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 3,319 篇，第 5 / 67 页
- NeurIPS 2026C3H: Compression-to-Consensus Criteria Hijacking in Multimodal LLM Recommender Systems
- NeurIPS 2026CA-Judge: Teach Large Models to Judge Anomalies via Comparison for Video Anomaly Detection
- NeurIPS 2026CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
- NeurIPS 2026CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models
- NeurIPS 2026CAM: Question Answering on Entity-Centric Videos with Continuous Extraction and Adaptive Querying
- NeurIPS 2026Can an LLM Reason Like a Lawyer? Benchmarking the ability of LLMs to map the facts of a case to the elements of the applicable legal rule
- NeurIPS 2026Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability?
- NeurIPS 2026Can Pixels Alone Reveal Image Origin? Minimax Limits and Learnable Interfaces for Passive Provenance
- NeurIPS 2026Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD
- NeurIPS 2026Can VLMs Reason When to Stop for Human Safety?
- NeurIPS 2026Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
- NeurIPS 2026CanViT: Toward Active-Vision Foundation Models
- NeurIPS 2026CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
- NeurIPS 2026Casper: A Projection-Based Neurosymbolic Layer for Scalable & Guaranteed Constraint Satisfaction
- NeurIPS 2026Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization
- NeurIPS 2026CATS: Acceptance-Oriented Critical Token Adaptive Selection for Multimodal Speculative Decoding
- NeurIPS 2026Causal Benchmarks for Multimodal AI Should Measure Categorical Difference, Not Capability Gap
- NeurIPS 2026Causal-VLM: Dense Causal Captioning in Videos
- NeurIPS 2026CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving
- NeurIPS 2026CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
- NeurIPS 2026CCDiff: Inverse Canonical Correlation Analysis for Discovering Visual Differences in Natural Language
- NeurIPS 2026CECAR: Cache & Expert Co-Aware Routing Accelerates On-Device Inference of MoE LLMs
- NeurIPS 2026CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
- NeurIPS 2026Certification from Examples is Hard for Circuits and Transformers under Minimal Overparametrization
- NeurIPS 2026Chain-of-Correction: Progress-Aware Policy Steering via Anchor-Grounded Predictive Reasoning
- NeurIPS 2026ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
- NeurIPS 2026Channel Mixer: A Pretrainable Tokenizer for Scalable Multi-Channel Vision Transformers
- NeurIPS 2026ChanSFormer: A Channel Agnostic Vision Transformer for Multi-Channel Cell Painting Images
- NeurIPS 2026Characterizing Universal Object Representations Across Vision Models
- NeurIPS 2026ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing
- NeurIPS 2026Cheap Per-Component Testing for PLS, Stable Under Rotation
- NeurIPS 2026ChildPose: Foundation for Children Pose Modeling
- NeurIPS 2026CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models
- NeurIPS 2026CIPHERGRID Benchmark: From Multimodal Rule Inference to Sequential Action
- NeurIPS 2026CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
- NeurIPS 2026Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
- NeurIPS 2026Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
- NeurIPS 2026CLeaR: A Unified Framework for Resolving the Leakage–Degradation Dilemma in Style Transfer
- NeurIPS 2026Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation
- NeurIPS 2026CLEF: EEG Foundation Models for Learning Clinical Semantics
- NeurIPS 2026Closed-Form Linear-Probe Dataset Distillation for Pre-trained Vision Models
- NeurIPS 2026Closing the Indexing-Decoding Gap in Multimodal Generative Retrieval via Prefix Retention Optimization
- NeurIPS 2026Closing the Loop with Fixed-Point Self-Attention
- NeurIPS 2026ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
- NeurIPS 2026CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
- NeurIPS 2026COCOTree: A Dataset and Benchmark for Open Tree-Structured Visual Decomposition
- NeurIPS 2026Code2World: A GUI World Model via Renderable Code Generation
- NeurIPS 2026CoDeRNet: Selective Cross-Task Routing under Heterogeneous Supervision for Change Detection and Captioning
- NeurIPS 2026CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Intervention
- NeurIPS 2026COHE: Auditing Non-Transitivity in Sample Difficulty Proxies for Vision 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。