Souvik Kundu - RankMe

94 papers A* 7A 6B 1C 3Misc 6Journal 52Unranked 19

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models. ASPLOS (1) Yuchen Xia, Divyam Sharma, Yichao Yuan, Souvik Kundu, Nishil Talati
2026	J	`jnl`	Power-SMC: Low-Latency Sequence-Level Power Sampling for Training-Free LLM Reasoning. CoRR Seyedarmin Azizi, Erfan Baghaei Potraghloo, Minoo Ahmadi, Souvik Kundu, Massoud Pedram
2025	—	`conf`	LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling. EMNLP (Findings) Zeyu Liu, Souvik Kundu, Lianghao Jiang, Anni Li, Srikanth Ronanki, Sravan Babu Bodapati, Gourav Datta, Peter Anthony Beerel
2025	J	`jnl`	LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling. CoRR Zeyu Liu, Souvik Kundu, Lianghao Jiang, Anni Li, Srikanth Ronanki, Sravan Bodapati, Gourav Datta, Peter A. Beerel
2025	—	`conf`	LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression. NAACL (Findings) Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal
2025	J	`jnl`	LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression. CoRR Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal
2025	A*	`conf`	MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba. ICLR Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram
2025	A	`conf`	MaskVD: Region Masking for Efficient Video Object Detection. WACV Sreetama Sarkar, Gourav Datta, Souvik Kundu, Kai Zheng, Chirayata Bhattacharyya, Peter A. Beerel
2025	A*	`conf`	Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression. EMNLP Sreetama Sarkar, Yue Che, Alex Gavin, Peter Anthony Beerel, Souvik Kundu
2025	J	`jnl`	Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression. CoRR Sreetama Sarkar, Yue Che, Alex Gavin, Peter A. Beerel, Souvik Kundu
2025	J	`jnl`	MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models. CoRR Yuchen Xia, Divyam Sharma, Yichao Yuan, Souvik Kundu, Nishil Talati
2025	J	`jnl`	RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning. CoRR Jingqi Xu, Jingxi Lu, Chenghao Li, Sreetama Sarkar, Souvik Kundu, Peter A. Beerel
2025	J	`jnl`	SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models. CoRR Jiayi Tian, Seyedarmin Azizi, Yequan Zhao, Erfan Baghaei Potraghloo, Sean McPherson, Sharath Nittur Sridhar, Zhengyang Wang, Zheng Zhang, Massoud Pedram, Souvik Kundu
2025	J	`jnl`	Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement. CoRR Yuchen Xia, Souvik Kundu, Mosharaf Chowdhury, Nishil Talati
2025	J	`jnl`	Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation. CoRR Erfan Baghaei Potraghloo, Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2024	—	`conf`	AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models. ACL (Short Papers) Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter A. Beerel
2024	J	`jnl`	AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models. CoRR Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter Anthony Beerel
2024	—	`conf`	Block Selective Reprogramming for On-device Training of Vision Transformers. CVPR Workshops Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel
2024	J	`jnl`	Block Selective Reprogramming for On-device Training of Vision Transformers. CoRR Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel
2024	—	`conf`	CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-training Quantization of ViTs. ECCV (67) Akshat Ramachandran, Souvik Kundu, Tushar Krishna
2024	J	`jnl`	CiMNet: Towards Joint Optimization for DNN Architecture and Configuration for Compute-In-Memory Hardware. CoRR Souvik Kundu, Anthony Sarah, Vinay Joshi, Om Ji Omer, Sreenivas Subramoney
2024	—	`conf`	DIA: Diffusion based Inverse Network Attack on Collaborative Inference. CVPR Workshops Dake Chen, Shiduo Li, Yuke Zhang, Chenghao Li, Souvik Kundu, Peter A. Beerel
2024	—	`conf`	LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation. EMNLP (Findings) Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2024	J	`jnl`	LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation. CoRR Seyedarmin Azizi, Souvik Kundu, Massoud Pedram
