新框架增强知识型视觉问答系统 · 跟踪 5 个来源

报道来源 [7]

1. Hugging Face Daily Papers TIER_1 English(EN) · 2026-08-26 10:58

   SeVeR：用于3D医学图像问答的选择性视觉暴露与检索

   Volumetric medical VQA requires reasoning over long and redundant 3D visual token sequences, especially in multi-sequence MRI where complementary modalities provide diverse diagnostic cues but expose the decoder to many repeated anatomical regions. To investigate reasoning under …

2. arXiv cs.AI TIER_1 English(EN) · Long Shu, Shuochen Liu, Wei Chen, Junda Lin, Zhi Zheng, Huijun Hou, Tong Xu · 2026-08-25 04:00

   SAFE-G：面向知识型视觉问答的结构感知忠实证据引导生成

   arXiv:2608.21796v1 Announce Type: cross Abstract: Knowledge-based Visual Question Answering (KB-VQA) aims to answer queries that necessitate reasoning over external knowledge sources beyond the visual content. Typically, current methods fuse multimodal features to retrieve extern…

3. Hugging Face Daily Papers TIER_1 English(EN) · 2026-08-20 07:37

   用于多模态视觉问答的引导式证据获取

   Multimodal LLMs can see a document, but they often can't read it reliably. Small text, tables, visual cues, and topological elements still trip them up under direct visual inference, even when the page is already sitting in the model's context. Most document-VQA systems treat per…

4. arXiv cs.CV TIER_1 English(EN) · Yaojun Hu, Danyang Tu, Yang Liu, Jiajin Zhang, Wei Fang, Zhiqiang Liu, Chunlai Dong, Yingda Xia, Haochao Ying, Jian Wu, Ling Zhang · 2026-08-27 04:00

   SeVeR：用于3D医学图像问答的选择性视觉暴露与检索

   arXiv:2608.25630v1 Announce Type: new Abstract: Volumetric medical VQA requires reasoning over long and redundant 3D visual token sequences, especially in multi-sequence MRI where complementary modalities provide diverse diagnostic cues but expose the decoder to many repeated ana…

5. arXiv cs.CV TIER_1 English(EN) · Hangrui Xu, Zhengxian Wu, Yunyao Yu, Zhuohong Chen, Rui Cong, Xiangwen Deng, Zhifang Liu, Peng Jiao, Haoqian Wang · 2026-08-25 04:00

   超越视觉相似性：面向知识型视觉问答的实体对齐检索

   arXiv:2608.21450v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, existing retrieval pipelines predominantly employ CLIP-style dual encoders, which …

6. arXiv cs.CV TIER_1 English(EN) · Qiyou Liu, Yong Zhang, Jianjie Luo, Zhenguo Yang, Yi Yu · 2026-08-25 04:00

   利用结构化上下文推理增强知识型视觉问答

   arXiv:2608.21431v1 Announce Type: new Abstract: Knowledge-based Visual Question Answering aims to answer questions about an image by integrating external knowledge with visual and textual information. Recent approaches often rely on in-context learning to prompt Large Language Mo…

7. arXiv cs.CV TIER_1 English(EN) · Quanxing Xu, Ling Zhou, Xian Zhong, Feifei Zhang, Rubing Huang · 2026-08-25 04:00

   QIRL：优化问答图像关系学习，实现偏见鲁棒的视觉问答

   arXiv:2504.03337v2 Announce Type: replace Abstract: Existing bias mitigation methods for Visual Question Answering (VQA), a typical Artificial intelligence application, endure two main limitations. First, they fail to capture the optimal relation between images and texts, as prev…