• case-insensitive prefix search: default
  e.g., sig matches "SIGIR" as well as "signal"
• exact word search: append dollar sign ($) to word
  e.g., graph$ matches "graph", but not "graphics"
• boolean and: separate words by space
  e.g., codd model
• boolean or: connect words by pipe symbol (|)
  e.g., graph|network

Update May 7, 2017: Please note that we had to disable the phrase search operator (.) and the boolean not operator (-) due to technical problems. For the time being, phrase search queries will yield regular prefix search result, and search terms preceded by a minus will be interpreted as regular (positive) search terms.

found 122 matches

• 2024
• 
  Sreetama Sarkar, Souvik Kundu, Peter A. Beerel:
  Linearizing Models for Efficient yet Robust Private Inference. CoRR abs/2402.05521 (2024)
• 
  Souvik Kundu, Anthony Sarah, Vinay Joshi, Om Ji Omer, Sreenivas Subramoney:
  CiMNet: Towards Joint Optimization for DNN Architecture and Configuration for Compute-In-Memory Hardware. CoRR abs/2402.11780 (2024)
• 
  Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao:
  GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM. CoRR abs/2403.05527 (2024)
• 
  Zeyu Liu, Souvik Kundu, Anni Li, Junrui Wan, Lianghao Jiang, Peter Anthony Beerel:
  AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models. CoRR abs/2403.13269 (2024)
• 2023
• 
  Sudipta Singha Roy, Robert E. Mercer, Souvik Kundu:
  Personality Trait Detection using an Hierarchy of Tree-transformers and Graph Attention Network. Canadian AI 2023
• 
  Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel:
  Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference. CVPR Workshops 2023: 4685-4689
• 
  Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel:
  C²PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference. DAC 2023: 1-6
• 
  Md. Abdullah-Al Kaiser, Gourav Datta, Sreetama Sarkar, Souvik Kundu, Zihan Yin, Manas Garg, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal:
  Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M). ACM Great Lakes Symposium on VLSI 2023: 613-618
• 
  Gourav Datta, Zeyu Liu, Md. Abdullah-Al Kaiser, Souvik Kundu, Joe Mathai, Zihan Yin, Ajey P. Jacob, Akhilesh R. Jaiswal, Peter A. Beerel:
  In-Sensor & Neuromorphic Computing Are all You Need for Energy Efficient Computer Vision. ICASSP 2023: 1-5
• 
  Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel:
  Sparse Mixture Once-for-all Adversarial Training for Efficient in-situ Trade-off between Accuracy and Robustness of DNNs. ICASSP 2023: 1-5
• 
  Haonan Wang, Connor Imes, Souvik Kundu, Peter A. Beerel, Stephen P. Crago, John Paul Walters:
  Quantpipe: Applying Adaptive Post-Training Quantization For Distributed Transformer Pipelines In Dynamic Edge Environments. ICASSP 2023: 1-5
• 
  Dake Chen, Yuke Zhang, Souvik Kundu, Chenghao Li, Peter A. Beerel:
  RNA-ViT: Reduced-Dimension Approximate Normalized Attention Vision Transformers for Latency Efficient Private Inference. ICCAD 2023: 1-9
• 
  Yan Han, Peihao Wang, Souvik Kundu, Ying Ding, Zhangyang Wang:
  Vision HGNN: An Image is More than a Graph of Nodes. ICCV 2023: 19821-19831
• 
  Yuke Zhang, Dake Chen, Souvik Kundu, Chenghao Li, Peter A. Beerel:
  SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation. ICCV 2023: 5093-5102
• 
  Yue Hu, Xinan Ye, Yifei Liu, Souvik Kundu, Gourav Datta, Srikar Mutnuri, Namo Asavisanu, Nora Ayanian, Konstantinos Psounis, Peter A. Beerel:
  FireFly: A Synthetic Dataset for Ember Detection in Wildfire. ICCV (Workshops) 2023: 3767-3771
• 
  Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah:
  InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning. ICCV (Workshops) 2023: 1515-1519
• 
  Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter A. Beerel:
  Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference. ICLR 2023
• 
  Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan Celine Lin:
  NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations. ICML 2023: 10482-10493
• 
  Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, Peter A. Beerel:
  ViTA: A Vision Transformer Inference Accelerator for Edge Applications. ISCAS 2023: 1-5
• 
  Duc Hoang, Souvik Kundu, Shiwei Liu, Zhangyang Wang:
  Don't just prune by magnitude! Your mask topology is a secret weapon. NeurIPS 2023
• 
  Souvik Ghosh, Quentin Smets, S. Banerjee, Tom Schram, K. Kennes, R. Verheyen, P. Kumar, M.-E. Boulon, Benjamin Groven, H. M. Silva, S. Kundu, Daire Cott, Dennis Lin, P. Favia, T. Nuytten, A. Phommahaxay, Inge Asselberghs, C. De La Rosa, Gouri Sankar Kar, Steven Brems:
  Integration of epitaxial monolayer MX₂ channels on 300mm wafers via Collective-Die-To-Wafer (CoD2W) transfer. VLSI Technology and Circuits 2023: 1-2
• 
  S. Kundu, D. H. van Doip, Tom Schram, Quentin Smets, S. Banerjee, Benjamin Groven, Daire Cott, S. Decoster, P. Bezard, F. Lazzarino, K. Banerjee, Souvik Ghosh, J. F. de Mamelfe, Pierre Morin, Cesar J. Lockhart de la Rosa, Inge Asselberghs, Gouri Sankar Kar:
  Towards low damage and fab-compatible top-contacts in MX2 transistors using a combined synchronous pulse atomic layer etch and wet-chemical etch approach. VLSI Technology and Circuits 2023: 1-2
• 
  Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel:
  Self-Attentive Pooling for Efficient Deep Learning. WACV 2023: 3963-3972
• 
  Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel:
  FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-off between Accuracy and Robustness. WACV 2023: 2348-2357
• 
  Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Tiffany Liu, Peter A. Beerel:
  Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference. CoRR abs/2301.09254 (2023)
• 
  Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, Shunlin Lu, Han Tang, Peter A. Beerel:
  Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs. CoRR abs/2302.03523 (2023)
• 
  Shashank Nag, Gourav Datta, Souvik Kundu, Nitin Chandrachoodan, Peter A. Beerel:
  ViTA: A Vision Transformer Inference Accelerator for Edge Applications. CoRR abs/2302.09108 (2023)
• 
  Md. Abdullah-Al Kaiser, Gourav Datta, Sreetama Sarkar, Souvik Kundu, Zihan Yin, Manas Garg, Ajey P. Jacob, Peter A. Beerel, Akhilesh R. Jaiswal:
  Technology-Circuit-Algorithm Tri-Design for Processing-in-Pixel-in-Memory (P2M). CoRR abs/2304.02968 (2023)
• 
  Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel:
  C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference. CoRR abs/2304.13266 (2023)
• 
  Souvik Kundu, Yuke Zhang, Dake Chen, Peter A. Beerel:
  Making Models Shallow Again: Jointly Learning to Reduce Non-Linearity and Depth for Latency-Efficient Private Inference. CoRR abs/2304.13274 (2023)

skipping 92 more matches