AI BriefingLG AI Research news
The latest AI and developer news from LG AI Research, with short summaries.
Visit website →[NeurIPS 2022] Symbolic Music Motif Generation - LG AI Research BLOG
LG AI Research has released research on a model that effectively generates Loops, the core unit of music.
The Role and Importance of Speech Recognition Datasets
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.
LG AI Research Overcomes the Limits of AI Vision Inspection
LG AI Research has solved the data scarcity and forgetting problems of existing AI vision inspection with a self-supervised learning-based technology.
LG AI Research: The Technical Principles of the EXAONE Multimodal Model
LG AI Research has unveiled the architecture of the EXAONE multimodal model, which understands text and images bidirectionally.
LG AI Research 191
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.
[NeurIPS 2021] Part 2: A Review of Deep Clustering Based on Variational Deep Embedding - LG AI Research BLOG
This article examines deep clustering techniques using Variational Autoencoder and the latest research based on VaDE.
LG AI Research: NeurIPS 2021 Research Summary - Part 3: Neural Architecture Search Review
This analyzes the latest research trends and cost-reduction techniques for Neural Architecture Search (NAS) presented at NeurIPS 2021.
LG AI Research 207
This introduces research that combines Reinforcement Learning (RL) with Graph Neural Networks (GNN) to process complex data and learn general-purpose policies.
[CVPR 2022] Large Vision-Language Models: What's Next?
Following NLP's success, the vision-language field is also accelerating large-scale model training leveraging massive data and infrastructure.
LG AI Research 221
A review of research trends in language models combining knowledge information, centered on ACL 2022.
LG AI Research: On-Site Sketch from CVPR 2022
LG AI Research participated in CVPR 2022, showcasing multimodal representation learning and L-Verse research.
LG AI Research 237
We analyze the concept of NeRF, which drew attention at CVPR 2022, and the latest research trends.
LG AI Research 238
This introduces the Continual Learning research trends based on Transformers and self-supervised learning presented at CVPR 2022.
LG AI Research 235
LG AI Research announced PSGI technology that efficiently infers hierarchical task structures.
LG AI Research 247
Proposes a new methodology that improves Domain Generalization (DG) performance by using Natural Language Supervision to align visual representations with human reasoning.
LG AI Research: Long-Tail Distribution Learning
This article covers the concept of Long-Tail Distribution (LTD) and various learning methodologies to address data imbalance problems.
LG AI Research 256
LG AI Research introduced key research on self-supervised learning presented at ICML 2022.
[ICML 2022] Part 3: Neural Combinatorial Optimization Research - LG AI Research Blog
This introduces Neural Combinatorial Optimization (NCO) research for efficiently solving combinatorial optimization problems in large-scale graph environments.
LG AI Research 262
Through an NVIDIA GTC 2022 session, the growth of the digital avatar market and its core technology, Omniverse ACE, are introduced.
LG AI Research 263
This explores the latest trends in personalized image/language models and NeRF technology through NVIDIA GTC 2022.