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

1,051 papers, page 18 of 22

851. ICML 2026STD-Former: Image-Conditioned Texture Dictionary Encoding with Sparse Topological Supervision for Texture Recognition
852. ICML 2026Steal the Patch Size: Adversarially Manipulate Vision Language Models
853. ICML 2026Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation
854. ICML 2026Step-Resolved Data Attribution for Looped Transformers
855. ICML 2026STORM: Segment, Track, and Object Re-Localization from a Single Image
856. ICML 2026StructMamPose: From Sequential Perception to Structural Reasoning for 3D Human Pose Estimation
857. ICML 2026STT-LLM: Structural-Temporal Tokenization for Adapting LLMs to Longitudinal Clinical Profiles
858. ICML 2026Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
859. ICML 2026Suppress and Diversify: Refining Robust Pathways for Corruption Robustness
860. ICML 2026SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding
861. ICML 2026SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
862. ICML 2026Symbal: Detecting Systematic Misalignments in Model-Generated Captions
863. ICML 2026Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
864. ICML 2026Synergistic Space-Vision Processing for Predicate Inference
865. ICML 2026SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment
866. ICML 2026Synthesizing Multimodal Geometry Datasets from Scratch and Enabling Visual Alignment via Plotting Code
867. ICML 2026T-Edit: Triple-Branch Diffusion Anchoring for Consistent Editing
868. ICML 2026Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
869. ICML 2026TabMGP: Martingale Posterior with TabPFN
870. ICML 2026Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
871. ICML 2026Task-and-Model-Aware Fractal-Consistency for Efficient LLM Reasoning
872. ICML 2026Task-Aware Mechanism: Hybrid MoE Vision Tower Towards Holistic Video Understanding
873. ICML 2026Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning
874. ICML 2026TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning
875. ICML 2026Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
876. ICML 2026Temporal-Aware Reasoning Optimization for Video Temporal Grounding
877. ICML 2026Test-Time Debiasing with Probabilistic Prompts via Wasserstein Distance in Vision-Language Models
878. ICML 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding
879. ICML 2026Text-Conditional JEPA for Learning Semantically Rich Visual Representations
880. ICML 2026Text-Driven Fusion for Infrared and Visible Images: Achieving Image Scene Adaptation on Hyperbolic Space
881. ICML 2026TextME: Bridging Unseen Modalities Through Text Descriptions
882. ICML 2026Textual Supervision Enhances Geospatial Representations in Vision-Language Models
883. ICML 2026TGV-KV: Text-Grounded KV Eviction for Vision-Language Models
884. ICML 2026The Abstraction Gap in Vision-Language Causal Reasoning
885. ICML 2026The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment
886. ICML 2026The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path
887. ICML 2026The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-Modal Divergence
888. ICML 2026The Geometry of Representational Failures in Vision Language Models
889. ICML 2026The Hidden Cost of Structured Generation in LLMs: Draft-Conditioned Constrained Decoding
890. ICML 2026The Hidden Risk: Membership Inference Attacks on Multimodal Federated Learning via Modality Imbalance
891. ICML 2026The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
892. ICML 2026The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design
893. ICML 2026The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
894. ICML 2026The Power of Power Law: Asymmetry Enables Compositional Reasoning
895. ICML 2026The Realignment Problem: When Right becomes Wrong in LLMs
896. ICML 2026The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
897. ICML 2026The Signal is in the Steps: Local Scoring for Reasoning Data Selection
898. ICML 2026The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity
899. ICML 2026The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models
900. ICML 2026Think in Cloud, Look at Edges: Semantic-Driven Query Decomposition for Efficient Video Reasoning

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.