Audio-Visual Learning papers, 2023–2026

Key findings

• Audio-Visual Learning went from 158 papers in 2023 to 282 in 2026, roughly 1.8x in three years.
• CVPR publishes the most Audio-Visual Learning work: 402 papers from 2023 to 2026, 51% of the four-venue total.
• The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 2 in 2023 to 19 in 2026.
• Among the 5 topics under Audio and Speech, it ranks #1 by 2026 paper count; the fastest grower in the group, Audio Generation, is up 4.3x versus 1.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Training-Free Video Moment Retrieval Framework via Selection from Multiple Visual Prompts
• ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
• ICLR 2026AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration
• CVPR 2026AVFakeBench A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs
• NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
• ICML 2025Token Coordinated Prompt Attention is Needed for Visual Prompting
• ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
• CVPR 2025A Distractor-Aware Memory for Visual Object Tracking with SAM2
• NeurIPS 2024Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
• ICML 2024EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
• ICLR 2024Can Transformers Capture Spatial Relations between Objects?
• CVPR 2024DiVa-360: The Dynamic Visual Dataset for Immersive Neural Fields
• NeurIPS 2023Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
• ICML 2023A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
• ICLR 2023A Control-Centric Benchmark for Video Prediction
• CVPR 2023An Empirical Study of End-to-End Video-Language Transformers With Masked Visual Modeling
• NeurIPS 2026AdaCodec: A Predictive Visual Code for Video MLLMs
• ICML 2026EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs
• ICLR 2026Depth Anything 3: Recovering the Visual Space from Any Views
• CVPR 2026Co-Me Confidence Guided Token Merging for Visual Geometric Transformers

All Audio-Visual Learning papers

190 papers, page 3 of 4

101. ICLR 2025Exploring the Design Space of Visual Context Representation in Video MLLMs
102. ICLR 2025From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
103. ICLR 2025KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models
104. ICLR 2025LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
105. ICLR 2025LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
106. ICLR 2025Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
107. ICLR 2025Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
108. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
109. ICLR 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
110. ICLR 2025MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
111. ICLR 2025Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
112. ICLR 2025OMG: Opacity Matters in Material Modeling with Gaussian Splatting
113. ICLR 2025PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
114. ICLR 2025Reconstructive Visual Instruction Tuning
115. ICLR 2025Representational Similarity via Interpretable Visual Concepts
116. ICLR 2025Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
117. ICLR 2025Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
118. ICLR 2025TopoGaussian: Inferring Internal Topology Structures from Visual Clues
119. ICLR 2025Toward Generalizing Visual Brain Decoding to Unseen Subjects
120. ICLR 2025TRACE: Temporal Grounding Video LLM via Causal Event Modeling
121. ICLR 2025Understanding Long Videos with Multimodal Language Models
122. ICLR 2025Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
123. ICLR 2025ViSAGe: Video-to-Spatial Audio Generation
124. ICLR 2025WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
125. ICML 2025AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment
126. ICML 2025Efficient Motion Prompt Learning for Robust Visual Tracking
127. ICML 2025Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
128. ICML 2025Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
129. ICML 2025MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
130. ICML 2025SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
131. ICML 2025Token Coordinated Prompt Attention is Needed for Visual Prompting
132. ICML 2025Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
133. ICML 2025video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
134. ICML 2025Visual Autoregressive Modeling for Image Super-Resolution
135. NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
136. NeurIPS 2025Anatomically inspired digital twins capture hierarchical object representations in visual cortex
137. NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
138. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
139. NeurIPS 2025Counterfactual Evolution of Multimodal Datasets via Visual Programming
140. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
141. NeurIPS 2025Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
142. NeurIPS 2025Differentiable Hierarchical Visual Tokenization
143. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
144. NeurIPS 2025EgoBlind: Towards Egocentric Visual Assistance for the Blind
145. NeurIPS 2025Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
146. NeurIPS 2025FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
147. NeurIPS 2025FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
148. NeurIPS 2025High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
149. NeurIPS 2025INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
150. NeurIPS 2025Learning Human-Object Interaction as Groups

FAQ

How many Audio-Visual Learning papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

790 in total: 158 in 2023, 160 in 2024, 190 in 2025, 282 in 2026.

How many Audio-Visual Learning papers are at NeurIPS 2026?

NeurIPS 2026 has 69 Audio-Visual Learning papers, versus 56 the year before.

How many Audio-Visual Learning papers are at ICLR 2026?

ICLR 2026 has 39 Audio-Visual Learning papers, versus 30 the year before.

How many Audio-Visual Learning papers are at ICML 2026?

ICML 2026 has 32 Audio-Visual Learning papers, versus 10 the year before.

How many Audio-Visual Learning papers are at CVPR 2026?

CVPR 2026 has 142 Audio-Visual Learning papers, versus 94 the year before.

Which conference publishes the most Audio-Visual Learning papers?

CVPR, with 402 papers from 2023 to 2026.