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
Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI
Dustin Wright, Christian Igel, Gabrielle Samuel, Raghavendra Selvan
Decomposed Guided Dynamic Filters for Efficient RGB-Guided Depth Completion
Yufei Wang, Yuxin Mao, Qi Liu, Yuchao Dai
TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Setting
Ping He, Yifan Xia, Xuhong Zhang, Shouling Ji
Applications of machine Learning to improve the efficiency and range of microbial biosynthesis: a review of state-of-art techniques
Akshay Bhalla, Suraj Rajendran
A Conflict Resolution Dataset Derived from Argoverse-2: Analysis of the Safety and Efficiency Impacts of Autonomous Vehicles at Intersections
Guopeng Li, Yiru Jiao, Simeon C. Calvert, J. W. C. van Lint