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

3,075 papers, page 56 of 62

2751. NeurIPS 2025Representation Consistency for Accurate and Coherent LLM Answer Aggregation
2752. NeurIPS 2025Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition
2753. NeurIPS 2025ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code
2754. NeurIPS 2025Restoring Pruned Large Language Models via Lost Component Compensation
2755. NeurIPS 2025Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
2756. NeurIPS 2025Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion
2757. NeurIPS 2025Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
2758. NeurIPS 2025Revealing Multimodal Causality with Large Language Models
2759. NeurIPS 2025Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
2760. NeurIPS 2025Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability
2761. NeurIPS 2025Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
2762. NeurIPS 2025Revisiting Semi-Supervised Learning in the Era of Foundation Models
2763. NeurIPS 2025Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening
2764. NeurIPS 2025RGB-to-Polarization Estimation: A New Task and Benchmark Study
2765. NeurIPS 2025RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
2766. NeurIPS 2025Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI
2767. NeurIPS 2025RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning
2768. NeurIPS 2025Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data
2769. NeurIPS 2025RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
2770. NeurIPS 2025Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
2771. NeurIPS 2025RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
2772. NeurIPS 2025Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics
2773. NeurIPS 2025RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills
2774. NeurIPS 2025Robust Cross-modal Alignment Learning for Cross-Scene Spatial Reasoning and Grounding
2775. NeurIPS 2025Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention
2776. NeurIPS 2025Robust Hallucination Detection in LLMs via Adaptive Token Selection
2777. NeurIPS 2025Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
2778. NeurIPS 2025Robustness in Both Domains: CLIP Needs a Robust Text Encoder
2779. NeurIPS 2025RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
2780. NeurIPS 2025ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
2781. NeurIPS 2025RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
2782. NeurIPS 2025RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
2783. NeurIPS 2025RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events
2784. NeurIPS 2025RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video
2785. NeurIPS 2025Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
2786. NeurIPS 2025SAFE: Multitask Failure Detection for Vision-Language-Action Models
2787. NeurIPS 2025SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
2788. NeurIPS 2025SafeVid: Toward Safety Aligned Video Large Multimodal Models
2789. NeurIPS 2025SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
2790. NeurIPS 2025SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation
2791. NeurIPS 2025SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding
2792. NeurIPS 2025SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning
2793. NeurIPS 2025SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models
2794. NeurIPS 2025Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs
2795. NeurIPS 2025Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
2796. NeurIPS 2025SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
2797. NeurIPS 2025Scaffolding Dexterous Manipulation with Vision-Language Models
2798. NeurIPS 2025Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis
2799. NeurIPS 2025Scaling Language-centric Omnimodal Representation Learning
2800. NeurIPS 2025Scaling Laws for Optimal Data Mixtures

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.