2024	J	`jnl`	Linearizing Models for Efficient yet Robust Private Inference. CoRR Sreetama Sarkar, Souvik Kundu, Peter A. Beerel
2024	J	`jnl`	MaskVD: Region Masking for Efficient Video Object Detection. CoRR Sreetama Sarkar, Gourav Datta, Souvik Kundu, Kai Zheng, Chirayata Bhattacharyya, Peter A. Beerel
2024	—	`conf`	RLNet: Robust Linearized Networks for Efficient Private Inference. CVPR Workshops Sreetama Sarkar, Souvik Kundu, Peter A. Beerel
2024	Misc	`conf`	Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural Networks: from Algorithms to Technology. ICASSP Souvik Kundu, Rui-Jie Zhu, Akhilesh Jaiswal, Peter A. Beerel
2024	Misc	`conf`	Sensi-Bert: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model. ICASSP Souvik Kundu, Sharath Nittur Sridhar, Maciej Szankin, Sairam Sundaresan
2024	—	`conf`	Understanding the Performance and Estimating the Cost of LLM Fine-Tuning. IISWC Yuchen Xia, Jiho Kim, Yuhan Chen, Haojie Ye, Souvik Kundu, Cong Callie Hao, Nishil Talati
2024	J	`jnl`	Understanding the Performance and Estimating the Cost of LLM Fine-Tuning. CoRR Yuchen Xia, Jiho Kim, Yuhan Chen, Haojie Ye, Souvik Kundu, Cong Hao, Nishil Talati
2024	—	`conf`	What Makes Vision Transformers Robust Towards Bit-Flip Attack? ICPR (8) Xuan Zhou, Souvik Kundu, Dake Chen, Jie Huang, Peter A. Beerel
2023	A*	`conf`	C DAC Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel
2023	J	`jnl`	C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference. CoRR Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel
2023	A	`conf`	FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-off between Accuracy and Robustness. WACV Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel
2023	J	`jnl`	FireFly A Synthetic Dataset for Ember Detection in Wildfire. CoRR Yue Hu, Xinan Ye, Yifei Liu, Souvik Kundu, Gourav Datta, Srikar Mutnuri, Namo Asavisanu, Nora Ayanian, Konstantinos Psounis, Peter A. Beerel
2023	—	`conf`	FireFly: A Synthetic Dataset for Ember Detection in Wildfire. ICCV (Workshops) Yue Hu, Xinan Ye, Yifei Liu, Souvik Kundu, Gourav Datta, Srikar Mutnuri, Namo Asavisanu, Nora Ayanian, Konstantinos Psounis, Peter A. Beerel
2023	Misc	`conf`	In-Sensor & Neuromorphic Computing Are all You Need for Energy Efficient Computer Vision. ICASSP Gourav Datta, Zeyu Liu, Md. Abdullah-Al Kaiser, Souvik Kundu, Joe Mathai, Zihan Yin, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel
2023	—	`conf`	InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning. ICCV (Workshops) Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah
2023	J	`jnl`	InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning. CoRR Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah
2023	A*	`conf`	Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference. ICLR Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter A. Beerel
2023	J	`jnl`	Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference. CoRR Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter A. Beerel
2023	—	`conf`	Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference. CVPR Workshops Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel
2023	J	`jnl`	Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference. CoRR Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel
2023	J	`jnl`	Overcoming Resource Constraints in Federated Learning: Large Models Can Be Trained with only Weak Clients. Trans. Mach. Learn. Res. Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr
2023	Misc	`conf`	Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments. ICASSP Haonan Wang, Connor Imes, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters
2023	A	`conf`	RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference. ICCAD Dake Chen, Yuke Zhang, Souvik Kundu, Chenghao Li, Peter A. Beerel
