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

5,190 papers, page 52 of 104

2551. ICLR 2026Test-Time Scaling with Reflective Generative Model
2552. ICLR 2026Text summarization via global structure awareness
2553. ICLR 2026The Achilles’ Heel of LLMs: How Altering a Handful of Neurons Can Cripple Language Abilities
2554. ICLR 2026The Art of Scaling Reinforcement Learning Compute for LLMs
2555. ICLR 2026The Devil behind the mask: An emergent safety vulnerability of Diffusion LLMs
2556. ICLR 2026THE END OF MANUAL DECODING: TOWARDS TRULY END-TO-END LANGUAGE MODELS
2557. ICLR 2026The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
2558. ICLR 2026The Geometry of Reasoning: Flowing Logics in Representation Space
2559. ICLR 2026The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?
2560. ICLR 2026The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
2561. ICLR 2026The Lattice Representation Hypothesis and Concept Algebra in LLMs
2562. ICLR 2026THE PATH OF LEAST RESISTANCE: GUIDING LLM REASONING TRAJECTORIES WITH PREFIX CONSENSUS
2563. ICLR 2026The Pensieve Paradigm: Stateful Language Models with Learned Memory Management
2564. ICLR 2026The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens
2565. ICLR 2026The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss
2566. ICLR 2026The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM
2567. ICLR 2026THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics
2568. ICLR 2026Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
2569. ICLR 2026Thicker and Quicker: The Jumbo Token for Fast Plain Vision Transformers
2570. ICLR 2026Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning
2571. ICLR 2026Think Then Embed: Generative Context Improves Multimodal Embedding
2572. ICLR 2026Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
2573. ICLR 2026ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
2574. ICLR 2026Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
2575. ICLR 2026Through the Lens of Contrast: Self-Improving Visual Reasoning in VLMs
2576. ICLR 2026TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment
2577. ICLR 2026TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning
2578. ICLR 2026Time Optimal Execution of Action Chunk Policies Beyond Demonstration Speed
2579. ICLR 2026TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
2580. ICLR 2026TimeSeriesExamAgent: Creating TimeSeries Reasoning Benchmarks at Scale
2581. ICLR 2026TINY BUT MIGHTY: A SOFTWARE-HARDWARE CO- DESIGN APPROACH FOR EFFICIENT MULTIMODAL IN- FERENCE ON BATTERY-POWERED SMALL DEVICES
2582. ICLR 2026TNT: Improving Chunkwise Training for Test-Time Memorization
2583. ICLR 2026To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration
2584. ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
2585. ICLR 2026Tokenisation over Bounded Alphabets is Hard
2586. ICLR 2026TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
2587. ICLR 2026ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
2588. ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
2589. ICLR 2026Towards a Foundation Model for Crowdsourced Label Aggregation
2590. ICLR 2026Towards All-Atom Foundation Models for Biomolecular Binding Affinity Prediction
2591. ICLR 2026Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models
2592. ICLR 2026Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction
2593. ICLR 2026Towards Quantization-Aware Training for Ultra-Low-Bit Reasoning LLMs
2594. ICLR 2026Towards Sampling Data Structures for Tensor Products in Turnstile Streams
2595. ICLR 2026Towards Self-Robust LLMs: Intrinsic Prompt Noise Resistance via CoIPO
2596. ICLR 2026Towards Spatial Supersensing in Video
2597. ICLR 2026Towards Text-Mask Consistency in Medical Image Segmentation
2598. ICLR 2026Towards True Speech-to-Speech Models Without Text Guidance
2599. ICLR 2026Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
2600. ICLR 2026Towards Understanding Valuable Preference Data for Large Language Model Alignment

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.