多模态大模型论文趋势 2023–2026

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。

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 1,401 篇，第 3 / 29 页

101. ICLR 2026Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection
102. ICLR 2026Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs
103. ICLR 2026Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes
104. ICLR 2026Beyond Speedup - Utilizing KV Cache for Sampling and Reasoning
105. ICLR 2026Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models
106. ICLR 2026Beyond Student: An Asymmetric Network for Neural Network Inheritance
107. ICLR 2026Beyond Text-Only: Towards Multimodal Table Retrieval in Open-World
108. ICLR 2026Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
109. ICLR 2026Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
110. ICLR 2026BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment
111. ICLR 2026Bilateral Information-aware Test-time Adaptation for Vision-Language Models
112. ICLR 2026BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models
113. ICLR 2026Bird's-eye-view Informed Reasoning Driver
114. ICLR 2026Block Recurrent Dynamics in Vision Transformers
115. ICLR 2026Block-wise Adaptive Caching for Accelerating Diffusion Policy
116. ICLR 2026BOLT: Decision‑Aligned Distillation and Budget-Aware Routing for Constrained Multimodal QA on Robots
117. ICLR 2026Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
118. ICLR 2026Boosting Medical Visual Understanding From Multi-Granular Language Learning
119. ICLR 2026Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization
120. ICLR 2026Bootstrapping MLLM for Weakly‑Supervised Class‑Agnostic Object Counting
121. ICLR 2026BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
122. ICLR 2026Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
123. ICLR 2026Branch and Bound Search for Exact MAP Inference in Credal Networks
124. ICLR 2026Branched Schrödinger Bridge Matching
125. ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
126. ICLR 2026Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
127. ICLR 2026Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding
128. ICLR 2026Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
129. ICLR 2026Bridging the Gap Between Promise and Performance for FP4 Quantization
130. ICLR 2026C-Evolve: Consensus-based Evolution for Prompt Groups
131. ICLR 2026Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
132. ICLR 2026Cache-to-Cache: Direct Semantic Communication Between Large Language Models
133. ICLR 2026Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
134. ICLR 2026cadrille: Multi-modal CAD Reconstruction with Reinforcement Learning
135. ICLR 2026Calibrating Verbalized Confidence with Self-Generated Distractors
136. ICLR 2026Can Large Language Models Match the Conclusions of Systematic Reviews?
137. ICLR 2026Can LLMs Move Beyond Short Exchanges to Realistic Therapy Conversations?
138. ICLR 2026Can LLMs Reason Soundly in Law? Auditing Inference Patterns for Legal Judgment
139. ICLR 2026Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
140. ICLR 2026Can SAEs reveal and mitigate racial biases of LLMs in healthcare?
141. ICLR 2026Can Vision-Language Models Answer Face to Face Questions in the Real-World?
142. ICLR 2026Can Vision–Language Models Assess Graphic Design Aesthetics? A Benchmark, Evaluation, and Dataset Perspective.
143. ICLR 2026Can we generate portable representations for clinical time series data using LLMs?
144. ICLR 2026Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
145. ICLR 2026CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning
146. ICLR 2026CAR-LoRA: Training Compression-Aware and Robust LoRA Adapters for Evolving LLMs
147. ICLR 2026CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
148. ICLR 2026CaReBench: A Fine-grained Benchmark for Video Captioning and Retrieval
149. ICLR 2026CARL: Camera-Agnostic Representation Learning for Spectral Image Analysis
150. ICLR 2026CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language Model

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。