2023	J	`jnl`	Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural networks: from Algorithms to Technology. CoRR Souvik Kundu, Rui-Jie Zhu, Akhilesh Jaiswal, Peter A. Beerel
2023	J	`jnl`	Revisiting Sparsity Hunting in Federated Learning: Why does Sparsity Consensus Matter? Trans. Mach. Learn. Res. Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr
2023	A*	`conf`	SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation. ICCV Yuke Zhang, Dake Chen, Souvik Kundu, Chenghao Li, Peter A. Beerel
2023	A	`conf`	Self-Attentive Pooling for Efficient Deep Learning. WACV Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel
2023	J	`jnl`	Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient BERT. CoRR Souvik Kundu, Sharath Nittur Sridhar, Maciej Szankin, Sairam Sundaresan
2023	J	`jnl`	Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs. CoRR Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel
2023	Misc	`conf`	Sparse Mixture Once-for-all Adversarial Training for Efficient in-situ Trade-off between Accuracy and Robustness of DNNs. ICASSP Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel
2023	—	`conf`	Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M). ACM Great Lakes Symposium on VLSI Md. Abdullah-Al Kaiser, Gourav Datta, Sreetama Sarkar, Souvik Kundu, Zihan Yin, Manas Garg, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal
2023	J	`jnl`	Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M). CoRR Md. Abdullah-Al Kaiser, Gourav Datta, Sreetama Sarkar, Souvik Kundu, Zihan Yin, Manas Garg, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal
2023	C	`conf`	ViTA: A Vision Transformer Inference Accelerator for Edge Applications. ISCAS Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, Peter A. Beerel
2023	J	`jnl`	ViTA: A Vision Transformer Inference Accelerator for Edge Applications. CoRR Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, Peter A. Beerel
2022	J	`jnl`	A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness. CoRR Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel
2022	A	`conf`	BMPQ: Bit-Gradient Sensitivity-Driven Mixed-Precision Quantization of DNNs from Scratch. DATE Souvik Kundu, Shikai Wang, Qirui Sun, Peter A. Beerel, Massoud Pedram
2022	J	`jnl`	Federated Learning of Large Models at the Edge via Principal Sub-Model Training. CoRR Yue Niu, Saurav Prakash, Souvik Kundu, Sunwoo Lee, Salman Avestimehr
2022	J	`jnl`	Federated Sparse Training: Lottery Aware Model Compression for Resource Constrained Edge. CoRR Sara Babakniya, Souvik Kundu, Saurav Prakash, Yue Niu, Salman Avestimehr
2022	J	`jnl`	In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Vision. CoRR Gourav Datta, Zeyu Liu, Md. Abdullah-Al Kaiser, Souvik Kundu, Joe Mathai, Zihan Yin, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel
2022	C	`conf`	P VLSI-SoC Gourav Datta, Souvik Kundu, Zihan Yin, Joe Mathai, Zeyu Liu, Zixu Wang, Mulin Tian, Shunlin Lu, Ravi Teja Lakkireddy, Andrew G. Schmidt, Wael Abd-Almageed, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel
2022	J	`jnl`	P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applications. CoRR Gourav Datta, Souvik Kundu, Zihan Yin, Ravi Teja Lakkireddy, Joe Mathai, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal
2022	C	`conf`	PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices. DSD Yang Hu, Connor Imes, Xuanang Zhao, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters
2022	J	`jnl`	QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer Pipelines in Dynamic Edge Environments. CoRR Haonan Wang, Connor Imes, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters
2022	J	`jnl`	Self-Attentive Pooling for Efficient Deep Learning. CoRR Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel
2022	J	`jnl`	Toward Adversary-aware Non-iterative Model Pruning through Dynamic Network Rewiring of DNNs. ACM Trans. Embed. Comput. Syst. Souvik Kundu, Yao Fu, Bill Ye, Peter A. Beerel, Massoud Pedram
