State of the Art

Current research focuses on advancing various AI models and algorithms, aiming to improve their performance, efficiency, and applicability across diverse domains. Key areas include enhancing deep learning for time series forecasting and image/video processing, developing more efficient motion planning algorithms for robotics and UAVs, and improving the robustness and interpretability of models for tasks like object detection, scene generation, and medical image analysis. These advancements are significant because they address limitations in existing methods, leading to more accurate, efficient, and reliable AI systems with broad applications in healthcare, manufacturing, robotics, and beyond.

Papers

June 8, 2023

Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor Decomposition
Zhewen Yu, Christos-Savvas Bouganis
State of the Art Tensor Decomposition Low Rank Tensor Mixed Speech Chip Learning Dataflow Accelerator

June 1, 2023

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Ismail Khalfaoui-Hassani, Thomas Pellegrini, Timothée Masquelier
State of the Art Dilated Convolution Bilinear Matrix Inequality

May 31, 2023

Breast Cancer Detection and Diagnosis: A comparative study of state-of-the-arts deep learning architectures
Brennon Maistry, Absalom E. Ezugwu
Convolutional Neural Network Deep Learning Model Comparative Study State of the Art Artificial Intelligence Model Medical Diagnosis Deep Learning Architecture Breast Cancer Breast Cancer Detection Breast Cancer Histopathological Image Classification

May 26, 2023

Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model
David Soong, Sriram Sridhar, Han Si, Jan-Samuel Wagner, Ana Caroline Costa Sá, Christina Y Yu, Kubra Karagoz, Meijian Guan, Hisham Hamadeh, Brandon W Higgs
Large Language Model State of the Art GPT 4 Retrieval Augmentation Retrieval Augmented Language Model Diverse Corpus

May 23, 2023

Impact of Light and Shadow on Robustness of Deep Neural Networks
Chengyin Hu, Weiwen Shi, Chao Li, Jialiang Sun, Donghua Wang, Junqi Wu, Guijian Tang
Deep Neural Network Native Robustness Global Impact Supervised ImageNet State of the Art Quantum Shadow Light Work Brightness Variation

May 21, 2023

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers
Linyuan Gong, Chenyan Xiong, Xiaodong Liu, Payal Bajaj, Yiqing Xie, Alvin Cheung, Jianfeng Gao, Xia Song
Zero Shot State of the Art Abnormal Signal Synthetic Signal Text to Text Transformer

May 13, 2023

TIPS: Topologically Important Path Sampling for Anytime Neural Networks
Guihong Li, Kartikeya Bhardwaj, Yuedong Yang, Radu Marculescu
State of the Art Markov Chain Sample Path Anytime Valid Sequential Inference

May 11, 2023

ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models
Qijiong Liu, Nuo Chen, Tetsuya Sakai, Xiao-Ming Wu
Large Language Model State of the Art Closed Source Large Language Model Content Recommendation Content Based Recommendation

April 15, 2023

EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks
Xi Chen, Siwei Mai, Konstantinos Michmizos
State of the Art Inductive Bias Low Latency Neural Network Architecture Motor Imagery EEG Classification Spiking Graph Convolutional Network

April 11, 2023

April 10, 2023

April 6, 2023

Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions
Chen Feng Tsai, Xiaochen Zhou, Sierra S. Liu, Jing Li, Mo Yu, Hongyuan Mei
Large Language Model Artificial Intelligence Natural Language Processing ChatGPT Generated Conversation State of the Art Open Ended Text Based Game

April 4, 2023

Re-thinking Model Inversion Attacks Against Deep Neural Networks
Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-Man Cheung
Deep Neural Network State of the Art Model Inversion Attack Model Inversion Attack Performance

March 31, 2023

End-to-end deep learning-based framework for path planning and collision checking: bin picking application
Mehran Ghafarian Tamizi, Homayoun Honari, Aleksey Nozdryn-Plotnicki, Homayoun Najjaran
State of the Art Path Planning Collision Free Industrial Robot Collision Detection Efficient Path Planning

March 24, 2023

Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts
Kastan Day, Daniel Christl, Rohan Salvi, Pranav Sriram
Pre Trained State of the Art Pre Trained Vision Transformer Encoder Side Encoder Model Joint Encoder

March 22, 2023

Split-Et-Impera: A Framework for the Design of Distributed Deep Learning Applications
Luigi Capogrosso, Federico Cunico, Michele Lora, Marco Cristani, Franco Fummi, Davide Quaglia
Deep Neural Network New Framework Product Design State of the Art Deep Learning Application Split and Fit

March 17, 2023

Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives
Siyu Teng, Xuemin Hu, Peng Deng, Bai Li, Yuchen Li, Dongsheng Yang, Yunfeng Ai, Lingxi Li, Zhe Xuanyuan, Fenghua Zhu, Long Chen
Autonomous Driving Motion Planning State of the Art Internal State Art Specific Information Intelligent Vehicle Future Perspective Motion Planner Precision Control Pipeline Layout

March 13, 2023

Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues
Mohamed Akrout, Amal Feriani, Faouzi Bellili, Amine Mezghani, Ekram Hossain
Machine Learning Model Domain Generalization Supervised Learning State of the Art Concept Identification Data Driven Machine Learning Wireless Application

State of the Art

Papers

Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor Decomposition

Dilated Convolution with Learnable Spacings: beyond bilinear interpolation

Breast Cancer Detection and Diagnosis: A comparative study of state-of-the-arts deep learning architectures

Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model

Impact of Light and Shadow on Robustness of Deep Neural Networks

Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers

TIPS: Topologically Important Path Sampling for Anytime Neural Networks

ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models

EEGSN: Towards Efficient Low-latency Decoding of EEG with Graph Spiking Neural Networks

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification

Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class

LCDctCNN: Lung Cancer Diagnosis of CT scan Images Using CNN Based Model

Brain-Inspired Spiking Neural Network for Online Unsupervised Time Series Prediction

Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions

Re-thinking Model Inversion Attacks Against Deep Neural Networks

End-to-end deep learning-based framework for path planning and collision checking: bin picking application

Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts

Split-Et-Impera: A Framework for the Design of Distributed Deep Learning Applications

Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives

Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues