arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.09586cs.CV
收藏

视觉语言模型:对26K篇论文的综述

Vision Language Models: A Survey of 26K Papers

School of Computer Science, The University of Manchester, Manchester, UK(曼彻斯特大学计算机科学学院)

Fengming Lin

AI总结:

该综述通过分析2023-2025年三大顶会26104篇论文,量化了视觉语言模型崛起、生成方法扩展及3D/视频韧性三大趋势,并揭示了VLM中参数高效适配与指令微调的主导地位。

摘要:

我们提出了一种透明、可复现的研究趋势测量方法,该方法覆盖了2023至2025年间来自CVPR、ICLR和NeurIPS的26,104篇被接收论文。我们对标题和摘要进行标准化处理、短语保护,并与手工构建的词典进行匹配,以分配最多35个主题标签,并挖掘关于任务、架构、训练机制、目标函数、数据集以及共同提及模态的细粒度线索。该分析量化了三个宏观转变:(1)多模态视觉-语言-大语言模型工作的急剧增长,这些工作日益将经典感知重新定义为指令跟随和多步推理;(2)生成方法的稳步扩展,其中扩散研究围绕可控性、蒸馏和速度进行整合;(3)3D和视频活动的韧性,其构成从NeRF转向高斯泼溅,并且越来越强调以人类和智能体为中心的理解。在视觉语言模型内部,参数高效适配(如提示学习、适配器、LoRA)和轻量级视觉-语言桥接占据主导;训练实践从从头构建编码器转向指令微调和微调强骨干网络;对比目标相对于交叉熵/排序和蒸馏有所退却。跨会议比较显示,CVPR在3D方面足迹更强,而ICLR的视觉语言模型份额最高,同时可靠性主题(如效率或鲁棒性)在各领域扩散。我们发布了词典和方法论,以便进行审计和扩展。局限性包括词典召回率和仅限摘要的范围,但纵向信号在各会议和年份间保持一致。

英文摘要:

We present a transparent, reproducible measurement of research trends across 26,104 accepted papers from CVPR, ICLR, and NeurIPS spanning 2023-2025. Titles and abstracts are normalized, phrase-protected, and matched against a hand-crafted lexicon to assign up to 35 topical labels and mine fine-grained cues about tasks, architectures, training regimes, objectives, datasets, and co-mentioned modalities. The analysis quantifies three macro shifts: (1) a sharp rise of multimodal vision-language-LLM work, which increasingly reframes classic perception as instruction following and multi-step reasoning; (2) steady expansion of generative methods, with diffusion research consolidating around controllability, distillation, and speed; and (3) resilient 3D and video activity, with composition moving from NeRFs to Gaussian splatting and a growing emphasis on human- and agent-centric understanding. Within VLMs, parameter-efficient adaptation like prompting/adapters/LoRA and lightweight vision-language bridges dominate; training practice shifts from building encoders from scratch to instruction tuning and finetuning strong backbones; contrastive objectives recede relative to cross-entropy/ranking and distillation. Cross-venue comparisons show CVPR has a stronger 3D footprint and ICLR the highest VLM share, while reliability themes such as efficiency or robustness diffuse across areas. We release the lexicon and methodology to enable auditing and extension. Limitations include lexicon recall and abstract-only scope, but the longitudinal signals are consistent across venues and years.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