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

1,401 papers, page 19 of 29

901. ICLR 2026PRISM: Controllable Diffusion for Compound Image Restoration with Scientific Fidelity
902. ICLR 2026PRISM: Enhancing PRotein Inverse Folding through Fine- Grained Retrieval on Structure-Sequence Multimodal Representations
903. ICLR 2026PRISM: Festina Lente Proactivity—Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
904. ICLR 2026PRISMM-Bench: A Benchmark of Peer-Review Grounded Multimodal Inconsistencies
905. ICLR 2026Probing Rotary Position Embeddings through Frequency Entropy
906. ICLR 2026Product of Experts for Visual Generation
907. ICLR 2026Programming with Pixels: Can Computer-Use Agents do Software Engineering?
908. ICLR 2026Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions
909. ICLR 2026Prompt and Parameter Co-Optimization for Large Language Models
910. ICLR 2026Prompt-Robust Vision-Language Models via Meta-Finetuning
911. ICLR 2026Propaganda AI: An Analysis of Semantic Divergence in Large Language Models
912. ICLR 2026Proper Velocity Neural Networks
913. ICLR 2026ProSafePrune: Projected Safety Pruning for Mitigating Over-Refusal in LLMs
914. ICLR 2026ProtoKV: Long-context Knowledges Are Already Well-Organized Before Your Query
915. ICLR 2026Proximal Supervised Fine-Tuning
916. ICLR 2026ProxyThinker: Test-Time Guidance through Small Visual Reasoners
917. ICLR 2026Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity
918. ICLR 2026PSP: Prompt-Guided Self-Training Sampling Policy for Active Prompt Learning
919. ICLR 2026PT$^2$-LLM: Post-Training Ternarization for Large Language Models
920. ICLR 2026Pulp Motion: Framing-aware multimodal camera and human motion generation
921. ICLR 2026Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference
922. ICLR 2026Pursuing Minimal Sufficiency in Spatial Reasoning
923. ICLR 2026PuzzleWorld: A Benchmark for Multimodal, Open-Ended Reasoning in Puzzlehunts
924. ICLR 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
925. ICLR 2026QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs
926. ICLR 2026QKV Projections Require a Fraction of Their Memory
927. ICLR 2026QLIP: A Dynamic Quadtree Vision Prior Enhances MLLM Performance Without Retraining
928. ICLR 2026QPrompt-R1: Real-Time Reasoning for Domain-Generalized Semantic Segmentation via Group-Relative Query Alignment
929. ICLR 2026QuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
930. ICLR 2026Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models
931. ICLR 2026QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
932. ICLR 2026Query-Guided Spatial–Temporal–Frequency Interaction for Music Audio–Visual Question Answering
933. ICLR 2026QueryStream: Advancing Streaming Video Understanding with Query-Aware Pruning and Proactive Response
934. ICLR 2026QUEST: A robust attention formulation using query-modulated spherical attention
935. ICLR 2026QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
936. ICLR 2026QuoKA: Query-Oriented KV Selection for Efficient LLM Prefill
937. ICLR 2026QuRL: Low-Precision Reinforcement Learning for Efficient Reasoning
938. ICLR 2026R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning
939. ICLR 2026R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning
940. ICLR 2026RACE Attention: A Strictly Linear-Time Attention for Long-Sequence Training
941. ICLR 2026RAG4DMC: Retrieval-Augmented Generation for Data-Level Modality Completion
942. ICLR 2026Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
943. ICLR 2026Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification
944. ICLR 2026Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
945. ICLR 2026RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty
946. ICLR 2026RAR: Reversing Visual Attention Re-Sinking for Unlocking Potential in Multimodal Large Language Models
947. ICLR 2026RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
948. ICLR 2026RCPU: Rotation-Constrained Error Compensation for Structured Pruning of a Large Language Model
949. ICLR 2026Read the Room: Video Social Reasoning with Mental-Physical Causal Chains
950. ICLR 2026Reading Images Like Texts: Sequential Image Understanding in Vision-Language Models

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.