多模态大模型论文趋势 2023–2026
视觉语言模型、图像/视频理解与生成式多模态基础模型
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 11,209 篇被归入该主题的论文。
主要结论
- 多模态大模型论文从 2023 年的 1,226 篇增长到 2026 年的 5,192 篇，三年间扩大到约 4.2 倍。
- NeurIPS 是发多模态大模型论文最多的会议，2023–2026 年共 3,319 篇，占四个会议总量的 30%。
- 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 596 篇。
- 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 1；同组增长最快的AI 智能体是 12 倍，多模态大模型是 4.2 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 433 | 138 | 146 | 509 | 1,226 |
| 2024 | 446 | 321 | 323 | 626 | 1,716 |
| 2025 | 1,074 | 816 | 390 | 795 | 3,075 |
| 2026 | 1,366 | 1,401 | 1,051 | 1,374 | 5,192 |
代表论文
按年份和会议均匀挑选，方便快速看到每一届的样貌
- NeurIPS 2026$\text{A}^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
- ICML 2026[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
- ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
- CVPR 20263D Space as a Scratchpad for Editable Text-to-Image Generation
- NeurIPS 2025$\Delta \mathrm{Energy}$: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalization
- ICML 2025Adapting While Learning: Grounding LLMs for Scientific Problems with Tool Usage Adaptation
- ICLR 2025$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models
- CVPR 20252DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification
- NeurIPS 2024A Concept-Based Explainability Framework for Large Multimodal Models
- ICML 2024A Multimodal Automated Interpretability Agent
- ICLR 2024Alt-Text with Context: Improving Accessibility for Images on Twitter
- CVPR 2024Data-Efficient Multimodal Fusion on a Single GPU
- NeurIPS 20234M: Massively Multimodal Masked Modeling
- ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
- ICLR 2023A Primal-Dual Framework for Transformers and Neural Networks
- CVPR 20233D Concept Learning and Reasoning From Multi-View Images
- NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
- ICML 2026$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA
- ICLR 2026A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models
- CVPR 20263D-IDE 3D Implicit Depth Emergent
全部多模态大模型论文
共 11,207 篇，第 87 / 225 页
- NeurIPS 2026Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models
- NeurIPS 2026Focus, Align, and Diffuse: Time-Series-Aware Keyframe Diffusion for Cardiac Dynamic Synthesis from Sparse Observations
- NeurIPS 2026FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
- NeurIPS 2026Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
- NeurIPS 2026FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models
- NeurIPS 2026FoldAbS: Repurposing the Protein Folding Model as a Foundation Encoder for Antibody Screening
- NeurIPS 2026Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
- NeurIPS 2026ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
- NeurIPS 2026ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models
- NeurIPS 2026Forgery Evidence Peaks Mid-Stack: Forensic Evidence Relay for Multimodal Forgery Detection
- NeurIPS 2026Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
- NeurIPS 2026FoundSurface: Feedforward Ray-Based 3D Scene Surface Reconstruction from Unposed Images
- NeurIPS 2026Fourier Contour Learning for Efficient and Traceable Cardiac MRI Quantification
- NeurIPS 2026Fractal-G: Topology-Aware Heterogeneous Graphs for Medical Image Segmentation
- NeurIPS 2026FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond
- NeurIPS 2026FrameSelect: A Unified Library for Video Frame Selection and Evaluation
- NeurIPS 2026FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated Videos
- NeurIPS 2026Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States
- NeurIPS 2026Frequency‑Aware Flow Matching for Continuous and Consistent Robotic Action Generation
- NeurIPS 2026From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
- NeurIPS 2026From Detection to Understanding — A Multi-Task Dataset for Traffic Anomaly Reasoning
- NeurIPS 2026From Facts to Personas: Interpretable Role Unlearning in LLMs via Mixture-of-Experts
- NeurIPS 2026From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
- NeurIPS 2026From Finding to Linking: Benchmarking and Advancing Cross-Long-Video Reasoning for Multimodal LLMs
- NeurIPS 2026From Heartbeat to Cardiochoreography: A Mechanics Foundation Model for Individualized 4D Cardiac Motion Generation Conditioned on Electrophysiology
- NeurIPS 2026From Label Priors to Task Evidence: Long-Video Frame Selection via Bayesian GRPO
- NeurIPS 2026From Matrix Inversion to Constraints: Provably Tighter Confidence Regions for Importance Weights in Label Shift
- NeurIPS 2026From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient
- NeurIPS 2026From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes
- NeurIPS 2026From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
- NeurIPS 2026From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs
- NeurIPS 2026From Squeezing to Grounding: Visual Guided DPO for Multimodal Hallucination Mitigation
- NeurIPS 2026From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models
- NeurIPS 2026From Weeks to Hours: Fast and Principled SFT Curation for LLM
- NeurIPS 2026FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization
- NeurIPS 2026FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning
- NeurIPS 2026Fusion or Confusion? Multimodal Complexity Is Not All You Need
- NeurIPS 2026FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal Models
- NeurIPS 2026FUTON: Fourier Tensor Network for Implicit Neural Representations
- NeurIPS 2026G$^2$TR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models
- NeurIPS 2026GEAR-Align: Grounding-Evidence-Aware Gradient Routing for Multimodal Alignment
- NeurIPS 2026GEAR: A GPU-Accelerated Global Solver for Nonlinear Programs via Linear Bound Propagation
- NeurIPS 2026GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs
- NeurIPS 2026Generalized Influence Functions for Better Model Change Estimates
- NeurIPS 2026Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife
- NeurIPS 2026Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
- NeurIPS 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
- NeurIPS 2026Generative Scenario Rollouts for End-to-End Autonomous Driving
- NeurIPS 2026GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
- NeurIPS 2026GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查多模态大模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "multimodal-llms"}
常见问题
- 2023–2026 年四大会议一共有多少篇多模态大模型论文？
- 共 11,209 篇，按年份分别是 2023 年 1,226 篇、2024 年 1,716 篇、2025 年 3,075 篇、2026 年 5,192 篇。
- NeurIPS 2026 有多少篇多模态大模型论文？
- NeurIPS 2026 有 1,366 篇多模态大模型论文，上一届是 1,074 篇。
- ICLR 2026 有多少篇多模态大模型论文？
- ICLR 2026 有 1,401 篇多模态大模型论文，上一届是 816 篇。
- ICML 2026 有多少篇多模态大模型论文？
- ICML 2026 有 1,051 篇多模态大模型论文，上一届是 390 篇。
- CVPR 2026 有多少篇多模态大模型论文？
- CVPR 2026 有 1,374 篇多模态大模型论文，上一届是 795 篇。
- 哪个会议的多模态大模型论文最多？
- NeurIPS，2023–2026 年共 3,319 篇。