High Efficiency
High efficiency in various computational domains is a central research theme, aiming to minimize resource consumption (time, memory, energy) while maintaining or improving performance. Current efforts focus on developing novel algorithms and architectures, such as optimized Thompson sampling for reinforcement learning, sparse attention mechanisms for transformers, and efficient model compression techniques, to achieve this goal across diverse applications including natural language processing, computer vision, and robotics. These advancements are crucial for deploying complex AI models on resource-constrained devices and for accelerating scientific discovery in data-intensive fields.
Papers
Deep Neural Networks with Efficient Guaranteed Invariances
Matthias Rath, Alexandru Paul Condurache
NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools
Peiran Yao, Matej Kosmajac, Abeer Waheed, Kostyantyn Guzhva, Natalie Hervieux, Denilson Barbosa
BioImageLoader: Easy Handling of Bioimage Datasets for Machine Learning
Seongbin Lim, Xingjian Zhang, Emmanuel Beaurepaire, Anatole Chessel
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
Yawei Li, Yuchen Fan, Xiaoyu Xiang, Denis Demandolx, Rakesh Ranjan, Radu Timofte, Luc Van Gool
Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits
Zhiyong Wang, Xutong Liu, Shuai Li, John C. S. Lui
EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography
Yiman Liu, Xiaoxiang Han, Tongtong Liang, Bin Dong, Jiajun Yuan, Menghan Hu, Qiaohong Liu, Jiangang Chen, Qingli Li, Yuqi Zhang
Efficient and Low Overhead Website Fingerprinting Attacks and Defenses based on TCP/IP Traffic
Guodong Huang, Chuan Ma, Ming Ding, Yuwen Qian, Chunpeng Ge, Liming Fang, Zhe Liu
Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition
Yifan Jiang, Han Chen, Hanseok Ko
Efficient physics-informed neural networks using hash encoding
Xinquan Huang, Tariq Alkhalifah
Efficient fair PCA for fair representation learning
Matthäus Kleindessner, Michele Donini, Chris Russell, Muhammad Bilal Zafar