| 2026 | ACL | Activation Steering for Chain-of-Thought Compression. | Seyedarmin Azizi, Erfan Baghaei Potraghloo, Souvik Kundu, Massoud Pedram |
| 2026 | ACL | Improving the Throughput of Diffusion-based Large Language Models via a Training-Free Confidence-Aware Calibration. | Jucheng Shen, Gaurav Sarkar, Yeonju Ro, Sharath Nittur Sridhar, Zhangyang Wang, Aditya Akella, Souvik Kundu |
| 2026 | ASPLOS | MoDM: Efficient Serving for Image Generation via Mixture-of-Diffusion Models. | Yuchen Xia, Divyam Sharma, Yichao Yuan, Souvik Kundu, Nishil Talati |
| 2025 | ACL | LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering. | Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Allen Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu |
| 2025 | EMNLP | LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling. | Zeyu Liu, Souvik Kundu, Lianghao Jiang, Anni Li, Srikanth Ronanki, Sravan Babu Bodapati, Gourav Datta, Peter Anthony Beerel |
| 2025 | EMNLP | Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression. | Sreetama Sarkar, Yue Che, Alex Gavin, Peter Anthony Beerel, Souvik Kundu |
| 2025 | ICCV | Ouromamba: a Data-Free Quantization Framework for Vision Mamba. | Akshat Ramachandran, Mingyu Lee, Huan Xu, Souvik Kundu, Tushar Krishna |
| 2025 | ICLR | Scaling Long Context Training Data by Long-Distance Referrals. | Yonghao Zhuang, Lanxiang Hu, Longfei Yun, Souvik Kundu, Zhengzhong Liu, Eric P. Xing, Hao Zhang |
| 2025 | ICLR | MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba. | Seyedarmin Azizi, Souvik Kundu, Mohammad Erfan Sadeghi, Massoud Pedram |
| 2025 | ICLR | 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 |
| 2025 | ICML | 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 |
| 2025 | ISCA | MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization. | Akshat Ramachandran, Souvik Kundu, Tushar Krishna |
| 2025 | ISLPED | Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator. | Akshat Ramachandran, Souvik Kundu, Arnab Raha, Shamik Kundu, Deepak K. Mathaikutty, Tushar Krishna |
| 2025 | NAACL | LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression. | Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal |
| 2025 | WACV | MaskVD: Region Masking for Efficient Video Object Detection. | Sreetama Sarkar, Gourav Datta, Souvik Kundu, Kai Zheng, Chirayata Bhattacharyya, Peter A. Beerel |
| 2024 | ACL | AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models. | Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter A. Beerel |
| 2024 | CVPR | DIA: Diffusion based Inverse Network Attack on Collaborative Inference. | Dake Chen, Shiduo Li, Yuke Zhang, Chenghao Li, Souvik Kundu, Peter A. Beerel |
| 2024 | CVPR | RLNet: Robust Linearized Networks for Efficient Private Inference. | Sreetama Sarkar, Souvik Kundu, Peter A. Beerel |
| 2024 | CVPR | Block Selective Reprogramming for On-device Training of Vision Transformers. | Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel |
| 2024 | ECCV | GenQ: Quantization in Low Data Regimes with Generative Synthetic Data. | Yuhang Li, Youngeun Kim, Donghyun Lee, Souvik Kundu, Priyadarshini Panda |
| 2024 | ECCV | CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-training Quantization of ViTs. | Akshat Ramachandran, Souvik Kundu, Tushar Krishna |
| 2024 | EMNLP | LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation. | Seyedarmin Azizi, Souvik Kundu, Massoud Pedram |
| 2024 | HiPC | Towards Real-Time LLM Inference on Heterogeneous Edge Platforms. | Rakshith Jayanth, Neelesh Gupta, Souvik Kundu, Deepak A. Mathaikutty, Viktor K. Prasanna |
| 2024 | ICASSP | Sensi-Bert: Towards Sensitivity Driven Fine-Tuning for Parameter-Efficient Language Model. | Souvik Kundu, Sharath Nittur Sridhar, Maciej Szankin, Sairam Sundaresan |
| 2024 | ICASSP | Recent Advances in Scalable Energy-Efficient and Trustworthy Spiking Neural Networks: from Algorithms to Technology. | Souvik Kundu, Rui-Jie Zhu, Akhilesh Jaiswal, Peter A. Beerel |
| 2024 | ICASSP | Analyzing Adversarial Vulnerabilities of Graph Lottery Tickets. | Subhajit Dutta Chowdhury, Zhiyu Ni, Qingyuan Peng, Souvik Kundu, Pierluigi Nuzzo |
| 2024 | ICLR | Fusing Models with Complementary Expertise. | Hongyi Wang, Felipe Maia Polo, Yuekai Sun, Souvik Kundu, Eric P. Xing, Mikhail Yurochkin |
| 2024 | ICML | 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 |
| 2024 | ICPR | What Makes Vision Transformers Robust Towards Bit-Flip Attack? | Xuan Zhou, Souvik Kundu, Dake Chen, Jie Huang, Peter A. Beerel |
| 2023 | AI | Personality Trait Detection using an Hierarchy of Tree-transformers and Graph Attention Network. | Sudipta Singha Roy, Robert E. Mercer, Souvik Kundu |
| 2023 | CVPR | 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 |
| 2023 | DAC | C | Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel |
