AI BriefingLG AI Research news
The latest AI and developer news from LG AI Research, with short summaries.
Visit website →[ICLR 2022] Part 2: Time Series Anomaly Detection
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 Solves Reinforcement Learning as a Sequence Modeling Problem
Decision Transformer converts reinforcement learning problems into sequence modeling problems, achieving stable policy learning through the Transformer architecture.
LG AI Research 227
Introduces the latest trends in multimodal representation learning and NeRF technology that drew attention at CVPR 2022.
[CVPR 2022] NeRF - Neural Radiance Fields for View Synthesis
We look at the concept behind NeRF technology, which drew attention at CVPR 2022, along with recent research trends including single-image usage, overcoming limitations, and scalability.
[CVPR 2022] Continual Learning Research Trends
This introduces the latest research trends in Transformer-based and self-supervised learning-based continual learning presented at CVPR 2022.
Learning Parameterized Task Structures for Generalization to Unseen Entities
Through Parameterized Subtask Graph Inference (PSGI), AI's generalization performance on untrained new entities and tasks has been improved.
LG AI Research: Commonsense-Based Subgoal Planning Research
They presented a methodology that leverages the commonsense knowledge embedded in LLMs to plan complex tasks step by step, improving planning accuracy through mutual information-based ranking and environment feedback.
Research on Domain Generalization via Grounding Visual Representations Using Text - LG AI Research
Proposed a domain generalization (DG) technique that maintains performance even when the image domain changes, by leveraging human linguistic descriptions.
[ICML 2022] Part 1: Long-Tail Distribution Learning
We examine the concept and various methodologies of Long-Tail Distribution learning to address the data imbalance problem.
[ICML 2022] Part 2: Self-supervised learning - LG AI Research BLOG
This article introduces key techniques from papers on Self-supervised learning presented at ICML 2022, focusing on the ADIOS framework.
LG AI Research 253: Trends in Neural Combinatorial Optimization Research
Introduces the LeNSE methodology for processing large-scale graph data through Neural Combinatorial Optimization (NCO) research presented at ICML 2022.
[GTC 2022] Part 1: Digital Avatar Technology Continues to Grow and Evolve
This summarizes the classification of digital avatars presented at NVIDIA GTC 2022, along with the ACE technology that implements them and its use cases.
LG AI Research GTC 2022 Review: Personalized Image/Language Model and Instant NeRF
It introduces the Personalized Image/Language Model and the innovative Instant NeRF technology presented at NVIDIA GTC 2022.
[IJCAI 2022] Conference Review and Deep Graph Learning Research Trends - LG AI Research BLOG
Through IJCAI 2022, the latest AI research trends including reinforcement learning, federated learning, and causal inference were analyzed.
[CLEF 2022] Context-Aware Named Entity Recognition and Relation Extraction - LG AI Research Blog
LG AI Research demonstrated its technical capabilities by achieving high performance in the ChEMU 2022 challenge, which extracts information from chemical patents.
LG AI Research: Introducing UniCLIP Technology
UniCLIP is a technology that improves data efficiency by unifying intra-domain and inter-domain contrastive learning into a single framework.
LG AI Research ECCV 2022 Review
LG AI Research presented research achievements related to continual learning and scale-invariant networks at ECCV 2022.
LG AI Research Develops HLA-Peptide Binding Prediction AI Model for Personalized Cancer Vaccine Development
LG AI Research has developed a new AI model based on a Conditional Attention mechanism that effectively predicts the interaction between HLA and peptides.
LG AI Research 293
LG AI Research has proposed SBM-Transformer, which captures both computational efficiency and performance at the same time.
LG AI Research: Presents an Offline Imitation Learning Methodology That Learns from State Information Alone
The research proposed a new imitation learning methodology that leverages expert demonstrations containing only state information to enable stable learning even in offline settings.