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

November 24, 2023

FRUITS: Feature Extraction Using Iterated Sums for Time Series Classification
Joscha Diehl, Richard Krieg
State of the Art Feature Extraction Time Series Classification Linear Classifier Iterated Sum

November 22, 2023

NeutronOrch: Rethinking Sample-based GNN Training under CPU-GPU Heterogeneous Environments
Xin Ai, Qiange Wang, Chunyu Cao, Yanfeng Zhang, Chaoyi Chen, Hao Yuan, Yu Gu, Ge Yu
State of the Art GNN Model GNN Training GNN Based Service Heterogeneous GPU GPU Training

November 16, 2023

UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework
Chris Kelly, Luhui Hu, Cindy Yang, Yu Tian, Deshun Yang, Bang Yang, Zaoshan Huang, Zihao Li, Yuexian Zou
State of the Art Vision Based Multimodal Foundation Model

October 25, 2023

Gramian Attention Heads are Strong yet Efficient Vision Learners
Jongbin Ryu, Dongyoon Han, Jongwoo Lim
State of the Art Attention Layer Classification Head Attention Based Aggregation Fine Grained Visual Classification

October 24, 2023

Representation Learning with Large Language Models for Recommendation
Xubin Ren, Wei Wei, Lianghao Xia, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, Chao Huang
Representation Learning Recommender System State of the Art Effective Recommendation Graph Based LLM Representation Novel Recommendation

October 20, 2023

FLTracer: Accurate Poisoning Attack Provenance in Federated Learning
Xinyu Zhang, Qingyu Liu, Zhongjie Ba, Yuan Hong, Tianhang Zheng, Feng Lin, Li Lu, Kui Ren
Federated Learning State of the Art Poisoning Attack

October 12, 2023

Dealing with zero-inflated data: achieving SOTA with a two-fold machine learning approach
Jože M. Rožanec, Gašper Petelin, João Costa, Blaž Bertalanič, Gregor Cerar, Marko Guček, Gregor Papa, Dunja Mladenić
Machine Learning Model State of the Art Demand Prediction Prediction Performance Double Machine Learning Zero Inflated Appliance Detection

October 11, 2023

Guided Attention for Interpretable Motion Captioning
Karim Radouane, Julien Lagarde, Sylvie Ranwez, Andon Tchechmedjiev
State of the Art Spatiotemporal Attention Visual Captioning Motion Encoder Guided Attention

October 4, 2023

Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions
Maziyar Khadivi, Todd Charter, Marjan Yaghoubi, Masoud Jalayer, Maryam Ahang, Ardeshir Shojaeinasab, Homayoun Najjaran
Reinforcement Learning Deep Reinforcement Learning NCD Method State of the Art Future Direction Machine Scheduling Production Scheduling

September 29, 2023

Effect of structure-based training on 3D localization precision and quality
Armin Abdehkakha, Craig Snoeyink
Mixed Effect State of the Art Quality Issue Super Resolution Microscopy

September 28, 2023

Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors
Yuanyi Zhong, Anand Bhattad, Yu-Xiong Wang, David Forsyth
Depth Estimation State of the Art Inter Part Equivariance Image Cropping Invariance Regularization

September 25, 2023

Audio classification with Dilated Convolution with Learnable Spacings
Ismail Khalfaoui-Hassani, Timothée Masquelier, Thomas Pellegrini
State of the Art Audio Classification Dilated Convolution Audio Classification Benchmark

September 21, 2023

Unveiling Optimal SDG Pathways: An Innovative Approach Leveraging Graph Pruning and Intent Graph for Effective Recommendations
Zhihang Yu, Shu Wang, Yunqiang Zhu, Wen Yuan, Xiaoliang Dai, Zhiqiang Zou
State of the Art Novel Approach Effective Recommendation Recommendation Algorithm Sustainable Development Graph Pruning

September 10, 2023

Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art
Aref Miri Rekavandi, Shima Rashidi, Farid Boussaid, Stephen Hoefs, Emre Akbas, Mohammed bennamoun
Timely Survey New Benchmark Computer Vision Transformer Megatron Decepticons Object Detection State of the Art Object Recognition Small Object Detection CNN Based Detector

August 31, 2023

Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation
John Mendonça, Patrícia Pereira, Helena Moniz, João Paulo Carvalho, Alon Lavie, Isabel Trancoso
State of the Art Open Domain Dialogue System Automatic Evaluation Metric Dialogue Evaluation LLM Prompt Multilingual Dialogue Evaluation

August 30, 2023

Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
Tanujit Chakraborty, Ujjwal Reddy K S, Shraddha M. Naik, Madhurima Panja, Bayapureddy Manvitha
Timely Survey Generative Adversarial Network GAN Model State of the Art Last Decade GAN Algorithm

August 29, 2023

Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation
Meng Yuan, Fuzhen Zhuang, Zhao Zhang, Deqing Wang, Jin Dong
Knowledge Graph State of the Art Effective Recommendation Knowledge Propagation Adaptive Space Fusion

August 28, 2023

1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation
Tao Zhang, Xingye Tian, Yikang Zhou, Yu Wu, Shunping Ji, Cilin Yan, Xuebo Wang, Xin Tao, Yuan Zhang, Pengfei Wan
State of the Art Place Solution Video Instance Segmentation HASOC Subtrack CLVision Challenge

August 26, 2023

Applications of machine Learning to improve the efficiency and range of microbial biosynthesis: a review of state-of-art techniques
Akshay Bhalla, Suraj Rajendran
Machine Learning Artificial Intelligence High Efficiency Financial Application State of the Art Decomposed Automation Correction GlcNAcylation Site

August 21, 2023

Malware Classification using Deep Neural Networks: Performance Evaluation and Applications in Edge Devices
Akhil M R, Adithya Krishna V Sharma, Harivardhan Swamy, Pavan A, Ashray Shetty, Anirudh B Sathyanarayana
Deep Neural Network Financial Application State of the Art Edge Device Performance Evaluation Malware Classification

State of the Art

Papers

FRUITS: Feature Extraction Using Iterated Sums for Time Series Classification

NeutronOrch: Rethinking Sample-based GNN Training under CPU-GPU Heterogeneous Environments

UnifiedVisionGPT: Streamlining Vision-Oriented AI through Generalized Multimodal Framework

Gramian Attention Heads are Strong yet Efficient Vision Learners

Representation Learning with Large Language Models for Recommendation

FLTracer: Accurate Poisoning Attack Provenance in Federated Learning

Dealing with zero-inflated data: achieving SOTA with a two-fold machine learning approach

Guided Attention for Interpretable Motion Captioning

Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions

Effect of structure-based training on 3D localization precision and quality

Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors

Audio classification with Dilated Convolution with Learnable Spacings

Unveiling Optimal SDG Pathways: An Innovative Approach Leveraging Graph Pruning and Intent Graph for Effective Recommendations

Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art

Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation

Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art

Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation

1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation

Applications of machine Learning to improve the efficiency and range of microbial biosynthesis: a review of state-of-art techniques

Malware Classification using Deep Neural Networks: Performance Evaluation and Applications in Edge Devices