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 206 篇，第 2 / 5 页

  1. NeurIPS 2026The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks
  2. NeurIPS 2026Thinking with Visual Primitives
  3. NeurIPS 2026To Think or Not to Think: Pre-Decisional Reasoning Budgets for Referring Audio-Visual Segmentation
  4. NeurIPS 2026Towards Visual Query Segmentation in the Wild
  5. NeurIPS 2026Trimming the Long-Tail of Visual World Modeling Evaluation
  6. NeurIPS 2026VESTA: Visual Exploration with Statistical Tool Agents
  7. NeurIPS 2026VideoSleuth: A Narrative-Centric Agentic System with Video-Audio Native MLLM for Long-Form Video Understanding
  8. NeurIPS 2026VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling
  9. NeurIPS 2026VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual Instructions
  10. NeurIPS 2026VistaQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence
  11. NeurIPS 2026Visual Grounding First, Multimodal In-context Learning Follows
  12. NeurIPS 2026Visual-ERM: Reward Modeling for Visual Equivalence
  13. NeurIPS 2026Visual-to-Executable Procedural Reconstruction of Buildings.
  14. NeurIPS 2026VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
  15. NeurIPS 2026VocalCoachBench: Benchmarking Audio-Language Models on Expert Feedback for Singing
  16. NeurIPS 2026Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning
  17. NeurIPS 2026What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment
  18. NeurIPS 2026Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering
  19. NeurIPS 2026Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs
  20. NeurIPS 2025$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
  21. NeurIPS 2025Anatomically inspired digital twins capture hierarchical object representations in visual cortex
  22. NeurIPS 2025Automatic Visual Instrumental Variable Learning for Confounding-Resistant Domain Generalization
  23. NeurIPS 2025AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding
  24. NeurIPS 2025Counterfactual Evolution of Multimodal Datasets via Visual Programming
  25. NeurIPS 2025DAVE: Diagnostic benchmark for Audio Visual Evaluation
  26. NeurIPS 2025Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
  27. NeurIPS 2025Differentiable Hierarchical Visual Tokenization
  28. NeurIPS 2025Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention
  29. NeurIPS 2025EgoBlind: Towards Egocentric Visual Assistance for the Blind
  30. NeurIPS 2025Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation
  31. NeurIPS 2025FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering
  32. NeurIPS 2025FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
  33. NeurIPS 2025High-dimensional neuronal activity from low-dimensional latent dynamics: a solvable model
  34. NeurIPS 2025INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
  35. NeurIPS 2025Learning Human-Object Interaction as Groups
  36. NeurIPS 2025Learning to cluster neuronal function
  37. NeurIPS 2025Learning to Instruct for Visual Instruction Tuning
  38. NeurIPS 2025Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
  39. NeurIPS 2025LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers
  40. NeurIPS 2025LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders
  41. NeurIPS 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
  42. NeurIPS 2025MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs
  43. NeurIPS 2025Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors
  44. NeurIPS 2025MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
  45. NeurIPS 2025On the rankability of visual embeddings
  46. NeurIPS 2025Perception Encoder: The best visual embeddings are not at the output of the network
  47. NeurIPS 2025Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection
  48. NeurIPS 2025PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
  49. NeurIPS 2025Quantum Visual Fields with Neural Amplitude Encoding
  50. NeurIPS 2025Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation

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