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 79 / 225 页
- NeurIPS 2026AmbiguousWorld: Benchmarking and Resolving Ambiguous Instructions in Video World Models
- NeurIPS 2026An Efficient Cross-modal Feature Reconstruction Model for Multimodal Multi-class Anomaly Detection
- NeurIPS 2026An Open-Source Training Dataset for Foundation Models for Black-box Optimization
- NeurIPS 2026Anatomy-Activated Mixture-of-Experts for 3D Medical Vision-Language Pre-training
- NeurIPS 2026Anatomy-aware Spatio-Temporal Modeling for Echocardiography Segmentation
- NeurIPS 2026AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion
- NeurIPS 2026Angular Networks: Low-Bit Learning from Randomized Similarity Estimators
- NeurIPS 2026Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation
- NeurIPS 2026Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
- NeurIPS 2026APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts
- NeurIPS 2026Apple-$\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
- NeurIPS 2026Approaching Effective Merging in Model Embedding Space
- NeurIPS 2026Approximate Bayesian inference with exchangeable distributions for neurosymbolic AI
- NeurIPS 2026Approximation Algorithms for GPU Pricing under Finite Capacity
- NeurIPS 2026Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration
- NeurIPS 2026Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning
- NeurIPS 2026Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study
- NeurIPS 2026Arena-T2I Hard: Benchmarking and Improving Faithfulness with Dependency-Aware Checklist Rewards
- NeurIPS 2026Argus: A Cross-Regime Benchmark for the Transferability of Uncertainty Quantification in Computer-Use Agents
- NeurIPS 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
- NeurIPS 2026As the Story Unfolds: Watching a Film and Identifying Characters as a Human Does
- NeurIPS 2026ASAP: Assembly-Source Aligned Pseudocode Refinement For Binary Decompilation
- NeurIPS 2026ASAP: Attention Sink Anchored Pruning
- NeurIPS 2026ASTRA: ADMM-Accelerated Topology Reconfiguration for Dynamic Satellite Constellations
- NeurIPS 2026ASVQ: What Reparameterization Is Just Enough for Efficient Codebook Learning?
- NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
- NeurIPS 2026Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
- NeurIPS 2026Attending on Attention ($A^2$): Smaller Self-Supervised ViTs Localize Better Than Larger Ones
- NeurIPS 2026Attention Alignment Between Humans and Vision-Language Models
- NeurIPS 2026Attention Heads are Complementary Visual Units: Mitigating Hallucinations in LVLMs via Adaptive Visual Cues Focusing
- NeurIPS 2026Attention Transfer Is Not Universally Effective for Vision Transformers
- NeurIPS 2026Attention-based PCA
- NeurIPS 2026Attention-based Routing for Interpretable Multimodal Brain Encoding
- NeurIPS 2026Audible World Models: Spatially Aware Sound Generation for 3D Worlds
- NeurIPS 2026Auditing Attention Head Masking for Out-of-Distribution Detection: Cross-Architecture Wins, Failures, and Polarity Inversions
- NeurIPS 2026Auditing Capsule Vision 2024: Within-Split Train-to-Validation Re-Exposure and a Kvasir-Channel Sensitivity Diagnostic
- NeurIPS 2026Auditing Sabotage Bench: A Benchmark for Detecting and Fixing Research Sabotage in ML Codebases
- NeurIPS 2026Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
- NeurIPS 2026Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria
- NeurIPS 2026Automatically Refining Coding Rules for AI Coding Agents
- NeurIPS 2026Automotive-ENV: Benchmarking Multimodal Models in Automotive Cockpit Environments
- NeurIPS 2026Auxiliary Clues Aware’s Geometry Problem Solving
- NeurIPS 2026AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
- NeurIPS 2026AVIS: Adaptive Test-Time Scaling for Vision–Language Models
- NeurIPS 2026AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression
- NeurIPS 2026BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone
- NeurIPS 2026Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection
- NeurIPS 2026BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
- NeurIPS 2026Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
- NeurIPS 2026BasicLT: Basic-Level Abstraction and Selective Differentiation for Long-Tailed Recognition
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。