論文要約性能で見る最近のLLM(2024/7)
705{icon} {views} 目的 最近いろいろなLLMが出ているが、論文要約というタスクで見たときにそれぞれがどの程度の性能/コストなのかを見ていく。コスト的と性能両方見て、どれが使いやすいのかを考えたい。 概要 […]...
論文まとめ:LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
115{icon} {views} タイトル:LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control 著者:Ji […]...
論文まとめ:Beyond Aesthetics: Cultural Competence in Text-to-Image Models
118{icon} {views} タイトル:Beyond Aesthetics: Cultural Competence in Text-to-Image Models 著者:Nithish Kannen, Arif […]...
論文まとめ:Unveiling Encoder-Free Vision-Language Models
268{icon} {views} タイトル:Unveiling Encoder-Free Vision-Language Models 著者:Haiwen Diao, Yufeng Cui, Xiaotong Li, […]...
論文まとめ:MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures
191{icon} {views} タイトル:MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures URL:https://mixeval.g […]...
論文まとめ:Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
299{icon} {views} * タイトル:Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text […]...
論文まとめ:ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimodal Models
187{icon} {views} 論文タイトル:ConTextual: Evaluating Context-Sensitive Text-Rich Visual Reasoning in Large Multimod […]...
論文まとめ:COLE: A Hierarchical Generation Framework for Graphic Design
275{icon} {views} * タイトル:COLE: A Hierarchical Generation Framework for Graphic Design * 著者:Peidong Jia, Chenxu […]...
論文まとめ:Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4
468{icon} {views} 論文タイトル:Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4 著者:Sond […]...
論文まとめ:Gemini: A Family of Highly Capable Multimodal Models
414{icon} {views} タイトル:Gemini: A Family of Highly Capable Multimodal Models 著者:Gemini Team((842 additional aut […]...