应用 · computer vision论文趋势 2023–2026

主要结论

• 应用 · computer vision论文从 2023 年的 106 篇增长到 2026 年的 1,326 篇，三年间扩大到约 13 倍。
• ICLR 是发应用 · computer vision论文最多的会议，2023–2026 年共 1,048 篇，占四个会议总量的 41%。
• 交叉方向里涨得最快的是应用 · speech and audio：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 292 篇。
• 在「应用领域」的 10 个主题里，它的 2026 年论文数排第 1；同组增长最快的应用 · health medicine是 61 倍，应用 · computer vision是 13 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 2026Adapting Vision Transformers to Organoid Imaging
• ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
• ICLR 2026A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features
• CVPR 2026Benchmarking PhD-Level Coding in 3D Geometric Computer Vision
• NeurIPS 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
• ICML 2025Action Dubber: Timing Audible Actions via Inflectional Flow
• ICLR 2025A Multiscale Frequency Domain Causal Framework for Enhanced Pathological Analysis
• CVPR 2025BHViT: Binarized Hybrid Vision Transformer
• NeurIPS 2024A Taxonomy of Challenges to Curating Fair Datasets
• ICML 2024Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module
• ICLR 2024Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
• CVPR 2024Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories
• NeurIPS 2023[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints
• ICML 2023Can Forward Gradient Match Backpropagation?
• ICLR 2023Fundamental limits on the robustness of image classifiers
• CVPR 2023BiFormer: Vision Transformer With Bi-Level Routing Attention
• NeurIPS 2026Computer Use at the Edge of the Statistical Precipice
• ICML 20263D Scene Assertion Verification
• ICLR 2026A Stitch in Time Saves Nine: Proactive Self-Refinement for Language Models
• CVPR 2026Describe Anything Anywhere At Any Moment

全部应用 · computer vision论文

共 168 篇，第 2 / 4 页

51. NeurIPS 2026Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following
52. NeurIPS 2026Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
53. NeurIPS 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
54. NeurIPS 2026EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
55. NeurIPS 2026Exploiting Fine-Tuning Structures to Improve Adversarial Transferability on Downstream SAM
56. NeurIPS 2026Extending 3D Reconstruction Models to Any Camera
57. NeurIPS 2026FACETS: Cross-Granularity Vision--Language Modeling for 3D Anomaly Detection
58. NeurIPS 2026FedIBS: Federated Vision-Language Adaptation via Intrinsic Bias Selection
59. NeurIPS 2026FinAl: Fine-grained Alignment for Detail-Preserving Medical Vision-Language Pretraining
60. NeurIPS 2026Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
61. NeurIPS 2026FM-ChangeNet: Learning Change through Pathwise Feature Transport
62. NeurIPS 2026Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models
63. NeurIPS 2026From Denoising to Refining: A Corrective Framework for Vision-Language Diffusion Model
64. NeurIPS 2026From Perception to Punchline: Empowering VLM with the Art of In-the-wild Memes
65. NeurIPS 2026From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
66. NeurIPS 2026GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
67. NeurIPS 2026GRASP: Guided Residual Adapters with Sample-wise Partitioning
68. NeurIPS 2026HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies
69. NeurIPS 2026HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
70. NeurIPS 2026Hierarchical Cross-Class Part Alignment for Prototypical Part Networks via Hyperbolic Entailment
71. NeurIPS 2026In-Context Learning Can Help Vision Language Models Overcome Training Prior
72. NeurIPS 2026Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
73. NeurIPS 2026Language Models Demand New Computer Science
74. NeurIPS 2026Learning Better Certified Models from Empirically-Robust Teachers
75. NeurIPS 2026Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions
76. NeurIPS 2026Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
77. NeurIPS 2026LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift
78. NeurIPS 2026Leveraging unlabelled data for generalizable neural population decoding
79. NeurIPS 2026LifeStream: Token Life-Cycle Modeling for Training-Free Online Video Understanding
80. NeurIPS 2026Local Intrinsic Dimension Unveils Hallucinations in Diffusion Models
81. NeurIPS 2026LoMo: Local Modality Substitution for Deeper Vision-Language Fusion
82. NeurIPS 2026Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models
83. NeurIPS 2026Lookalike3D: Seeing Double in 3D
84. NeurIPS 2026LookThere! Sparse Vision by Reinforced Selection
85. NeurIPS 2026LR-V2X: Loss Resilient Collaborative Perception under Low-Bandwidth Communication
86. NeurIPS 2026LSVD: Loss-Aware Low-Rank Approximation for Efficient Low-Precision Vision-Language Models
87. NeurIPS 2026M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
88. NeurIPS 2026Masked Diffusion Vision-Language Models for Temporal Action Localization
89. NeurIPS 2026MEME: Lightweight Hierarchical Mixture-of-Experts for Unified Affective Computing
90. NeurIPS 2026Mind the Heads: Topological Representation Alignment for Multimodal LLMs
91. NeurIPS 2026Mixture of Probes: Learning with Privileged Modalities in Multimodal LLMs Through Probing
92. NeurIPS 2026Mixture-of-Hierarchical Experts: Optimized Mamba Architecture for Vision Diffusion
93. NeurIPS 2026MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models
94. NeurIPS 2026MonoChunk3D: Monocular Online 3D Instance Segmentation with Persistent Instance States
95. NeurIPS 2026MorphoHELM: A Comprehensive Benchmark for Evaluating Representations for Microscopy-Based Morphology Assays
96. NeurIPS 2026MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening
97. NeurIPS 2026Neural Expansion: A Unified Mechanism for How Deep Neural Network Generalize
98. NeurIPS 2026Not All Tokens Should Be Treated Equally: Context Credits Reassignment
99. NeurIPS 2026OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
100. NeurIPS 2026On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs

常见问题

2023–2026 年四大会议一共有多少篇应用 · computer vision论文？

共 2,538 篇，按年份分别是 2023 年 106 篇、2024 年 334 篇、2025 年 772 篇、2026 年 1,326 篇。

NeurIPS 2026 有多少篇应用 · computer vision论文？

NeurIPS 2026 有 168 篇应用 · computer vision论文，上一届是 165 篇。

ICLR 2026 有多少篇应用 · computer vision论文？

ICLR 2026 有 538 篇应用 · computer vision论文，上一届是 338 篇。

ICML 2026 有多少篇应用 · computer vision论文？

ICML 2026 有 554 篇应用 · computer vision论文，上一届是 201 篇。

CVPR 2026 有多少篇应用 · computer vision论文？

CVPR 2026 有 66 篇应用 · computer vision论文，上一届是 68 篇。

哪个会议的应用 · computer vision论文最多？

ICLR，2023–2026 年共 1,048 篇。