Video question answering (VQA) with vision-language models (VLMs) depends critically on which frames are selected from the input video, yet most systems rely on uniform or heuristic sampling that cannot be optimized for downstream answering quality. We introduce \textbf{HORNet}, a lightweight frame selection policy trained with Group Relative Policy Optimization (GRPO) to learn which frames a frozen VLM needs to answer questions correctly. With fewer than 1M trainable parameters, HORNet reduces input frames by up to 99\% and VLM processing time by up to 93\%, while improving answer quality on short-form benchmarks (+1.7\% F1 on MSVD-QA) and achieving strong performance on temporal reasoning tasks (+7.3 points over uniform sampling on NExT-QA). We formalize this as Select Any Frames (SAF), a task that decouples visual input curation from VLM reasoning, and show that GRPO-trained selection generalizes better out-of-distribution than supervised and PPO alternatives. HORNet's policy further transfers across VLM answerers without retraining, yielding an additional 8.5\% relative gain when paired with a stronger model. Evaluated across six benchmarks spanning 341,877 QA pairs and 114.2 hours of video, our results demonstrate that optimizing \emph{what} a VLM sees is a practical and complementary alternative to optimizing what it generates while improving efficiency. Code is available at https://github.com/ostadabbas/HORNet.
School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院);Department of Mathematics, University of California, San Diego(加州大学圣地亚哥分校数学系);School of Software Engineering, Xi'an Jiaotong University(西安交通大学软件工程学院)
GraghVQA: Language-Guided Graph Neural Networks for Graph-based Visual Question Answering
Stanford University(斯坦福大学)
图像不仅仅是对象或属性的集合--它们代表了相互连接的对象之间的关系网。场景图作为一种新的图像结构化图形表示形式出现。场景图将对象编码为通过成对关系连接的节点作为边。为了支持场景图上的问答,我们提出了GraphVQA,一个语言引导的图神经网络框架,它将自然语言问题翻译和执行为图节点之间消息传递的多次迭代。我们探索了GraphVQA框架的设计空间,并讨论了不同设计选择的权衡。我们在GQA数据集上的实验表明,GraphVQA的性能大大优于最先进的模型(88.43% vs. 94.78%)。
Saliency Guided Longitudinal Medical Visual Question Answering
Dept. of Computer Science and Engineering University of California, San Diego(计算机科学与工程系,加州大学圣地亚哥分校);Dept. of Radiology and Biomedical Imaging Yale University(放射学与生物医学成像系,耶鲁大学)
Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering
University of Texas at Austin(德克萨斯大学奥斯汀分校);Arizona State University(亚利桑那州立大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Massachusetts Institute of Technology(麻省理工学院)
VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstruction
1 Academy for Engineering;Technology, Fudan University, Shanghai, China;2 Institute of Metaverse \& Intelligent Medicine, Fudan University, Shanghai, China;3 Engineering Research Center of AI;4 Jilin Provincial Key Laboratory of Intelligence Science
DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering
National and Local Joint Engineering Laboratory of Computer Aided Design, School of Software Engineering, Dalian University(大连大学软件工程学院计算机辅助设计国家地方联合工程实验室);School of Computer Science and Technology, Dalian University of Technology(大连理工大学计算机科学与技术学院)
VisRAG2.0: Mitigating Visual Hallucinations via Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
School of Software and Microelectronics, Peking University, China(北京大学软件与微电子学院);School of Computer Science and Engineering, Northeastern University, China(东北大学计算机科学与工程学院);Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学人工智能研究院计算机科学与技术系)
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Khoury College of Computer Sciences, Northeastern University(东北大学克劳尔计算机科学学院);New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别新实验室)
SKLCCSE, School of Artificial Intelligence, Beihang University, Beijing, China(北京航空航天大学人工智能学院);Hangzhou International Innovation Institute, Beihang University, Hangzhou, China(北京航空航天大学杭州国际创新研究院)
Copy-Move Forgery Detection and Question Answering for Remote Sensing Image
Faculty of Information Science and Engineering, Ocean University of China(信息科学与工程学院,中国海洋大学);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(杭州高等研究院,中国科学院大学)
GHR-VQA: Graph-guided Hierarchical Relational Reasoning for Video Question Answering
School of ECE National Technical University of Athens(国家技术大学雅典电子工程学院);Robotics Institute Athena Research Center(雅典研究中心机器人研究所);University of Luxembourg(卢森堡大学)