Trends · 研究趋势
数据来自 Hugging Face 论文的 AI 提取关键词,按月统计研究方向的增长与热度。
Yifan Xu, Xiao Liu, Xueqiao Sun +7 authors
AndroidLab provides a systematic framework for training and evaluating Android agents, supporting both large language models and multimodal models, and improves their task success rates.
Hugo Laurençon, Lucile Saulnier, Léo Tronchon +9 authors
The OBELICS dataset, containing interleaved image-text documents, is introduced and used to train competitive multimodal models.
Yew Ken Chia, Liying Cheng, Hou Pong Chan +5 authors
A benchmark and framework named M-LongDoc evaluates and improves large multimodal models for document reading, focusing on open-ended solutions and retrieval tasks over lengthy documents.
Lianghui Zhu, Xinggang Wang, Xinlong Wang
Large Language Models fine-tuned as scalable judges (JudgeLM) achieve state-of-the-art performance in evaluating open-ended benchmarks through a comprehensive dataset and benchmark, enhancing judgment efficiency and accuracy.
Qiying Yu, Quan Sun, Xiaosong Zhang +4 authors
CapsFusion is an advanced framework that improves multimodal pretraining data by combining web-based image-text pairs and synthetic captions, leading to enhanced model performance, sample efficiency, and scalability.
Weihao Yu, Zhengyuan Yang, Linjie Li +5 authors
MM-Vet evaluates large multimodal models across complicated tasks using defined vision-language capabilities and a unified LLM-based evaluator.
Vernon Toh, Navonil Majumder, Zhengyuan Liu +2 authors
The MNIST-PRO benchmark isolates perceptual-state construction in partially observable settings, revealing that multimodal agents struggle to integrate fragmented glimpses, continue exploring, and revise incorrect beliefs.
Wenliang Dai, Junnan Li, Dongxu Li +6 authors
InstructBLIP models, built through instruction-aware visual feature extraction on BLIP-2, achieve top performance in vision-language tasks, including zero-shot evaluation and fine-tuned downstream tasks.
北京市昌平区探索星信息技术及软件开发工作室
京ICP备2026059466号