Entrar
insight - Multimodal Models
X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment Study
提案された多言語VIFデータセットの構築方法とX-LLaVAモデルの効率的な多言語拡張フレームワークを示す。
Optimizing Bilingual Large Vision-Language Alignment Study at Seoul National University
Proposing cost-effective methods for multilingual LMM training and dataset construction.
Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Comprehensive Evaluation
Multimodal foundation models like CLIP show robustness under natural distribution shifts but fail to improve robustness under synthetic distribution shifts and adversarial attacks.
Exploring GPT-4V as a Generalist Web Agent: SEEACT Study
GPT-4V shows promise as a generalist web agent with the SEEACT study, highlighting its potential for completing tasks on live websites.
Typographic Attacks in Large Multimodal Models: Alleviating with Informative Prompts
Large Multimodal Models face distractibility from typographic attacks, but can be mitigated by providing more informative prompts.
Produtos
© 2024 by Linnk AI