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 24 / 28 页
- NeurIPS 2026SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
- NeurIPS 2026T-ReX: Learning Tile-Reuse Indexes for Structured Model Compression
- NeurIPS 2026T2V-AttnDisrupt: Inducing Hallucinations in LVLMs via Misrouting Visual Evidence Retrieval
- NeurIPS 2026TailAdapt: Heavy-Tailed Sparse Variational Adaptation for Long-Tailed Class Incremental Learning
- NeurIPS 2026Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
- NeurIPS 2026TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
- NeurIPS 2026TasteBench: multimodal benchmark for sensory prediction, from molecules to sustainable foods
- NeurIPS 2026Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning
- NeurIPS 2026Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving
- NeurIPS 2026TED: Text-Axis Evidence Decomposition for Prompted Anomaly Localization
- NeurIPS 2026Tempered Guided Diffusion
- NeurIPS 2026TeMPO: Frame-Causal Token Compression for Efficient Video Large Language Model
- NeurIPS 2026Temporal Backtracking Search for Test-time Generative Video Reasoning
- NeurIPS 2026Temporal Slice Learning for AI-Generated Video Detection with 400× Fewer FLOPs
- NeurIPS 2026Test-Time Adaptation via Self-Reinforced Optimal Transport for Zero-Shot OOD Detection with Vision–Language Models
- NeurIPS 2026Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles
- NeurIPS 2026Tethered Predictive-Inertial Proposals with Objective Verification for Diffusion-Prior Inverse Problems
- NeurIPS 2026Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning
- NeurIPS 2026Text-Vision Co-Instructed Image Editing
- NeurIPS 2026TF-PRVR: Training-Free Partially Relevant Video Retrieval for Real-World Generalization
- NeurIPS 2026The Adversarial Gait: Detecting Visual Adversarial Attacks against Vision-Language Models via Self-Targeted Gradient Characterization
- NeurIPS 2026The Alignment Illusion in Multimodal Large Language Models
- NeurIPS 2026The BAMBI Dataset: Multimodal Nadir UAV-Recordings of Forest Wildlife
- NeurIPS 2026The Butterfly Effect in Reasoning: Branch-Structured Distributional Memory for Stochastic Agents
- NeurIPS 2026The Cost of Absolute Position: A Spread-Expressivity Tradeoff for Additive Positional Encodings
- NeurIPS 2026The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
- NeurIPS 2026The Fault in Our Metrics: Revisiting Generative Model Evaluation with Chamfer Distance
- NeurIPS 2026The Graph Concept Bottleneck: Decoding Combinatorial Reasoning in GNNs for Interpretability
- NeurIPS 2026The Marauder’s Map: Bézier Manifolds Reveal Hidden Surfaces for Model Merging and Ensembling
- NeurIPS 2026The Missing Corpus: Infinite Ground Truth for File-Grounded LLM Evaluation
- NeurIPS 2026The Optimal Control Foundation of Early Exits – Turnpikes and ResNets
- NeurIPS 2026The Power of Second Order Methods for Sequence Preconditioning
- NeurIPS 2026The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
- NeurIPS 2026The road reaches every place, the short cut only one: Self-Adversarial Shortcut Mitigation for AI-Generated Image Detection
- NeurIPS 2026The Subjectivity of Monoculture
- NeurIPS 2026The Unembedding Bottleneck: A Mechanistic Analysis of Single Digit Counting in LLMs
- NeurIPS 2026The VLM as Sensor: Bayesian Active Search for Long Video Understanding
- NeurIPS 2026THEIA: A Multimodal Dataset and Benchmark for Vision-Language Analysis of Layout
- NeurIPS 2026They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
- NeurIPS 2026Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving
- NeurIPS 2026Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generation
- NeurIPS 2026Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators
- NeurIPS 2026ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
- NeurIPS 2026TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics
- NeurIPS 2026TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
- NeurIPS 2026Tight Gap-Dependent Regret Bounds and Problem-Independent Bounds for Cost-aware Cascading Bandits
- NeurIPS 2026Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
- NeurIPS 2026Tokenizer-Generator Coupling in Medical Image Generation
- NeurIPS 2026TokenSwap: Benchmarking and Reducing the Modality Gap in Multimodal LLMs
- NeurIPS 2026Too Aligned to be Real: Detecting AI-Generated Images via Cross-modal Alignment Shift
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。