Audio-Visual Generation papers, 2023–2026

Key findings

• Audio-Visual Generation went from 92 papers in 2023 to 336 in 2026, roughly 3.7x in three years.
• CVPR publishes the most Audio-Visual Generation work: 383 papers from 2023 to 2026, 49% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 6 in 2023 to 79 in 2026.
• Among the 5 topics under Multimodal Generation, it ranks #2 by 2026 paper count; the fastest grower in the group, Storytelling Generation, is up 15x versus 3.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Binding Visual Features Point by Point
• ICML 2026AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs
• ICLR 2026AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
• CVPR 2026Benchmarking Single-Factor Physical Video-to-Audio Generation
• NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
• ICML 2025Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
• ICLR 2025AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models
• CVPR 2025Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding
• NeurIPS 2024Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
• ICML 2024CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
• ICLR 2024Can Transformers Capture Spatial Relations between Objects?
• CVPR 2024EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition
• ICLR 2023Learning to reason over visual objects
• CVPR 2023Autoregressive Visual Tracking
• NeurIPS 2026From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation
• ICML 2026Deep Ensemble Clustering for Visual Representation Learning
• ICLR 2026AQuA: Toward Strategic Response Generation for Ambiguous Visual Questions
• CVPR 2026Co-Me Confidence Guided Token Merging for Visual Geometric Transformers

All Audio-Visual Generation papers

183 papers, page 2 of 4

51. NeurIPS 2026RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation
52. NeurIPS 2026RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
53. NeurIPS 2026Referring and Reasoning Camouflaged Object Segmentation in Audio-Visual Scenes
54. NeurIPS 2026RefineTok: Scale-Wise Tokenization for Progressive Visual Refinement
55. NeurIPS 2026RegimeVGGT: Layer-Wise Spatially Preserving Redundancy Removal for Visual Geometry Grounded Transformer
56. NeurIPS 2026RelationVGGT : Visual Geometry Transformers for 3D Spatial Relation Segmentation
57. NeurIPS 2026Render Structure Uncertainty for HTML Repair in MLLM-based UI-to-Code Generation
58. NeurIPS 2026Representation Fréchet Loss for Visual Generation
59. NeurIPS 2026RVCBench: Benchmarking Robustness of Voice Cloning Across Modern Audio Generation Models
60. NeurIPS 2026SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation
61. NeurIPS 2026Shaping Useful Noise: Energy Distributions Predict Visual Pretraining Quality
62. NeurIPS 2026Shift-Aware Identity-Guided Latent Refinement for Referring Audio–Visual Segmentation
63. NeurIPS 2026Simple Test-Time Refinement for Plot-to-Code Generation via Visual-Code Diagnostics
64. NeurIPS 2026SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows
65. NeurIPS 2026ST-DiffEye: Diffusion-based Continuous Gaze Generation via Joint Scanpath-Trajectory Modeling
66. NeurIPS 2026StableAvatar: Ultra-Long Audio-Driven Avatar Video Generation
67. NeurIPS 2026TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM Workflows
68. NeurIPS 2026Test-Time Conditioning with Representation-Aligned Visual Features
69. NeurIPS 2026To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation
70. NeurIPS 2026Towards Visual Query Segmentation in the Wild
71. NeurIPS 2026V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation
72. NeurIPS 2026VAR-Q: Tuning-free KV Cache Quantization for Visual Autoregressive Image and Video Generation
73. NeurIPS 2026VeriWorld: A Verifiable Visual SWE-Bench for Spatial Reasoning in 3D Environments
74. NeurIPS 2026VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
75. NeurIPS 2026Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs
76. NeurIPS 2026VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model
77. NeurIPS 2026VisionCreator-S1: Evolving Visual-Generation Agents via Skill-GRPO Optimization
78. NeurIPS 2026VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
79. NeurIPS 2026Visual-to-Executable Procedural Reconstruction of Buildings.
80. NeurIPS 2026VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
81. NeurIPS 2026VUM: Visual Unified Models for Image Generation and Perception
82. NeurIPS 2026WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning
83. NeurIPS 2026What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
84. NeurIPS 2026Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs
85. NeurIPS 2025🎧MOSPA: Human Motion Generation Driven by Spatial Audio
86. NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
87. NeurIPS 2025Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
88. NeurIPS 2025ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
89. NeurIPS 2025Audio Super-Resolution with Latent Bridge Models
90. NeurIPS 2025Audio-Sync Video Generation with Multi-Stream Temporal Control
91. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
92. NeurIPS 2025BNMusic: Blending Environmental Noises into Personalized Music
93. NeurIPS 2025Bridging the gap to real-world language-grounded visual concept learning
94. NeurIPS 2025CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
95. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
96. NeurIPS 2025Differentiable Hierarchical Visual Tokenization
97. NeurIPS 2025DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images
98. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
99. NeurIPS 2025FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction
100. NeurIPS 2025FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance

FAQ

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

780 in total: 92 in 2023, 131 in 2024, 221 in 2025, 336 in 2026.

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

NeurIPS 2026 has 84 Audio-Visual Generation papers, versus 57 the year before.

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

ICLR 2026 has 64 Audio-Visual Generation papers, versus 32 the year before.

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

ICML 2026 has 39 Audio-Visual Generation papers, versus 19 the year before.

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

CVPR 2026 has 149 Audio-Visual Generation papers, versus 113 the year before.

Which conference publishes the most Audio-Visual Generation papers?

CVPR, with 383 papers from 2023 to 2026.