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 1,051 篇，第 5 / 22 页
- ICML 2026DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving
- ICML 2026DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
- ICML 2026DEGAP: Dynamic Entropy-Guided Attention Perturbation for Contrastive Decoding in Large Vision-Language Models
- ICML 2026Degradation-Aware Metric Prompting for Hyperspectral Image Restoration
- ICML 2026Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs
- ICML 2026Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning
- ICML 2026DenseMLLM: Standard Multimodal LLMs for Dense Prediction
- ICML 2026Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
- ICML 2026Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
- ICML 2026Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
- ICML 2026Detecting Errors in AI-Generated Annotations: When and Why Semantic Neighbors Help
- ICML 2026Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
- ICML 2026Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
- ICML 2026Difference-Aware Decision Learning for Multimodal Image Fusion
- ICML 2026Differentiable Conformal Training for LLM Reasoning Factuality
- ICML 2026DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
- ICML 2026Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics
- ICML 2026Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs
- ICML 2026Discovering Differences in Strategic Behavior between Humans and LLMs
- ICML 2026Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
- ICML 2026Discriminative Visual Process Rewards for Scaling Thinking at Test-Time with Images
- ICML 2026Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography
- ICML 2026Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
- ICML 2026Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
- ICML 2026Dismantling the Illusion of Vision-Language-Action Models Competence via Explicit Distributional Shifts
- ICML 2026Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers
- ICML 2026Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMs
- ICML 2026Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs
- ICML 2026Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
- ICML 2026DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement
- ICML 2026Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation
- ICML 2026Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
- ICML 2026Divide and Conquer: Reliable Multi-View Evidential Learning for Deepfake Detection
- ICML 2026DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home
- ICML 2026DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model
- ICML 2026dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
- ICML 2026Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox
- ICML 2026Do Vision and Text Cues Exhibit Evidential Coupling? UFO: A Benchmark for Compositional Multimodal Reasoning in Unified Models
- ICML 2026Do-Prompt: Causal Interventions Meet Variational Prompt Bottlenecks
- ICML 2026DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents
- ICML 2026DocVAL: Validated Chain-of-Thought Distillation for Grounded Document VQA
- ICML 2026Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
- ICML 2026Does Reasoning Improve Seeing? Understanding When Vision-Language Models Benefit from Thinking
- ICML 2026Don't Force the Fit: Bounded Log-Likelihood Loss for Enhanced Reasoning in Large Language Models
- ICML 2026Don't Forget Why You Started: Tackling Dual Forgetting in Vision-Language Continual Learning
- ICML 2026Don't Overthink with Pixels: Efficient Reasoning for Segmentation
- ICML 2026DOUBT: Decoupled Object-level Understanding and Bridging via vMF-based Trustworthiness for Hallucination Detection in MLLMs
- ICML 2026DPsurv: Dual-Prototype Evidential Fusion for Uncertainty-Aware and Interpretable Whole Slide Image Survival Prediction
- ICML 2026DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents
- ICML 2026DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models
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。