AI Briefing#deep-learning
The latest AI and developer news about #deep-learning, with the original source and a short summary.
The latest AI and developer news about #deep-learning, with the original source and a short summary.
This piece analyzes the principles of Diffusion Models, a core component of generative models, and the differences among various generative models.
Introduces various implementation methodologies for improving the computational efficiency of self-attention, the core of the Transformer.
This introduces deep learning-based anomaly detection technology and the latest research that learns complex patterns in time series data to detect abnormal data.
Decision Transformer converts reinforcement learning problems into sequence modeling problems, achieving stable policy learning through the Transformer architecture.
We examine the concept and various methodologies of Long-Tail Distribution learning to address the data imbalance problem.
Through IJCAI 2022, the latest AI research trends including reinforcement learning, federated learning, and causal inference were analyzed.
LG AI Research has developed a new AI model based on a Conditional Attention mechanism that effectively predicts the interaction between HLA and peptides.
This piece analyzes the advancement of speech recognition technology and the importance of benchmark datasets for measuring performance, comparing the status of domestic and international datasets.
This review focuses on the Diffusion Model, one of the most-noticed generative models among the diverse works presented at NeurIPS 2021, and covers the key research on it.
This article covers the concept of Long-Tail Distribution (LTD) and various learning methodologies to address data imbalance problems.
This introduces Neural Combinatorial Optimization (NCO) research for efficiently solving combinatorial optimization problems in large-scale graph environments.
At the IJCAI 2022 conference, research trends emphasizing the importance of reinforcement learning, federated learning, and reasoning capabilities were confirmed.
This piece covers the necessity and principles of Causal Representation Learning, which reasons about causality beyond correlation to overcome the limitations of existing machine learning.
LG AI Research presented a new training methodology at NeurIPS 2023 to improve deep learning performance on Tabular Data.
LG AI Research has unveiled a self-supervised learning technique using Binning to overcome the limitations of Tabular Data.
Introduces industrial anomaly detection technology and the PatchCore algorithm for quality control in manufacturing processes.
Introduces deep learning-based anomaly detection technology for quality control in manufacturing processes, along with the PatchCore and ReConPatch algorithms.
Introduces innovative time series forecasting AI models presented at ICLR 2024 and LG AI Research's research vision.
LG AI Research presented research on the model compression technique LeSS and LLM structured pruning at an ICLR 2024 workshop.
LG AI Research proposed a new benchmark that goes beyond the limitations of existing Gaussian-data-centric approaches to verify mutual information (MI) estimation performance on unstructured data.
LG AI Research presented RaTab, a technology that improves the self-supervised learning efficiency of tabular data, at AAAI-25.
LG AI Research has developed MOIRA, a multimodal integration framework that maintains high accuracy even in clinical settings with missing data.
LG AI Research has proposed 'Cluster-Aware Upcycling,' a technology that solves the problem of redundancy among experts when converting existing Dense models into MoE.
LG AI Research has unveiled Cluster-Aware Upcycling technology that reduces expert redundancy and maximizes specialization when converting a Dense model into an MoE.