口语理解论文趋势 2023–2026

主要结论

• 口语理解论文从 2023 年的 40 篇增长到 2026 年的 61 篇，三年间扩大到约 1.5 倍。
• CVPR 是发口语理解论文最多的会议，2023–2026 年共 62 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 14 篇。
• 在「语音与音频」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的音频生成是 4.3 倍，口语理解是 1.5 倍。

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

• NeurIPS 2026Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
• ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
• ICLR 2026Neuron-Level Analysis of Cultural Understanding in Large Language Models
• CVPR 2026Consistent Instance Field for Dynamic Scene Understanding
• NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
• ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
• ICLR 2025Toward Understanding In-context vs. In-weight Learning
• CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
• NeurIPS 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
• ICML 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
• ICLR 2024Understanding Addition in Transformers
• CVPR 2024SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
• NeurIPS 2023ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation
• ICML 2023How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding
• ICLR 2023Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks
• CVPR 2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
• NeurIPS 2026EmbodiedObject: All-in-One Object Understanding with SLAT
• ICML 2026Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions
• ICLR 2026Towards Understanding the Shape of Representations in Protein Language Models
• CVPR 2026Lifting Unlabeled Internet-level Data for 3D Scene Understanding

全部口语理解论文

共 50 篇，第 1 / 1 页

1. CVPR 2025Apollo: An Exploration of Video Understanding in Large Multimodal Models
2. CVPR 2025ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding
3. CVPR 2025DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding
4. CVPR 2025EventGPT: Event Stream Understanding with Multimodal Large Language Models
5. CVPR 2025FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding
6. CVPR 2025Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding
7. CVPR 2025GroundingFace: Fine-grained Face Understanding via Pixel Grounding Multimodal Large Language Model
8. CVPR 2025HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
9. CVPR 2025LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
10. CVPR 2025Mamba4D: Efficient 4D Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
11. CVPR 2025MP-GUI: Modality Perception with MLLMs for GUI Understanding
12. CVPR 2025MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving
13. CVPR 2025PEACE: Empowering Geologic Map Holistic Understanding with MLLMs
14. CVPR 2025Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs
15. CVPR 2025Towards Universal Soccer Video Understanding
16. CVPR 2025Understanding Multi-layered Transmission Matrices
17. CVPR 2025VEU-Bench: Towards Comprehensive Understanding of Video Editing
18. CVPR 2025VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
19. CVPR 2025VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
20. ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
21. ICLR 2025Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
22. ICLR 2025Toward Understanding In-context vs. In-weight Learning
23. ICLR 2025Understanding Factual Recall in Transformers via Associative Memories
24. ICLR 2025Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry
25. ICLR 2025Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape View
26. ICLR 2025Uni-Sign: Toward Unified Sign Language Understanding at Scale
27. ICML 2025On Understanding Attention-Based In-Context Learning for Categorical Data
28. ICML 2025Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
29. ICML 2025Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis
30. ICML 2025Understanding Mode Connectivity via Parameter Space Symmetry
31. ICML 2025Understanding Nonlinear Implicit Bias via Region Counts in Input Space
32. ICML 2025Understanding the difficulties of posterior predictive estimation
33. ICML 2025Understanding the Kronecker Matrix-Vector Complexity of Linear Algebra
34. ICML 2025Understanding the Limits of Deep Tabular Methods with Temporal Shift
35. ICML 2025Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees
36. ICML 2025Understanding the Unfairness in Network Quantization
37. NeurIPS 2025FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing
38. NeurIPS 2025Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks
39. NeurIPS 2025The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
40. NeurIPS 2025Through the River: Understanding the Benefit of Schedule-Free Methods for Language Model Training
41. NeurIPS 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
42. NeurIPS 2025Towards a Geometric Understanding of Tensor Learning via the t-Product
43. NeurIPS 2025Towards Understanding Transformers in Learning Random Walks
44. NeurIPS 2025Understanding Adam Requires Better Rotation Dependent Assumptions
45. NeurIPS 2025Understanding Bias Terms in Neural Representations
46. NeurIPS 2025Understanding Differential Transformer Unchains Pretrained Self-Attentions
47. NeurIPS 2025Understanding the Evolution of the Neural Tangent Kernel at the Edge of Stability
48. NeurIPS 2025Understanding the Gain from Data Filtering in Multimodal Contrastive Learning
49. NeurIPS 2025Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
50. NeurIPS 2025Understanding while Exploring: Semantics-driven Active Mapping

常见问题

2023–2026 年四大会议一共有多少篇口语理解论文？

共 189 篇，按年份分别是 2023 年 40 篇、2024 年 38 篇、2025 年 50 篇、2026 年 61 篇。

NeurIPS 2026 有多少篇口语理解论文？

NeurIPS 2026 有 25 篇口语理解论文，上一届是 14 篇。

ICLR 2026 有多少篇口语理解论文？

ICLR 2026 有 6 篇口语理解论文，上一届是 7 篇。

ICML 2026 有多少篇口语理解论文？

ICML 2026 有 12 篇口语理解论文，上一届是 10 篇。

CVPR 2026 有多少篇口语理解论文？

CVPR 2026 有 18 篇口语理解论文，上一届是 19 篇。

哪个会议的口语理解论文最多？

CVPR，2023–2026 年共 62 篇。