© 2024 Intel AI Lab. Site made with Jekyll; and modified from Allan Lab
We are part of the Intelligent Systems Research Lab at Intel Labs, Intel Corporation
Hello from
Lu Yin, Shiwei Liu, Ajay Jaiswal, Souvik Kundu, Zhangyang (Atlas) Wang
Pruning Small Magnitude Weights Monotonically and Irreversibly Impairs Difficult Downstream Tasks in LLMs
ICML 2024.
[arXiv] [project]
[code]
Souvik Kundu, Zeyu Liu, Anni Li, Junrui Wan, Lianghao Jiang, Peter A. Beerel
AFLoRA: Adaptive Freezing of Low-Rank Adepters for Parameter Efficient Fine-Tuning of Language Models
Under review 2024.
[Under review] [project]
[code]
Sreetama Sarkar, Souvik Kundu, Kai Zheng, Peter A. Beerel
Block Selective Reprogramming for On-device Training of Vision Transformers
under review 2024.
[CVPRW] [project]
[code]
Souvik Kundu, Sreetama Sarkar, Peter A. Beerel
RLNet: Robust Linearized Networks for Efficient Private Inference
CVPR 2024.
[CVPRW] [project]
[code]
Raj Ghugare, Santiago Miret, Adriana Hugessen, Mariano Phielipp, Glen Berseth
Searching the Space of High-Value Molecules Using Reinforcement Learning and Language Models
ICLR 2024.
[ICLR] [project]
[code]
Mikhail Galkin, Xinyu Yuan, Hesham Mostafa, Jian Tang, Zhaocheng Zhu
Towards Foundation Models for Knowledge Graph Reasoning
ICLR 2024.
[ICLR] [project]
[code]
Hongyi Wang, Felipe Maia Polo, Yuekai Sun, Souvik Kundu, Eric Xing, Mikhail Yurochkin
Fusing Models with Complementary Expertise
ICLR 2024.
[ICLR] [project]
[code]
Jose Rojas Chaves, Subarna Tripathi
VideoSAGE: Video Summarization with Graph Representation Learning
CVPR 2024.
[CVPRW] [project]
[code]
A. Ramachandran, Souvik Kundu, Tushar Krishna
CLAMP-ViT: Contrastive Data-Free Learning for Adaptive Post-Training Quantization of ViTs
under review 2024.
[Under review] [project]
[code]
Tz-Ying Wu, Kyle Min, Subarna Tripathi, Nuno Vasconcelos
Ego-VPA: Egocentric Video Understanding with Parameter-efficient Adaptation
under review 2024.
[Under review] [project]
[code]
Ting Hsuan Liao, Sainan Liu, Ilke Demir, Jia-Bin Huang
PASTE: Prompt-Aligned Scene TExture synthesis
under review 2024.
[Under review] [project]
[code]
Changhoon Kim, Kyle Min, Yezhou Yang
R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
under review 2024.
[Under review] [project]
[code]
Jiraphon Yenphraphai, Xichen Pan, Sainan Liu, Daniele Panozzo, Saining Xie
Image Sculpting: Precise Object Editing with 3D Geometry Control
CVPR 2024.
[CVPR] [project]
[code]
Changhoon Kim, Kyle Min, Maitreya Patel, Sheng Cheng, Yezhou Yang
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
CVPR 2024.
[CVPR] [project]
[code]
Ivan Rodin, Antonino Furnari, Kyle Min, Subarna Tripathi, Giovanni Maria Farinella
Action Scene Graphs for Long-Form Understanding of Egocentric Videos
CVPR 2024.
[CVPR] [project]
[code]
Sharath Nittur Sridhar, Maciej Szankin, Fang Chen, Sairam Sundaresan, Anthony Sarah
SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search
Association for the Advancement of Artificial Intelligence (AAAI) 2024.
