视觉-语言-动作论文趋势 2023–2026

主要结论

• 视觉-语言-动作论文从 2023 年的 257 篇增长到 2026 年的 708 篇，三年间扩大到约 2.8 倍。
• CVPR 是发视觉-语言-动作论文最多的会议，2023–2026 年共 640 篇，占四个会议总量的 39%。
• 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 21 篇增至 2026 年的 135 篇。
• 在「机器人与具身」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的人形控制是 3.8 倍，视觉-语言-动作是 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 Dual-Domain Vision Transformer with Spectral Positional Bias
• ICML 2026FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
• ICLR 2026Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation
• CVPR 2026ActAvatar Temporally-Aware Precise Action Control for Talking Avatars
• NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
• ICML 2025Feasible Action Search for Bandit Linear Programs via Thompson Sampling
• ICLR 2025Action Sequence Augmentation for Action Anticipation
• CVPR 2025Active Event-based Stereo Vision
• NeurIPS 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
• ICML 2024Causal Action Influence Aware Counterfactual Data Augmentation
• ICLR 2024Matrix Manifold Neural Networks++
• CVPR 2024End-to-End Spatio-Temporal Action Localisation with Video Transformers
• NeurIPS 2023Activity Grammars for Temporal Action Segmentation
• ICML 2023Algorithmic Collective Action in Machine Learning
• ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
• CVPR 20233Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
• NeurIPS 2026A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
• ICML 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
• ICLR 2026EAST: Early Action Prediction Sampling Strategy with Token Masking
• CVPR 2026DarkShake-DVS Event-based Human Action Recognition under Low-light and Shaking Camera

全部视觉-语言-动作论文

共 255 篇，第 1 / 6 页

1. ICML 2026A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
2. ICML 2026Action Manifold Smoothing: A Lipschitz Pathway Perspective on High-Dimensional Reinforcement Learning
3. ICML 2026Action-Sufficient Goal Representations
4. ICML 2026Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision-Language Models
5. ICML 2026Adaptive Token Refinement in Long-Tailed Large Vision-Language Models Fine-Tuning
6. ICML 2026AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation
7. ICML 2026AlignedNorm: Prompting Vision–Language Models via Coupled Prompt Field
8. ICML 2026Attacking Gray-Box Large Vision-Language Models with Adaptive SVD-Structured Adversarial Alignment
9. ICML 2026AURA: Visually Interpretable Affective Understanding via Robust Archetypes
10. ICML 2026AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving
11. ICML 2026Benign Overfitting in Adversarial Training for Vision Transformers
12. ICML 2026Beyond Attention Imbalance: Mitigating Hallucinations via Spectral Surgery
13. ICML 2026Bring Future Vision: Dynamic Computation Allocation Guided by Lightweight Feature Forecaster
14. ICML 2026Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting
15. ICML 2026BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks
16. ICML 2026CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
17. ICML 2026Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
18. ICML 2026Chunk-Guided Q-Learning
19. ICML 2026Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Vision-Language Models
20. ICML 2026Co-Evolving Latent Action World Models
21. ICML 2026Compass-RoPE: Isotropic Rotary Position Embeddings for Vision Transformers
22. ICML 2026Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
23. ICML 2026Conformal Risk-Averse Decision Making with Action Conditional Guarantee
24. ICML 2026Contrastive Representation Regularization for Vision-Language-Action Models
25. ICML 2026D$^2$O: A Dual Debiasing Operator for Training-Free Test-Time Adaptation of Vision–Language Models
26. ICML 2026DDGA: Dirichlet Distributional Gradient Aggregation for Transferable Vision-Language Adversarial Attacks
27. ICML 2026Deformba: Vision State Space Model with Adaptive State Fusion
28. ICML 2026DEGAP: Dynamic Entropy-Guided Attention Perturbation for Contrastive Decoding in Large Vision-Language Models
29. ICML 2026Designing Observation and Action Models for Efficient Reinforcement Learning with LLMs
30. ICML 2026DiLA: Disentangled Latent Action World Models
31. ICML 2026Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies
32. ICML 2026Dismantling the Illusion of Vision-Language-Action Models Competence via Explicit Distributional Shifts
33. ICML 2026Dive into the Scene: Breaking the Perceptual Bottleneck in Vision-Language Decision Making via Focus Plan Generation
34. ICML 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
35. ICML 2026Dyn-VPP: Video Prediction Policy Optimization for Improved Visual Dynamics
36. ICML 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
37. ICML 2026EcoVLA: Environment-Aware Adaptive Pruning with Interleaved Inference Orchestration for Vision-Language-Action Models
38. ICML 2026Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
39. ICML 2026EnsembleVLA: Ensemble Learning for Vision-Language Action Models
40. ICML 2026Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
41. ICML 2026Factored Latent Action World Models
42. ICML 2026FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
43. ICML 2026Forensic Prompting with Dual-Action Policy Optimization for Vision-Language Forgery Detection and Localization
44. ICML 2026FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision–Language Models
45. ICML 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
46. ICML 2026From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges
47. ICML 2026From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
48. ICML 2026General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
49. ICML 2026Geometric Collapse: When Vision Models Fail to Verify Physical Causality
50. ICML 2026HieRD: Hierarchical Relational Distillation for Vision-Language Embedding Models

常见问题

2023–2026 年四大会议一共有多少篇视觉-语言-动作论文？

共 1,639 篇，按年份分别是 2023 年 257 篇、2024 年 329 篇、2025 年 345 篇、2026 年 708 篇。

NeurIPS 2026 有多少篇视觉-语言-动作论文？

NeurIPS 2026 有 204 篇视觉-语言-动作论文，上一届是 108 篇。

ICLR 2026 有多少篇视觉-语言-动作论文？

ICLR 2026 有 113 篇视觉-语言-动作论文，上一届是 64 篇。

ICML 2026 有多少篇视觉-语言-动作论文？

ICML 2026 有 126 篇视觉-语言-动作论文，上一届是 33 篇。

CVPR 2026 有多少篇视觉-语言-动作论文？

CVPR 2026 有 265 篇视觉-语言-动作论文，上一届是 140 篇。

哪个会议的视觉-语言-动作论文最多？

CVPR，2023–2026 年共 640 篇。