视听学习论文趋势 2023–2026

音视频联合建模

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 790 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

视听学习论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202348201278158
202433192088160
202556301094190
2026693932142282

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部视听学习论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 190 篇，第 3 / 4 页

  1. ICLR 2025Exploring the Design Space of Visual Context Representation in Video MLLMs
  2. ICLR 2025From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities
  3. ICLR 2025KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models
  4. ICLR 2025LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
  5. ICLR 2025LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
  6. ICLR 2025Learning Video-Conditioned Policy on Unlabelled Data with Joint Embedding Predictive Transformer
  7. ICLR 2025Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
  8. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
  9. ICLR 2025MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs
  10. ICLR 2025MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
  11. ICLR 2025Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
  12. ICLR 2025OMG: Opacity Matters in Material Modeling with Gaussian Splatting
  13. ICLR 2025PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training
  14. ICLR 2025Reconstructive Visual Instruction Tuning
  15. ICLR 2025Representational Similarity via Interpretable Visual Concepts
  16. ICLR 2025Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
  17. ICLR 2025Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion
  18. ICLR 2025TopoGaussian: Inferring Internal Topology Structures from Visual Clues
  19. ICLR 2025Toward Generalizing Visual Brain Decoding to Unseen Subjects
  20. ICLR 2025TRACE: Temporal Grounding Video LLM via Causal Event Modeling
  21. ICLR 2025Understanding Long Videos with Multimodal Language Models
  22. ICLR 2025Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
  23. ICLR 2025ViSAGe: Video-to-Spatial Audio Generation
  24. ICLR 2025WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
  25. ICML 2025AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment
  26. ICML 2025Efficient Motion Prompt Learning for Robust Visual Tracking
  27. ICML 2025Ex-VAD: Explainable Fine-grained Video Anomaly Detection Based on Visual-Language Models
  28. ICML 2025Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities
  29. ICML 2025MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
  30. ICML 2025SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
  31. ICML 2025Token Coordinated Prompt Attention is Needed for Visual Prompting
  32. ICML 2025Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
  33. ICML 2025video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model
  34. ICML 2025Visual Autoregressive Modeling for Image Super-Resolution
  35. NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
  36. NeurIPS 2025Anatomically inspired digital twins capture hierarchical object representations in visual cortex
  37. NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
  38. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
  39. NeurIPS 2025Counterfactual Evolution of Multimodal Datasets via Visual Programming
  40. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
  41. NeurIPS 2025Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
  42. NeurIPS 2025Differentiable Hierarchical Visual Tokenization
  43. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
  44. NeurIPS 2025EgoBlind: Towards Egocentric Visual Assistance for the Blind
  45. NeurIPS 2025Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
  46. NeurIPS 2025FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
  47. NeurIPS 2025FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
  48. NeurIPS 2025High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
  49. NeurIPS 2025INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
  50. NeurIPS 2025Learning Human-Object Interaction as Groups

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查视听学习在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "audio-visual-learning"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇视听学习论文？
共 790 篇，按年份分别是 2023 年 158 篇、2024 年 160 篇、2025 年 190 篇、2026 年 282 篇。
NeurIPS 2026 有多少篇视听学习论文？
NeurIPS 2026 有 69 篇视听学习论文，上一届是 56 篇。
ICLR 2026 有多少篇视听学习论文？
ICLR 2026 有 39 篇视听学习论文，上一届是 30 篇。
ICML 2026 有多少篇视听学习论文？
ICML 2026 有 32 篇视听学习论文，上一届是 10 篇。
CVPR 2026 有多少篇视听学习论文？
CVPR 2026 有 142 篇视听学习论文，上一届是 94 篇。
哪个会议的视听学习论文最多？
CVPR，2023–2026 年共 402 篇。

「语音与音频」下的其他主题