Applications · computer vision papers, 2023–2026

Key findings

• Applications · computer vision went from 106 papers in 2023 to 1,326 in 2026, roughly 13x in three years.
• ICLR publishes the most Applications · computer vision work: 1,048 papers from 2023 to 2026, 41% of the four-venue total.
• The fastest-growing overlap is with Applications · speech and audio: papers tagged with both rose from 0 in 2023 to 292 in 2026.
• Among the 10 topics under Application Domains, it ranks #1 by 2026 paper count; the fastest grower in the group, Applications · health medicine, is up 61x versus 13x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Applications · computer vision papers

165 papers, page 2 of 4

51. NeurIPS 2025FACE: Faithful Automatic Concept Extraction
52. NeurIPS 2025Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
53. NeurIPS 2025FastJAM: a Fast Joint Alignment Model for Images
54. NeurIPS 2025Fix False Transparency by Noise Guided Splatting
55. NeurIPS 2025FLAME: Fast Long-context Adaptive Memory for Event-based Vision
56. NeurIPS 2025FlowFeat: Pixel-Dense Embedding of Motion Profiles
57. NeurIPS 2025FLOWING: Implicit Neural Flows for Structure-Preserving Morphing
58. NeurIPS 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
59. NeurIPS 2025Frequency-Aware Token Reduction for Efficient Vision Transformer
60. NeurIPS 2025From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging
61. NeurIPS 2025From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit
62. NeurIPS 2025Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span
63. NeurIPS 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
64. NeurIPS 2025GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity
65. NeurIPS 2025GLVD: Guided Learned Vertex Descent
66. NeurIPS 2025GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers
67. NeurIPS 2025Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges
68. NeurIPS 2025GSPN-2: Efficient Parallel Sequence Modeling
69. NeurIPS 2025HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene
70. NeurIPS 2025Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
71. NeurIPS 2025HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
72. NeurIPS 2025Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models
73. NeurIPS 2025High Dynamic Range Imaging with Time-Encoding Spike Camera
74. NeurIPS 2025HMVLM:Human Motion-Vision-Language Model via MoE LoRA
75. NeurIPS 2025HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
76. NeurIPS 2025IBGS: Image-Based Gaussian Splatting
77. NeurIPS 2025InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras
78. NeurIPS 2025Instance-Level Composed Image Retrieval
79. NeurIPS 2025Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks
80. NeurIPS 2025InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition
81. NeurIPS 2025Interactive Anomaly Detection for Articulated Objects via Motion Anticipation
82. NeurIPS 2025InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts
83. NeurIPS 2025Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats
84. NeurIPS 2025IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals
85. NeurIPS 2025IRRISIGHT: A Large-Scale Multimodal Dataset and Scalable Pipeline to Address Irrigation and Water Management in Agriculture
86. NeurIPS 2025JAFAR: Jack up Any Feature at Any Resolution
87. NeurIPS 2025Leaving No OOD Instance Behind: Instance-Level OOD Fine-Tuning for Anomaly Segmentation
88. NeurIPS 2025LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision
89. NeurIPS 2025LuxDiT: Lighting Estimation with Video Diffusion Transformer
90. NeurIPS 2025LVLM-Driven Attribute-Aware Modeling for Visible-Infrared Person Re-Identification
91. NeurIPS 2025Manipulating Feature Visualizations with Gradient Slingshots
92. NeurIPS 2025Merlin L48 Spectrogram Dataset
93. NeurIPS 2025MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans
94. NeurIPS 2025Miss-ReID: Delivering Robust Multi-Modality Object Re-Identification Despite Missing Modalities
95. NeurIPS 2025MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
96. NeurIPS 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
97. NeurIPS 2025MolVision: Molecular Property Prediction with Vision Language Models
98. NeurIPS 2025More effort is needed to protect pedestrian privacy in the era of AI
99. NeurIPS 2025Native Segmentation Vision Transformers
100. NeurIPS 2025NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

FAQ

How many Applications · computer vision papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,538 in total: 106 in 2023, 334 in 2024, 772 in 2025, 1,326 in 2026.

How many Applications · computer vision papers are at NeurIPS 2026?

NeurIPS 2026 has 168 Applications · computer vision papers, versus 165 the year before.

How many Applications · computer vision papers are at ICLR 2026?

ICLR 2026 has 538 Applications · computer vision papers, versus 338 the year before.

How many Applications · computer vision papers are at ICML 2026?

ICML 2026 has 554 Applications · computer vision papers, versus 201 the year before.

How many Applications · computer vision papers are at CVPR 2026?

CVPR 2026 has 66 Applications · computer vision papers, versus 68 the year before.

Which conference publishes the most Applications · computer vision papers?

ICLR, with 1,048 papers from 2023 to 2026.