Multimodal LLMs papers, 2023–2026

Key findings

• Multimodal LLMs went from 1,226 papers in 2023 to 5,192 in 2026, roughly 4.2x in three years.
• NeurIPS publishes the most Multimodal LLMs work: 3,319 papers from 2023 to 2026, 30% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 35 in 2023 to 596 in 2026.
• Among the 4 topics under Trending Systems, it ranks #1 by 2026 paper count; the fastest grower in the group, AI Agents, is up 12x versus 4.2x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Multimodal LLMs papers

1,366 papers, page 23 of 28

1101. NeurIPS 2026Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
1102. NeurIPS 2026Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
1103. NeurIPS 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
1104. NeurIPS 2026SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
1105. NeurIPS 2026Spectral Rank Calibration for Continual LoRA Merging in Multimodal Large Language Models
1106. NeurIPS 2026Spectral Unlearning: Transformer Structure-Preserving Updates for Language Model
1107. NeurIPS 2026SPEXT: A Decoupled Multi-Spectral Foundation Model for Earth Observation and Vision-Language Grounding
1108. NeurIPS 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
1109. NeurIPS 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
1110. NeurIPS 2026SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
1111. NeurIPS 2026Split Then Select: Moment-Preserving Density Control for Generalized Primitive Splatting
1112. NeurIPS 2026SpRePE: A Spherical Geometry-Aware Position Embedding scheme for Vision Transformers
1113. NeurIPS 2026SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation
1114. NeurIPS 2026SSR3D-LLM: Structured Spatial Reasoning via Latent Steps for Fine-Grained Grounding in Unified 3D-LLMs
1115. NeurIPS 2026Stability-Aware Self-Training for CLIP under Cross-Modal Anchoring Mismatch
1116. NeurIPS 2026Stable and Scalable Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs
1117. NeurIPS 2026StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training
1118. NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
1119. NeurIPS 2026Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models
1120. NeurIPS 2026Statistical Query Lower Bounds for Smoothed Agnostic Learning
1121. NeurIPS 2026STEER: Route-Aware Adaptive Reasoning for Autonomous Driving
1122. NeurIPS 2026Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models
1123. NeurIPS 2026Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond
1124. NeurIPS 2026Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
1125. NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
1126. NeurIPS 2026StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
1127. NeurIPS 2026Stitched Value Model for Diffusion Alignment
1128. NeurIPS 2026Stranger Things: When Objects Appear Without Their Typical Neighbours
1129. NeurIPS 2026StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos
1130. NeurIPS 2026Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
1131. NeurIPS 2026StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering
1132. NeurIPS 2026StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
1133. NeurIPS 2026Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs
1134. NeurIPS 2026StructLens: A Structural Lens for Language Models via Maximum Spanning Trees
1135. NeurIPS 2026Structural Self-Teaching for Compositional Generation in Unified Multimodal Models
1136. NeurIPS 2026Structure Over Scale: Learning Visual Reasoning from Pedagogical Video
1137. NeurIPS 2026Structure-Prompted Multimodal Protein Language Model for Preference-Aligned Fitness Prediction
1138. NeurIPS 2026Structure, Subspace and System: Push the Real Limit of Extremely Low-Bit Quantization for MoE-LLMs
1139. NeurIPS 2026Structured Sparse Memory for Recurrent Reasoning
1140. NeurIPS 2026Structured State-Space Regularization for Generation-Friendly Image Tokenization
1141. NeurIPS 2026Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
1142. NeurIPS 2026Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging
1143. NeurIPS 2026Subset-Conditioned Boundary Compensation for Missing-Modality Multimodal Classification
1144. NeurIPS 2026SUPERVISE: A Unified Framework for Standardized and Reproducible Superpixel Evaluation
1145. NeurIPS 2026Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
1146. NeurIPS 2026Susceptibilities for Neural Networks Learning from Physical Data
1147. NeurIPS 2026SWE-Pro: A Benchmark for Evaluating LLMs on Performance-Oriented Repository-Level Optimization
1148. NeurIPS 2026SynDORBench: Evaluating LVLM Perceptual Robustness Under Physically Constrained Visibility Conditions
1149. NeurIPS 2026SynGeo: Synergizing Seeing and Proving through Revisable Geometric States
1150. NeurIPS 2026SynIB: Informational Bottleneck for Maximizing Synergy in Multimodal Learning

FAQ

How many Multimodal LLMs papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

11,209 in total: 1,226 in 2023, 1,716 in 2024, 3,075 in 2025, 5,192 in 2026.

How many Multimodal LLMs papers are at NeurIPS 2026?

NeurIPS 2026 has 1,366 Multimodal LLMs papers, versus 1,074 the year before.

How many Multimodal LLMs papers are at ICLR 2026?

ICLR 2026 has 1,401 Multimodal LLMs papers, versus 816 the year before.

How many Multimodal LLMs papers are at ICML 2026?

ICML 2026 has 1,051 Multimodal LLMs papers, versus 390 the year before.

How many Multimodal LLMs papers are at CVPR 2026?

CVPR 2026 has 1,374 Multimodal LLMs papers, versus 795 the year before.

Which conference publishes the most Multimodal LLMs papers?

NeurIPS, with 3,319 papers from 2023 to 2026.