Výsledky vyhledávání

Report

ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts

Autor: Du, Sinan, Zhang, Guosheng, Wang, Keyao, Wang, Yuanrui, Yue, Haixiao, Zhang, Gang, Ding, Errui, Wang, Jingdong, Xu, Zhengzhuo, Yuan, Chun

Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning tas

Externí odkaz: http://arxiv.org/abs/2412.08341

Zobrazit plný text záznamu

Report

ChartMoE: Mixture of Expert Connector for Advanced Chart Understanding

Autor: Xu, Zhengzhuo, Qu, Bowen, Qi, Yiyan, Du, Sinan, Xu, Chengjin, Yuan, Chun, Guo, Jian

Automatic chart understanding is crucial for content comprehension and document parsing. Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in chart understanding through domain-specific alignment and fine-tuning. Howe

Externí odkaz: http://arxiv.org/abs/2409.03277

Zobrazit plný text záznamu

Report

ChartBench: A Benchmark for Complex Visual Reasoning in Charts

Autor: Xu, Zhengzhuo, Du, Sinan, Qi, Yiyan, Xu, Chengjin, Yuan, Chun, Guo, Jian

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in image understanding and generation. However, current benchmarks fail to accurately evaluate the chart comprehension of MLLMs due to limited chart types and inappropriate m

Externí odkaz: http://arxiv.org/abs/2312.15915

Zobrazit plný text záznamu