To overcome differences in observation timing among agents in asynchronous environments, an AOCC structure was proposed to improve MARL learning efficiency.
LG AI Research presented cases of applying Multi-Agent Reinforcement Learning (MARL) to solve real-world problems at AAMAS 2024.
LG AI Research presented multi-agent reinforcement learning research for autonomous driving and industrial site optimization at AAMAS 2024.
A joint study by LG AI Research and the University of Michigan won the NAACL 2024 Social Impact Award for analyzing LLMs' understanding of cultural common sense and their biases.
A joint study by LG AI Research and the University of Michigan analyzing LLMs' understanding of cultural common sense won the NAACL 2024 Social Impact Award.
LG AI Research introduces the latest research trends in foundation models presented at ICLR 2024, focused on interpretability, sustainability, and safety.
This introduces the latest research trends presented at ICLR 2024 regarding the generalization ability, efficiency, and safety of Foundation Models.
It introduces the 'Generative Image Dynamics' research, selected as Best Paper at CVPR 2024, a technology that generates natural motion from still images.
LG AI Research unveiled EXAONE 3.0 7.8B, an open-source model with excellent English and Korean performance.
LG AI Research has open-sourced EXAONE 3.0 7.8B, an expert-grade AI model with outstanding English and Korean performance.
LG AI Research unveiled ChatEXAONE, an enterprise AI agent based on the open-source LLM EXAONE 3.0.
LG AI Research has unveiled ChatEXAONE, an AI agent based on EXAONE 3.0 that supports enterprise work innovation.
LG AI Research has released EXAONEPath, an open-source model specialized in pathology image analysis.
LG AI Research has unveiled EXAONEPath, an open-source model specialized for histopathology image analysis that achieves both high performance and cost efficiency.
LG AI Research presented a Binning-based Pretext Task study at ICML 2024 that improves self-supervised learning performance on tabular data.
LG AI Research presented a new methodology at ICML 2024 that improves learning performance on tabular data.
LG AI Research presented CADO research at ICML 2024, combining reinforcement learning and diffusion models to solve combinatorial optimization problems.
LG AI Research presented CADO, a study combining diffusion models with reinforcement learning to solve combinatorial optimization problems, at ICML 2024.
It introduces the latest research trends for overcoming the limitations of LLMs presented at ACL 2024 and LG AI Research's achievements.
Through the ACL 2024 tutorial session, we explore the latest research trends, including how to evaluate LLM-generated text and its vulnerabilities.
We introduce ChartInstruct, a general-purpose chart understanding model that comprehends the visual information in charts and performs complex reasoning.
We introduce ChartInstruct, a general-purpose chart vision-language model that applies Instruction Tuning to maximize chart understanding and reasoning capabilities.
This piece examines the latest techniques for optimizing inference efficiency and resource usage in LLMs, centered on research presented at ACL 2024.
This piece analyzes the latest efficiency research aimed at solving the computational cost and inference speed issues that come with the growing scale of LLMs.
AI Briefing