Research map

Vision-language and multimodal: research map

Multimodal LLMs, CLIP-style models, VQA and embodied tasks.

7,482 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026), in 6 topics. Within all five venues, its share grew from 6.0% in 2023–24 to 10.5% in 2025–26 (1,587 → 4,783 papers at ICML, NeurIPS, CVPR and AAAI, the venues with data for all four years).

Explore Vision-language and multimodal in the interactive map

Topics

• Multimodal LLMs · 2,371 papers
  VLM capability analysis, Chain-of-thought multimodal reasoning, Multimodal LLM benchmarks
• Human and embodied modeling · 1,673 papers
  Scene graph generation, Language-grounded scene text and structure, Multimodal retrieval-augmented modeling
• Cross-modal learning · 1,303 papers
  Multimodal fusion with missing modalities, Multi-modality image fusion, Medical multimodal fusion
• CLIP and zero-shot · 959 papers
  Open-vocabulary alignment from VLMs, Attribute-based zero-shot learning, Adapting VLMs for zero-shot classification
• Robot action and navigation · 630 papers
  Vision-language-action foundation models, Memory and subgoal-based manipulation, Embodied multimodal LLM agents
• Visual question answering · 546 papers
  Universal VQA models, Attention and prior-robust VQA, Vision-language model VQA evaluation

Most cited papers in Vision-language and multimodal

• Deep contextualized word representations (ICLR 2018 · 12,263 citations)
• Learning Transferable Visual Models From Natural Language Supervision (ICML 2021 · 5,285 citations)
• Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering (CVPR 2018 · 5,159 citations)
• Making the v in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering (CVPR 2017 · 2,316 citations)
• Stacked Attention Networks for Image Question Answering (CVPR 2016 · 2,094 citations)
• CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning (CVPR 2017 · 1,831 citations)
• Image Captioning With Semantic Attention (CVPR 2016 · 1,739 citations)
• Conditional Prompt Learning for Vision-Language Models (CVPR 2022 · 1,735 citations)
• Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning (CVPR 2017 · 1,734 citations)
• Improved Baselines with Visual Instruction Tuning (CVPR 2024 · 1,490 citations)
• Visual Instruction Tuning (NeurIPS 2023 · 1,198 citations)
• Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (CVPR 2018 · 1,195 citations)