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 1,366 篇，第 22 / 28 页
- NeurIPS 2026See it to Place it: Evolving Macro Placements with Vision Language Models
- NeurIPS 2026Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning
- NeurIPS 2026Seeing the World through Any Eyes
- NeurIPS 2026Seeing Together: Multi-Robot Cooperative Egocentric Spatial Reasoning with Multimodal Large Language Models
- NeurIPS 2026SEGA: Spectral-Energy Guided Attention for Resolution Extrapolation in Diffusion Transformers
- NeurIPS 2026Segment and Select: Vision-Language Segmentation in 3D Scenarios
- NeurIPS 2026Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation
- NeurIPS 2026Selective Answering for Medical VQA via Parallel Independent Claim Verification
- NeurIPS 2026Selective Disk Bispectrum: A Complete and Rotation Invariant Image Descriptor
- NeurIPS 2026Self-Calibrated GUI Reward Model via Inverse Dynamic Modeling
- NeurIPS 2026Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
- NeurIPS 2026SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
- NeurIPS 2026Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models
- NeurIPS 2026Semantic Freedom Bottleneck for Domain-Generalized Multimodal Face Anti-Spoofing
- NeurIPS 2026SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers
- NeurIPS 2026SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
- NeurIPS 2026Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
- NeurIPS 2026SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
- NeurIPS 2026SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
- NeurIPS 2026SF-DST: Adapting Vision-Language Models for Anomaly Detection via Asymmetric Modulation and A-LoRA
- NeurIPS 2026SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs
- NeurIPS 2026Shared-Noise Mechanisms for Verifiable Differentially Private Counting
- NeurIPS 2026SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring
- NeurIPS 2026SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
- NeurIPS 2026Signed-Permutation Coordinate Transport for RMSNorm Transformers
- NeurIPS 2026SiliciclasticReservoirs: A Million-Reservoir Dataset and Flow-Matching Foundation Model for 3D Siliciclastic Reservoir Generation
- NeurIPS 2026SiliconBench: Speed, Memory, and Fidelity for LLM Inference on Apple Silicon
- NeurIPS 2026Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
- NeurIPS 2026Simplified Reversible Residual Networks
- NeurIPS 2026SimVLA: Attributing Gains in VLA Models Through Controlled Ablation
- NeurIPS 2026SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
- NeurIPS 2026SING-CH: Task-Scale-Agnostic Lifelong Cross-Modal Hashing on Statistical Manifolds
- NeurIPS 2026Single-Pass Evidence Measurement for Interpretable and Uncertainty-Aware Multimodal Face Anti-Spoofing
- NeurIPS 2026SkillCIR: Intent-Guided Skill Composition for Training-Free Composed Image Retrieval
- NeurIPS 2026SkipSR: Faster Super-Resolution with Token Skipping
- NeurIPS 2026SLVMBench: Skill Learning from Video Memory
- NeurIPS 2026SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memory
- NeurIPS 2026sMMC-22M: A Context-Aware Dataset and Benchmark for Single-Cell Spatial Transcriptomics
- NeurIPS 2026SOAR: Regression-based LiDAR Relocalization for UAVs
- NeurIPS 2026SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation
- NeurIPS 2026Soft Token Alignment for Cross-Lingual Reasoning
- NeurIPS 2026SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
- NeurIPS 2026SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
- NeurIPS 2026Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
- NeurIPS 2026Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models
- NeurIPS 2026SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models
- NeurIPS 2026SP$^3$: Spherical Priors for Plug-and-Play Restoration
- NeurIPS 2026SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver
- NeurIPS 2026SpaG-DiT: Enhancing Spatial Grounding for Diffusion Transformers
- NeurIPS 2026Sparse All-Layer Connector for Domain Generalised Semantic Segmentation
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。