AI BriefingLG AI Research news
The latest AI and developer news from LG AI Research, with short summaries.
Visit website →[CVPR 2026] Beyond Text: VinQA, a Multimodal Document QA That Answers Using Visual Elements Like Diagrams, Charts, and Tables
LG AI Research has unveiled 'VinQA,' a multimodal document QA study that generates long-form answers by appropriately placing text and visual elements together.
LG AI Research 63
LG AI Research proposed ASER, a continual learning algorithm that minimizes forgetting by evaluating the importance of data.
LG AI Research: Research on Online Class-Incremental Continual Learning
LG AI Research proposed the ASER algorithm, which learns new data while preserving existing knowledge by leveraging KNN-SV, a data valuation model.
CNN Explanation Technique Based on Contribution-Based Input Sampling and Block-Wise Feature Aggregation
LG AI Research has developed SISE, a new image recognition explanation technology that overcomes the limitations of existing XAI models.
LG AI Research 119
Introduces the latest trends in generative models, including the Score-based models and VAEBM that drew attention at ICLR 2021.
LG AI Research 126
This introduces generative models and SDE-based Score-based Generative Modeling, key trends at ICLR 2021.
LG AI Research 125
Introduces the latest reinforcement learning research trends for solving real-world problems, as discussed at ICLR 2021.
LG AI Research 156
It covers the characteristics of combinatorial optimization problems and the complexity of integer programming, as introduced at ICML 2021.
[ICML 2021] Part 2: Generative Models for OOD Detection
This paper introduces a new methodology that leverages the characteristics of Hierarchical VAE to improve Out-of-distribution detection performance.
[ICML 2021] Part 3: Spatio-temporal Time-series Forecasting
This introduces graph-based Spatio-temporal Time-series Forecasting research presented at ICML 2021.
The Role of Speech Recognition Datasets in the Infinite Advancement of Voice-Based AI
This analyzes the role of benchmark datasets, a key factor determining the advancement and performance evaluation of voice-based AI technology, along with the current status in Korea and abroad.
LG AI Research Pushes Past the Limits of Vision Inspection AI
LG AI Research used Contrastive Learning to build an unsupervised anomaly detection model with higher accuracy than supervised learning.
LG AI Research 183
LG AI Research has revealed the technical principles of EXAONE, a multimodal model that understands text and images bidirectionally.
[NeurIPS 2021] Part 1: Generative Models - Diffusion Model Review
This piece analyzes the principles of Diffusion Models, a core component of generative models, and the differences among various generative models.
LG AI Research: A Review of Variational Deep Embedding-based Deep Clustering
This reviews Variational Autoencoder-based Deep Clustering techniques and key papers presented at NeurIPS 2021.
LG AI Research: Neural Architecture Search (NAS) Review
This reviews the concept of Neural Architecture Search (NAS), which automatically searches for optimal neural network architectures, along with cost-reduction techniques.
LG AI Research 206
Introducing SWAT, a general-purpose policy model that leverages structural embeddings to reflect a robot's morphological information.
LG AI Research 211
From the emergence of DALL-E through VQ-VAE-based models to LG AI Research's L-Verse, we look at the evolution of Vision-Language models.
[ACL 2022] Retrieval-Based Knowledge Augmentation Methods for Natural Language Understanding - LG AI Research BLOG
This post examines various research cases that combine external knowledge and retrieval technology to improve the performance of language models.
LG AI Research 222
Introduces various implementation methodologies for improving the computational efficiency of self-attention, the core of the Transformer.