[arXiv] [project]
[code]
Souvik Kundu, Sharath Nittur Sridhar, Maciej Szankin, Sairam Sundaresan
Sensi-BERT: Towards Sensitivity Driven Fine-Tuning for Parameter Efficient BERT
ICASSP 2024.
[ICASSP] [project]
[code]
Sainan Liu, Shan Lin, Jingpei Lu, Shreya Saha, Alexey Supikov, Michael Yip
BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitives
CVPRW 2024.
[ArXiv] [project]
[code]
Souvik Kundu, Anthony Sarah, Vinay Joshi, Om J Omer, Sreenivas Subramoney
Towards Joint Optimization for DNN Architecture and Configuration for Compute-In-Memory Hardware
TinyML 2024.
[arXiv] [project]
[code]
Shreya Saha, Sainan Liu, Shan Lin, Jingpei Lu, Michael Yip
BASED: Bundle-Adjusting Surgical Endoscopic Dynamic Video Reconstruction using Neural Radiance Fields
arXiv 2023.
[ArXiv] [project]
[code]
Yi Ren, Samuel Lavoie, Mikhail Galkin, Danica J. Sutherland, Aaron Courville
Improving Systematic Generalization using Simplicial Embeddings and Iterated Learning
NeurIPS 2023.
[ArXiv] [project]
[code]
Zhaocheng Zhu, Xinyu Yuan, Mikhail Galkin, Sophie Xhonneux, Ming Zhang, Maxime Gazeau, Jian Tang
A* Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs
NeurIPS 2023.
[ArXiv] [project]
[code]
Yan Han, Peihao Wang, Souvik Kundu, Ding Ying, Zhangyang (Atlas) Wang
Vision HGNN: An Image is More than a Graph of Nodes
International Conference on Computer Vision (ICCV) ORAL, 2023.
[CVF] [project]
[code]
Souvik Kundu, Yuke Zhang, Dake Chen*, Chenghao Li, Peter A. Beerel
SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation
International Conference on Computer Vision (ICCV), 2023.
[CVF] [project]
[code]
Sharath Nittur Sridhar, Souvik Kundu, Sairam Sundaresan, Maciej Szankin, Anthony Sarah
InstaTune: Instantaneous Neural Architecture Search During Fine-Tuning
International Conference on Computer Vision (ICCV) Workshops 2023.
[CVF] [project]
[code]
Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Celine Lin
NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations
International Conference on Machine Learning (ICML), 2023.
[PMLR] [project]
[code]
Kyle Min
STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization
Ego4D challenge at CVPR 2023.
[ArXiv] [project]
[code]
Souvik Kundu, Shunlin Lu, Yuke Zhang, Jacqueline Liu, Peter A. Beerel
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
International Conference on Learning Representation (ICLR), 2023.
[OpenReview] [project]
[code]
Yi Li, Kyle Min, Subarna Tripathi, Nuno Vasconcelos
SViTT: Temporal Learning of Sparse Video-Text Transformer
Computer Vision and Pattern Recognition (CVPR), 2023.
[arXiv] [project]
[code]
Sayak Nag, Kyle Min, Subarna Tripathi, Amit Roy Choudhury
Unbiased video scene graph generation
Computer Vision and Pattern Recognition (CVPR), 2023.
[arXiv] [project]
[code]
Yuke Zhang, Dake Chen, Souvik Kundu, Haomei Liu, Ruiheng Peng, Peter A. Beerel
C2PI: An Efficient Crypto-Clear Two-Party Neural Network Private Inference
Design Automation Conference (DAC), 2023.
[arxiv] [project]
[code]
Shengyu Feng, Hesham Mostafa, Marcel Nassar, Somdeb Majumdar, Subarna Tripathi
Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.
[CVF] [project]
[code]
Fang Chen, Gourav Datta, Souvik Kundu, Peter A. Beerel
Self-Attentive Pooling for Efficient Deep Learning
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023.
[CVF] [project]
[code]
Shaowei Liu, Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang
Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
Computer Vision and Pattern Recognition (CVPR), 2022.