2021	A*	`conf`	Analyzing the Confidentiality of Undistillable Teachers in Knowledge Distillation. NeurIPS Souvik Kundu, Qirui Sun, Yao Fu, Massoud Pedram, Peter A. Beerel
2021	Misc	`conf`	AttentionLite: Towards Efficient Self-Attention Models for Vision. ICASSP Souvik Kundu, Sairam Sundaresan
2021	J	`jnl`	AttentionLite: Towards Efficient Self-Attention Models for Vision. CoRR Souvik Kundu, Sairam Sundaresan
2021	J	`jnl`	BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch. CoRR Souvik Kundu, Shikai Wang, Qirui Sun, Peter A. Beerel, Massoud Pedram
2021	—	`conf`	DNR: A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs. ASP-DAC Souvik Kundu, Mahdi Nazemi, Peter A. Beerel, Massoud Pedram
2021	A*	`conf`	HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise. ICCV Souvik Kundu, Massoud Pedram, Peter A. Beerel
2021	J	`jnl`	HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise. CoRR Souvik Kundu, Massoud Pedram, Peter A. Beerel
2021	J	`jnl`	HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification. CoRR Gourav Datta, Souvik Kundu, Akhilesh R. Jaiswal, Peter A. Beerel
2021	J	`jnl`	Pipeline Parallelism for Inference on Heterogeneous Edge Computing. CoRR Yang Hu, Connor Imes, Xuanang Zhao, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters
2021	A	`conf`	Spike-Thrift: Towards Energy-Efficient Deep Spiking Neural Networks by Limiting Spiking Activity via Attention-Guided Compression. WACV Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel
2021	J	`jnl`	Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression. CoRR Souvik Kundu, Gourav Datta, Massoud Pedram, Peter A. Beerel
2021	B	`conf`	Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding. IJCNN Gourav Datta, Souvik Kundu, Peter A. Beerel
2021	J	`jnl`	Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding. CoRR Gourav Datta, Souvik Kundu, Peter A. Beerel
2020	J	`jnl`	A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs. CoRR Souvik Kundu, Mahdi Nazemi, Peter A. Beerel, Massoud Pedram
2020	J	`jnl`	Attention-based Image Upsampling. CoRR Souvik Kundu, Hesham Mostafa, Sharath Nittur Sridhar, Sairam Sundaresan
2020	J	`jnl`	Pre-Defined Sparsity for Low-Complexity Convolutional Neural Networks. IEEE Trans. Computers Souvik Kundu, Mahdi Nazemi, Massoud Pedram, Keith M. Chugg, Peter A. Beerel
2020	J	`jnl`	Pre-defined Sparsity for Low-Complexity Convolutional Neural Networks. CoRR Souvik Kundu, Mahdi Nazemi, Massoud Pedram, Keith M. Chugg, Peter A. Beerel
2020	J	`jnl`	qBSA: Logic Design of a 32-bit Block-Skewed RSFQ Arithmetic Logic Unit. CoRR Souvik Kundu, Gourav Datta, Peter A. Beerel, Massoud Pedram
2019	J	`jnl`	A Pre-defined Sparse Kernel Based Convolution for Deep CNNs. CoRR Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter A. Beerel, Keith M. Chugg
2019	—	`conf`	CSrram: Area-Efficient Low-Power Ex-Situ Training Framework for Memristive Neuromorphic Circuits Based on Clustered Sparsity. ISVLSI Arash Fayyazi, Souvik Kundu, Shahin Nazarian, Peter A. Beerel, Massoud Pedram
2019	J	`jnl`	Metastability-Resilient Synchronization FIFO for SFQ Logic. CoRR Gourav Datta, Haolin Cong, Souvik Kundu, Peter A. Beerel
2019	—	`conf`	pSConv: A Pre-defined S parse Kernel Based Convolution for Deep CNNs. Allerton Souvik Kundu, Saurav Prakash, Haleh Akrami, Peter A. Beerel, Keith M. Chugg
2018	—	`conf`	A Highly Parallel FPGA Implementation of Sparse Neural Network Training. ReConFig Sourya Dey, Diandian Chen, Zongyang Li, Souvik Kundu, Kuan-Wen Huang, Keith M. Chugg, Peter A. Beerel
2018	J	`jnl`	A Highly Parallel FPGA Implementation of Sparse Neural Network Training. CoRR Sourya Dey, Diandian Chen, Zongyang Li, Souvik Kundu, Kuan-Wen Huang, Keith M. Chugg, Peter A. Beerel
2018	J	`jnl`	SpRRAM: A Predefined Sparsity Based Memristive Neuromorphic Circuit for Low Power Application. CoRR Arash Fayyazi, Souvik Kundu, Shahin Nazarian, Peter A. Beerel, Massoud Pedram