A new benchmark evaluates how role-playing agents interact socially.
― 6 min read
Ming Yan
A new framework improves how language agents learn and perform tasks.
― 6 min read
A new framework improves efficiency and accuracy in solving complex physical problems.
― 6 min read
MIBench tests multimodal models' performance on multiple images.
― 6 min read
mPLUG-Owl3 improves understanding of images and videos for better responses.
― 6 min read
A new method to combine language models more effectively.
― 6 min read
MaVEn enhances AI's ability to process multiple images for better reasoning.
― 5 min read