[arXiv] [project]
[code]
Xiang Zhang, Yongwen Su, Subarna Tripathi, Zhuowen Tu
Text Spotting Transformers
Computer Vision and Pattern Recognition (CVPR), 2022.
[arXiv] [project]
[code]
Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
Learning long-term spatial-temporal graphs for active speaker detection
European Conference on Computer Vision (ECCV), 2022.
[arXiv] [project]
[code]
Alakh Desai, Tz-Ying Wu, Subarna Tripathi, Nuno Vasconcelos
Single-Stage Visual Relationship Learning using Conditional Queries
Neural Information Processing Systems (NeurIPS), 2022.
[openReview] [project]
[code]
Daniel Cummings, Sharath Nittur Sridhar, Anthony Sarah, Maciej Szankin
Accelerating Neural Architecture Exploration Across Modalities Using Genetic Algorithms
Genetic and Evolutionary Computation Conference (GECCO) 2022.
[arXiv] [project]
[code]
Daniel Cummings, Anthony Sarah, Sharath Nittur Sridhar, Maciej Szankin, Pablo Munoz, Sairam Sundaresan
A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities
Automated Machine Learning (AutoML) 2022.
[arXiv] [project]
[code]
J. Pablo Munoz, Nikolay Lyalyushkin, Chaunté W. Lacewell, Anastasia Senina, Daniel Cummings, Anthony Sarah, Alexander Kozlov, Nilesh Jain
Automated Super-Network Generation for Scalable Neural Architecture Search
Automated Machine Learning (AutoML) 2022.
[OpenReview] [project]
[code]
Sharath Nittur Sridhar, Anthony Sarah, Sairam Sundaresan
TrimBERT: Tailoring BERT for Trade-offs
International Conference on Machine Learning (ICML) 2022.
[arXiv] [project]
[code]
Souvik Kundu, Sairam Sundaresan, M. Pedram, P. A. Beerel
FLOAT: Fast Learnable Once-for-All Adversarial Training for Tunable Trade-off between Accuracy and Robustness
Winter Conference on Applications of Computer Vision (WACV) 2022.
[OpenReview] [project]
[code]
Souvik Kundu, Sairam Sundaresan, Sharath Nittur Sridhar, S Lu, H Tang, P. A. Beerel
Sparse Mixture Once-for-all Adversarial Training for Efficient in-situ Trade-off between Accuracy and Robustness of DNNs
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022.
[arXiv] [project]
[code]
Souvik Kundu, Sairam Sundaresan
AttentionLite: Towards Efficient Self-attention models for Vision
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2021.
[arXiv] [project]
[code]
Alicja Kwasniewska, Maciej Szankin, Jacek Ruminski, Anthony Sarah, David Gamba
Improving Accuracy of Respiratory Rate Estimation by Restoring High Resolution Features With Transformers and Recursive Convolutional Models
Computer Vision and Pattern Recognition (CVPR) 2021.
[CVF] [project]
[code]
Sharath Nittur Sridhar, Anthony Sarah
Undivided Attention: Are Intermediate Layers Necessary for BERT?
Neural Information Processing Systems (NeurIPS) 2021.
[NeurIPS] [project]
[code]
Hala Lamdouar, Sairam Sundaresan, Anna Jungbluth, Sudeshna Boro Saikia, Amanda Joy Camarata, Nathan Miles, Marcella Scoczynski, Mavis Stone, Anthony Sarah, Andres Munoz-Jaramillo, Ayris Narock, Adam Szabo
Deep-SWIM: A few-shot learning approach to classify Solar WInd Magnetic field structures
Neural Information Processing Systems (NeurIPS) 2021.
[NeurIPS] [project]
[code]
© 2024 Intel AI Lab. Site made with Jekyll; and modified from Allan Lab
We are part of the Intelligent Systems Research Lab at Intel Labs, Intel Corporation