Deja vu: Contextual sparsity for efficient llms at inference time

Z Liu, J Wang, T Dao, T Zhou, B Yuan… - International …, 2023 - proceedings.mlr.press
Large language models (LLMs) with hundreds of billions of parameters have sparked a new
wave of exciting AI applications. However, they are computationally expensive at inference …

Neural cognitive diagnosis for intelligent education systems

F Wang, Q Liu, E Chen, Z Huang, Y Chen, Y Yin… - Proceedings of the AAAI …, 2020 - aaai.org
Cognitive diagnosis is a fundamental issue in intelligent education, which aims to discover
the proficiency level of students on specific knowledge concepts. Existing approaches …

NeuralCD: a general framework for cognitive diagnosis

F Wang, Q Liu, E Chen, Z Huang, Y Yin… - … on Knowledge and …, 2022 - ieeexplore.ieee.org
Cognitive diagnosis is widely applicable in the scenarios where users' cognitive states need
to be assessed, such as games and clinical measurement. Especially in intelligent …

Deep reinforcement learning for load-balancing aware network control in IoT edge systems

Q Liu, T Xia, L Cheng, M Van Eijk… - … on Parallel and …, 2021 - ieeexplore.ieee.org
Load balancing is directly associated with the overall performance of a parallel and
distributed computing system. Although the relevant problems in communication and …

Breaking the linear iteration cost barrier for some well-known conditional gradient methods using maxip data-structures

Z Xu, Z Song, A Shrivastava - Advances in Neural …, 2021 - proceedings.neurips.cc
Conditional gradient methods (CGM) are widely used in modern machine learning. CGM's
overall running time usually consists of two parts: the number of iterations and the cost of …

Query-aware quantization for maximum inner product search

J Zhang, D Lian, H Zhang, B Wang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Abstract Maximum Inner Product Search (MIPS) plays an essential role in many applications
ranging from information retrieval, recommender systems to natural language processing …

[HTML][HTML] CARMEL: Capturing spatio-temporal correlations via time-series sub-window imaging for home appliance classification

B Bertalanič, C Fortuna - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Energy management systems (EMS), as enablers of more efficient energy consumption,
monitor and manage appliances to help residents be more energy efficient and thus more …

Convrnn-t: Convolutional augmented recurrent neural network transducers for streaming speech recognition

M Radfar, R Barnwal, RV Swaminathan… - arXiv preprint arXiv …, 2022 - arxiv.org
The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end
(E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of …

[PDF][PDF] A pre-trained deep learning model for fast online prediction of structural seismic responses

WJ Tang, DS Wang, HB Huang, JC Dai… - International Journal of …, 2023 - researchgate.net
Deep learning techniques have gradually attracted considerable research interest in
numerous application scenarios because of their capacity to simplify and accelerate …

A fast sampling algorithm for maximum inner product search

Q Ding, HF Yu, CJ Hsieh - The 22nd International …, 2019 - proceedings.mlr.press
Abstract Maximum Inner Product Search (MIPS) has been recognized as an important
operation for the inference phase of many machine learning algorithms, including matrix …