AI BriefingLG AI Research news
The latest AI and developer news from LG AI Research, with short summaries.
Visit website →LG AI Research 271
At the IJCAI 2022 conference, research trends emphasizing the importance of reinforcement learning, federated learning, and reasoning capabilities were confirmed.
LG AI Research 272
LG AI Research collaborated with Elsevier to achieve the top performance in the ChEMU 2022 challenge, which extracts reaction information from chemical patents and journals.
LG AI Research: Introducing UniCLIP Technology
It introduces UniCLIP, a unified contrastive learning framework that breaks down boundaries between domains to enhance data efficiency.
LG AI Research 290
LG AI Research developed a new attention mechanism-based AI model that improves HLA-peptide binding prediction performance.
LG AI Research 291
The paper proposes SBM-Transformer, which adjusts attention sparsity based on data to improve computational efficiency.
LG AI Research 294
We propose a new algorithm that improves the stability of offline Learning from Observation (LfO), which imitates expert behavior using only state information.
LG AI Research 297
LG AI Research is researching a loop-based music generation model to help with motif generation, which is at the core of music composition.
Transferring Pre-trained Multimodal Representations via Cross-modal Similarity Matching
This work proposes BeamCLIP, a methodology for efficiently transferring the representational power of large-scale multimodal models to small target models.
LG AI Research 300
Introduces the latest research trends in generative models (SGM) and LLMs presented at NeurIPS 2022.
[NeurIPS 2022] Transferring Pretrained Multimodal Representations via Cross-Modal Similarity Matching
Introduces BeamCLIP, a technique that efficiently transfers the representational power of the large-scale multimodal model CLIP to a smaller model.
LG AI Research 302
LG AI Research reviewed major research trends in generative models, LLMs, and reinforcement learning presented at NeurIPS 2022.
Trends in Causal Representation Learning Research - LG AI Research BLOG
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.
Towards Causal Representation Learning
This paper analyzes the limitations of existing machine learning from a Causal Inference perspective and presents the need for causal representation learning.
Can Large Language Models Improve Few-shot Retrieval Performance for Complex Question Answering
This introduces PromptRank, a technique that uses LLMs to find efficient document paths for complex Multi-hop Question Answering (MQA).
PromptRank Approach to Improve Few-shot Efficiency for Complex Question Answering in LLMs
PromptRank is a technique that combines unsupervised retrieval with an LLM reranker to improve data efficiency in multi-hop question answering.
[ICASSP 2023] Introducing a Multi-Resolution Sequence Aggregation and Model-Agnostic Framework for Time Series Forecasting
This introduces the MAMA framework, which maximizes forecasting performance by leveraging multi-resolution information in time series data.
LG AI Research 334
LG AI Research presented the MAMA framework at ICASSP 2023, maximizing time series forecasting performance.
LG AI Research Attends CVPR 2023 and Hosts NICE Workshop
LG AI Research explored the latest vision research trends at CVPR 2023 and discussed the limitations of image captioning through the NICE workshop.
LG AI Research: CVPR 2023 Research Trends and NICE Workshop Review
LG AI Research analyzed the computer vision research trends presented at CVPR 2023 and visual reasoning techniques leveraging LLMs.
LG AI Research 337
LG AI Research proposed the QASA benchmark and a multi-step reasoning methodology for deep reasoning on scientific literature.