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 48 of 104

2351. ICLR 2026Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
2352. ICLR 2026Rethinking Causal Mask Attention for Vision-Language Inference
2353. ICLR 2026Rethinking Code Similarity for Automated Algorithm Design with LLMs
2354. ICLR 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
2355. ICLR 2026Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration
2356. ICLR 2026Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
2357. ICLR 2026Rethinking LLM Evaluation: Can We Evaluate LLMs with 200× Less Data?
2358. ICLR 2026Rethinking LLM Reasoning: From Explicit Trajectories to Latent Representations
2359. ICLR 2026Rethinking Radiology Report Generation: From Narrative Flow to Topic-Guided Findings
2360. ICLR 2026Rethinking Residual Errors in Compensation-based LLM Quantization
2361. ICLR 2026Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
2362. ICLR 2026Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
2363. ICLR 2026Reverse-Engineered Reasoning for Open-Ended Generation
2364. ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
2365. ICLR 2026Revisiting Confidence Calibration for Misclassification Detection in VLMs
2366. ICLR 2026Revisiting Multimodal Positional Encoding in Vision–Language Models
2367. ICLR 2026Revisiting the Past: Data Unlearning with Model State History
2368. ICLR 2026Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
2369. ICLR 2026ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
2370. ICLR 2026RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
2371. ICLR 2026Riemannian High-Order Pooling for Brain Foundation Models
2372. ICLR 2026RIVER: Real-time Video Interaction Benchmark
2373. ICLR 2026RL for Reasoning by Adaptively Revealing Rationales
2374. ICLR 2026RL makes MLLMs see better than SFT
2375. ICLR 2026RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
2376. ICLR 2026RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
2377. ICLR 2026RLAP-CLIP: Continual Multimodal Learning with Prototype Adaptation and Difficulty-Aware Routing
2378. ICLR 2026RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
2379. ICLR 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
2380. ICLR 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
2381. ICLR 2026RobotArena $\infty$: Unlimited Robot Benchmarking via Real-to-Sim Translation
2382. ICLR 2026Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
2383. ICLR 2026Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging
2384. ICLR 2026Robust Reward Modeling via Causal Rubrics
2385. ICLR 2026Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts
2386. ICLR 2026RobustSpring: Benchmarking Robustness to Image Corruptions for Optical Flow, Scene Flow and Stereo
2387. ICLR 2026RoRE: Rotary Ray Embedding for Generalised Multi-Modal Scene Understanding
2388. ICLR 2026Rote Learning Considered Useful: Generalizing over Memorized Data in LLMs
2389. ICLR 2026Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs
2390. ICLR 2026Routing, Cascades, and User Choice for LLMs
2391. ICLR 2026ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
2392. ICLR 2026RPM: Reasoning-Level Personalization for Black-Box Large Language Models
2393. ICLR 2026SABRE-FL: Selective and Accurate Backdoor Rejection for Federated Prompt Learning
2394. ICLR 2026SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression
2395. ICLR 2026Safeguarding Multimodal Knowledge Copyright in the RAG-as-a-Service Environment
2396. ICLR 2026SafeMoE: Safe Fine-Tuning for MoE LLMs by Aligning Harmful Input Routing
2397. ICLR 2026Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
2398. ICLR 2026SAGE: Spatial-visual Adaptive Graph Exploration for Efficient Visual Place Recognition
2399. ICLR 2026SAM 3: Segment Anything with Concepts
2400. ICLR 2026Same Content, Different Representations: A Controlled Study for Table QA

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.