| 2023 | ICASSP | In-Sensor & Neuromorphic Computing Are all You Need for Energy Efficient Computer Vision. | Gourav Datta, Zeyu Liu, Md. Abdullah-Al Kaiser, Souvik Kundu, Joe Mathai, Zihan Yin, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel |
| 2023 | ICASSP | Sparse Mixture Once-for-all Adversarial Training for Efficient in-situ Trade-off between Accuracy and Robustness of DNNs. | Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel |
| 2023 | ICASSP | Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments. | Haonan Wang, Connor Imes, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters |
| 2023 | ICCAD | RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference. | Dake Chen, Yuke Zhang, Souvik Kundu, Chenghao Li, Peter A. Beerel |
| 2023 | ICCV | Vision HGNN: An Image is More than a Graph of Nodes. | Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang |
| 2023 | ICCV | 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 |
| 2023 | ICLR | Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference. | Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter A. Beerel |
| 2023 | ICML | 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 |
| 2023 | ISCAS | ViTA: A Vision Transformer Inference Accelerator for Edge Applications. | Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, Peter A. Beerel |
| 2023 | WACV | Self-Attentive Pooling for Efficient Deep Learning. | Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel |
| 2023 | WACV | 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 |
| 2022 | DATE | BMPQ: Bit-Gradient Sensitivity-Driven Mixed-Precision Quantization of DNNs from Scratch. | Souvik Kundu, Shikai Wang, Qirui Sun, Peter A. Beerel, Massoud Pedram |
| 2022 | DSD | PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices. | Yang Hu, Connor Imes, Xuanang Zhao, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters |
| 2022 | LREC | Evaluation Benchmarks for Spanish Sentence Representations. | Vladimir Araujo, Andrs Carvallo, Souvik Kundu, Jos Caete, Marcelo Mendoza, Robert E. Mercer, Felipe Bravo-Marquez, Marie-Francine Moens, Alvaro Soto |
| 2021 | ASPDAC | DNR: A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs. | Souvik Kundu, Mahdi Nazemi, Peter A. Beerel, Massoud Pedram |
| 2021 | ICASSP | AttentionLite: Towards Efficient Self-Attention Models for Vision. | Souvik Kundu, Sairam Sundaresan |
| 2021 | ICCV | 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 |
| 2021 | IJCNN | Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding. | Gourav Datta, Souvik Kundu, Peter A. Beerel |
| 2021 | WACV | 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 |
| 2020 | ACL | Learning to Identify Follow-Up Questions in Conversational Question Answering. | Souvik Kundu, Qian Lin, Hwee Tou Ng |
| 2020 | COLING | A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection. | Qian Lin, Souvik Kundu, Hwee Tou Ng |
| 2019 | ACL | Exploiting Explicit Paths for Multi-hop Reading Comprehension. | Souvik Kundu, Tushar Khot, Ashish Sabharwal, Peter Clark |
| 2018 | AAAI | A Question-Focused Multi-Factor Attention Network for Question Answering. | Souvik Kundu, Hwee Tou Ng |
| 2018 | EMNLP | A Nil-Aware Answer Extraction Framework for Question Answering. | Souvik Kundu, Hwee Tou Ng |
| 2018 | ISDA | QBEECH: Multi-hop Clustering of Cognitive Based Sensor Nodes in the Administration of Queen Nodes. | Souvik Kundu, Srividhya Karthikeyan, A. Karthikeyan |
| 2016 | ICASSP | Joint acoustic factor learning for robust deep neural network based automatic speech recognition. | Souvik Kundu, Gautam Mantena, Yanmin Qian, Tian Tan, Marc Delcroix, Khe Chai Sim |
| 2016 | ICASSP | Speaker-aware training of LSTM-RNNS for acoustic modelling. | Tian Tan, Yanmin Qian, Dong Yu, Souvik Kundu, Liang Lu, Khe Chai Sim, Xiong Xiao, Yu Zhang |
| 2016 | Interspeech | Incorporating a Generative Front-End Layer to Deep Neural Network for Noise Robust Automatic Speech Recognition. | Souvik Kundu, Khe Chai Sim, Mark J. F. Gales |
| 2013 | CEC | Teaching and learning best Differential Evoltuion with self adaptation for real parameter optimization. | Subhodip Biswas, Souvik Kundu, Swagatam Das, Athanasios V. Vasilakos |
| 2013 | CEC | Modified estimation of Distribution algorithm with differential mutation for constrained optimization. | Shantanab Debchoudhury, Subhodip Biswas, Souvik Kundu, Swagatam Das, Athanasios V. Vasilakos, Ankur Mondal |
| 2013 | GECCO | Information sharing in bee colony for detecting multiple niches in non-stationary environments. | Subhodip Biswas, Souvik Kundu, Swagatam Das, Athanasios V. Vasilakos |
| 2013 | GECCO | Crowding-based local differential evolution with speciation-based memory archive for dynamic multimodal optimization. | Souvik Kundu, Subhodip Biswas, Swagatam Das, Ponnuthurai N. Suganthan |