Kundu, Souvik
- GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
2024/03/08 by Hao Kang, Qingru Zhang, Kang, Hao +11 · 20 citations
Computer Science · #Advanced Data Storage Technologies #Algorithms and Data Compression #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Packet Processing and Optimization
- HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep\n Spiking Neural Networks by Training with Crafted Input Noise
2021/10/06 by Souvik Kundu, Kundu, Souvik, Massoud Pedram +3 · 9 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Ferroelectric and Negative Capacitance Devices
- Understanding the Performance and Estimating the Cost of LLM Fine-Tuning
2024/08/08 by Yuchen Xia, Xia, Yuchen, J. Kim +11 · 12 citations
Computer Science · Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Iterative Learning Control Systems #Machine Learning (cs.LG) #Simulation Techniques and Applications
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
2024/06/10 by Haoran You, Yipin Guo, You, Haoran +15 · 10 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Machine Learning (cs.LG) #Mathematics, Computing, and Information Processing #Natural Language Processing Techniques
- LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
2024/10/04 by Jang, Doohyuk, Park, Sihwan, Yang, June Yong +5 · 12 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- SEAL: Steerable Reasoning Calibration of Large Language Models for Free
2025/04/07 by Chen, Runjin, Zhang, Zhenyu, Hong, Junyuan +2 · 18 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences
- GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMs
2024/11/21 by Sanjay Das, Das, Sanjay, Souvik Kundu +10 · 12 citations
Computer Science · #Advanced Malware Detection Techniques #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Security and Verification in Computing
- Self-Attentive Pooling for Efficient Deep Learning
2022/09/16 by Fang Chen, Chen, Fang, Gourav Datta +5 · 4 citations
Computer Science · #Advanced Neural Network Applications #Image Enhancement Techniques #Domain Adaptation and Few-Shot Learning
- Fusing Models with Complementary Expertise
2023/10/02 by Hongyi Wang, Wang, Hongyi, Felipe Maia Polo +9 · 5 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Multimodal Machine Learning Applications #Topic Modeling
- MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization
2024/11/08 by Ramachandran, Akshat, Kundu, Souvik, Krishna, Tushar · 7 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)
- CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
2025/02/04 by Wenhao Zheng, Zheng, Wenhao, Yixiao Chen +15 · 8 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Performance (cs.PF) #Topic Modeling
- Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
2023/01/23 by Souvik Kundu, Kundu, Souvik, Shunlin Lu +7 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques
- Hybrid Ranking Network for Text-to-SQL
2020/08/11 by Lyu, Qin, Chakrabarti, Kaushik, Hathi, Shobhit +3 · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Pipeline Parallelism for Inference on Heterogeneous Edge Computing
2021/10/28 by Yang Hu, Hu, Yang, Connor Imes +11 · 2 citations
Computer Science · #Advanced Neural Network Applications #Distributed #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #Stochastic Gradient Optimization Techniques #and Cluster Computing (cs.DC)
- AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models
2024/03/20 by Zeyu Liu, Liu, Zeyu, Souvik Kundu +9 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Graphics and Visualization Techniques #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Neural Networks and Applications
- Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
2025/05/22 by Sarkar, Sreetama, Che, Yue, Gavin, Alex +2 · 7 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
2023/06/10 by Yonggan Fu, Fu, Yonggan, Ye Yuan +9 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Advanced Neural Network Applications #Generative Adversarial Networks and Image Synthesis
- GenQ: Quantization in Low Data Regimes with Generative Synthetic Data
2023/12/07 by Yuhang Li, Li, Yuhang, Youngeun Kim +5 · 2 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multimodal Machine Learning Applications
- Block Selective Reprogramming for On-device Training of Vision Transformers
2024/03/25 by Sarkar, Sreetama, Kundu, Souvik, Zheng, Kai +1 · 2 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
2024/07/07 by Akshat Ramachandran, Souvik Kundu, Ramachandran, Akshat +3 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning and ELM #electronic engineering #information engineering
- HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification
2021/07/26 by Gourav Datta, Souvik Kundu, Datta, Gourav +5 · 1 citation
Engineering · #Advanced Memory and Neural Computing #CCD and CMOS Imaging Sensors #FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE) #Remote-Sensing Image Classification
- LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation
2024/06/18 by Azizi, Seyedarmin, Kundu, Souvik, Pedram, Massoud · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Understanding of Emotion Perception from Art
2021/10/13 by Digbalay Bose, Bose, Digbalay, Krishna Somandepalli +9 · 1 citation
Computer Science · Neuroscience · #Multimodal Machine Learning Applications #Aesthetic Perception and Analysis #Generative Adversarial Networks and Image Synthesis
- Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems
2024/07/09 by Amey Agrawal, Anmol Agarwal, Agrawal, Amey +13 · 2 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Data Mining Algorithms and Applications #Data Quality and Management #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Parallel #Semantic Web and Ontologies #and Cluster Computing (cs.DC)
- LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
2025/02/10 by Park, Sihwan, Jang, Doohyuk, Kim, Sungyub +2 · 3 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models
2025/03/15 by Yuchen Xia, Divyam Sharma, Xia, Yuchen +6 · 4 citations
Computer Science · #Computer Graphics and Visualization Techniques #Generative Adversarial Networks and Image Synthesis #Image Enhancement Techniques
- P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applications
2022/03/07 by Datta, Gourav, Kundu, Souvik, Yin, Zihan +5 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)
- Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs
2022/12/27 by Souvik Kundu, Sairam Sundaresan, Kundu, Souvik +9 · 1 citation
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Integrated Circuits and Semiconductor Failure Analysis
- C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference
2023/04/26 by Zhang, Yuke, Chen, Dake, Kundu, Souvik +3 · 1 citation
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference
2023/04/26 by Souvik Kundu, Kundu, Souvik, Yuke Zhang +5 · 1 citation
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- FireFly A Synthetic Dataset for Ember Detection in Wildfire
2023/08/06 by Hu, Yue, Ye, Xinan, Liu, Yifei +7 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.4 #Machine Learning (cs.LG)
- Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits
2025/05/27 by Yeshwanth Venkatesha, Venkatesha, Yeshwanth, Souvik Kundu +3 · 4 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Artificial Intelligence (cs.AI) #Distributed #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Parallel #Robotics (cs.RO) #Robotics and Automated Systems #and Cluster Computing (cs.DC)
- Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models
2024/06/03 by Abhimanyu Rajeshkumar Bambhaniya, R. Jeberson Retna Raj, Bambhaniya, Abhimanyu +14 · 1 citation
Business, Management and Accounting · Computer Science · Social Sciences · #Access Control and Trust #Artificial Intelligence (cs.AI) #Business Process Modeling and Analysis #Digital Rights Management and Security #Distributed #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG) #Parallel #and Cluster Computing (cs.DC)
- OuroMamba: A Data-Free Quantization Framework for Vision Mamba
2025/03/13 by Ramachandran, Akshat, Lee, Mingyu, Xu, Huan +2 · 3 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
2025/04/19 by Ramachandran, Akshat, Kundu, Souvik, Raha, Arnab +3 · 2 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Hardware Architecture (cs.AR) #Machine Learning (cs.LG)
- Flux fractionalization transition in anisotropic S=1 antiferromagnets and dimer-loop models
2023/05/11 by Kundu, Souvik, Damle, Kedar · 2 citations
#FOS: Physical sciences #Statistical Mechanics (cond-mat.stat-mech)