ICCVW 2023 InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah

NeurIPSW 2023 InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah

ICLR 2023 Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter Anthony Beerel

CVPRW 2023 Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel

ICML 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

TMLR 2023 Overcoming Resource Constraints in Federated Learning: Large Models Can Be Trained with Only Weak Clients Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr

TMLR 2023 Revisiting Sparsity Hunting in Federated Learning: Why Does Sparsity Consensus Matter? Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr

ICCV 2023 SAL-ViT: Towards Latency Efficient Private Inference on ViT Using Selective Attention Search with a Learnable SoftMax Approximation Yuke Zhang, Dake Chen, Souvik Kundu, Chenghao Li, Peter A. Beerel

WACV 2023 Self-Attentive Pooling for Efficient Deep Learning Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel

NeurIPSW 2023 Sparse but Strong: Crafting Adversarially Robust Graph Lottery Tickets Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, Souvik Kundu, Pierluigi Nuzzo

ICCV 2023 Vision HGNN: An Image Is More than a Graph of Nodes Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang

NeurIPSW 2022 Federated Learning of Large Models at the Edge via Principal Sub-Model Training Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr

NeurIPSW 2022 Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr

NeurIPS 2021 Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation Souvik Kundu, Qirui Sun, Yao Fu, Massoud Pedram, Peter Beerel

ICCV 2021 HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise Souvik Kundu, Massoud Pedram, Peter A. Beerel

WACV 2021 Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel

AAAI 2018 A Question-Focused Multi-Factor Attention Network for Question Answering Souvik Kundu, Hwee Tou Ng