应用 · human computer interaction论文趋势 2023–2026

主要结论

• 应用 · human computer interaction论文从 2023 年的 133 篇增长到 2026 年的 369 篇，三年间扩大到约 2.8 倍。
• CVPR 是发应用 · human computer interaction论文最多的会议，2023–2026 年共 340 篇，占四个会议总量的 33%。
• 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 10 篇增至 2026 年的 117 篇。
• 在「应用领域」的 10 个主题里，它的 2026 年论文数排第 5；同组增长最快的应用 · health medicine是 61 倍，应用 · human computer interaction是 2.8 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 2026A Cross-Interaction Neural Architecture for Submodular Functions
• ICML 2026DiscoverLLM: From Executing Intents to Discovering Them
• ICLR 2026CLUTCH: Contextualized Language model for Unlocking Text-Conditioned Hand motion modelling in the wild
• CVPR 2026Bezier Degradation Modeling for LiDAR-based Human Motion Capture
• NeurIPS 20253D Human Pose Estimation with Muscles
• ICML 2025Human-Aligned Image Models Improve Visual Decoding from the Brain
• ICLR 2025CoMotion: Concurrent Multi-person 3D Motion
• CVPR 2025A Focused Human Body Model for Accurate Anthropometric Measurements Extraction
• NeurIPS 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
• ICML 2024Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function
• ICLR 2024Social-Transmotion: Promptable Human Trajectory Prediction
• CVPR 2024Disentangled Pre-training for Human-Object Interaction Detection
• NeurIPS 2023ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors
• ICML 2023Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach
• ICLR 2023A View From Somewhere: Human-Centric Face Representations
• CVPR 20233D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels
• NeurIPS 2026Ad-Hoc Teamwork from Human Demonstrations
• ICML 2026Fix the Mind, Not the Move: Interpretable AI Assistance via Knowledge-Gap Localization
• ICLR 2026Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation
• CVPR 2026BIT Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification

全部应用 · human computer interaction论文

共 66 篇，第 1 / 2 页

1. ICML 2025ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization
2. ICML 2025Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
3. ICML 2025An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
4. ICML 2025Are High-Quality AI-Generated Images More Difficult for Models to Detect?
5. ICML 2025Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds
6. ICML 2025CogReact: A Reinforced Framework to Model Human Cognitive Reaction Modulated by Dynamic Intervention
7. ICML 2025CollabLLM: From Passive Responders to Active Collaborators
8. ICML 2025Contour Integration Underlies Human-Like Vision
9. ICML 2025CUPS: Improving Human Pose-Shape Estimators with Conformalized Deep Uncertainty
10. ICML 2025DCBM: Data-Efficient Visual Concept Bottleneck Models
11. ICML 2025DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization
12. ICML 2025DVI:A Derivative-based Vision Network for INR
13. ICML 2025EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation
14. ICML 2025Efficient Quantification of Multimodal Interaction at Sample Level
15. ICML 2025EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams
16. ICML 2025Exploring Invariance in Images through One-way Wave Equations
17. ICML 2025Exploring Vision Semantic Prompt for Efficient Point Cloud Understanding
18. ICML 2025FeatSharp: Your Vision Model Features, Sharper
19. ICML 2025Flopping for FLOPs: Leveraging Equivariance for Computational Efficiency
20. ICML 2025From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
21. ICML 2025FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
22. ICML 2025GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing
23. ICML 2025How Effective Can Dropout Be in Multiple Instance Learning ?
24. ICML 2025Human Body Restoration with One-Step Diffusion Model and A New Benchmark
25. ICML 2025Human Cognition-Inspired Hierarchical Fuzzy Learning Machine
26. ICML 2025Human-Aligned Image Models Improve Visual Decoding from the Brain
27. ICML 2025Impossible Videos
28. ICML 2025Instruct2See: Learning to Remove Any Obstructions Across Distributions
29. ICML 2025Interaction-Aware Gaussian Weighting for Clustered Federated Learning
30. ICML 2025LieRE: Lie Rotational Positional Encodings
31. ICML 2025Lightweight-Mark: Rethinking Deep Learning-Based Watermarking
32. ICML 2025MindCustomer: Multi-Context Image Generation Blended with Brain Signal
33. ICML 2025MiraGe: Editable 2D Images using Gaussian Splatting
34. ICML 2025More Than Meets the Eye: Enhancing Multi-Object Tracking Even with Prolonged Occlusions
35. ICML 2025Multi-Modal Object Re-identification via Sparse Mixture-of-Experts
36. ICML 2025Mutual Learning for SAM Adaptation: A Dual Collaborative Network Framework for Source-Free Domain Transfer
37. ICML 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillation
38. ICML 2025Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models
39. ICML 2025Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting
40. ICML 2025Permutation-Free High-Order Interaction Tests
41. ICML 2025Position: Democratic AI is Possible. The Democracy Levels Framework Shows How It Might Work.
42. ICML 2025Position: When Incentives Backfire, Data Stops Being Human
43. ICML 2025Pre-training Auto-regressive Robotic Models with 4D Representations
44. ICML 2025Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves
45. ICML 2025ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering
46. ICML 2025Reinforcement Learning Control of a Physical Robot Device for Assisted Human Walking without a Simulator
47. ICML 2025Revisiting Noise Resilience Strategies in Gesture Recognition: Short-Term Enhancement in sEMG Analysis
48. ICML 2025Risk-Sensitive Theory of Mind: Coordinating with Agents of Unknown Bias using Cumulative Prospect Theory
49. ICML 2025Robust Reward Alignment via Hypothesis Space Batch Cutting
50. ICML 2025Robust Spatio-Temporal Centralized Interaction for OOD Learning

常见问题

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

共 1,027 篇，按年份分别是 2023 年 133 篇、2024 年 227 篇、2025 年 298 篇、2026 年 369 篇。

NeurIPS 2026 有多少篇应用 · human computer interaction论文？

NeurIPS 2026 有 73 篇应用 · human computer interaction论文，上一届是 86 篇。

ICLR 2026 有多少篇应用 · human computer interaction论文？

ICLR 2026 有 100 篇应用 · human computer interaction论文，上一届是 61 篇。

ICML 2026 有多少篇应用 · human computer interaction论文？

ICML 2026 有 115 篇应用 · human computer interaction论文，上一届是 66 篇。

CVPR 2026 有多少篇应用 · human computer interaction论文？

CVPR 2026 有 81 篇应用 · human computer interaction论文，上一届是 85 篇。

哪个会议的应用 · human computer interaction论文最多？

CVPR，2023–2026 年共 340 篇。