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 113 篇，第 2 / 3 页

51. ICLR 2026Language-Instructed Vision Embeddings for Controllable and Generalizable Perception
52. ICLR 2026Learning Robust Intervention Representations with Delta Embeddings
53. ICLR 2026Learning to Reason as Action Abstractions with Scalable Mid-Training RL
54. ICLR 2026Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions
55. ICLR 2026Long-tailed Test-Time Adaptation for Vision-Language Models
56. ICLR 2026M$^3$E: Continual Vision-and-Language Navigation via Mixture of Macro and Micro Experts
57. ICLR 2026MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation
58. ICLR 2026Naming to Learn: Class Incremental Learning for Vision-Language Model with Unlabeled Data
59. ICLR 2026On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding
60. ICLR 2026On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
61. ICLR 2026OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
62. ICLR 2026Online Decision Making with Generative Action Sets
63. ICLR 2026Pay Less Attention to Function Words for Free Robustness of Vision-Language Models
64. ICLR 2026PHyCLIP: $\ell_1$-Product of Hyperbolic Factors Unifies Hierarchy and Compositionality in Vision-Language Representation Learning
65. ICLR 2026PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
66. ICLR 2026Pose-RFT: Aligning MLLMs for 3D Pose Generation via Hybrid Action Reinforcement Fine-Tuning
67. ICLR 2026Post-hoc Probabilistic Vision-Language Models
68. ICLR 2026Primary-Fine Decoupling for Action Generation in Robotic Imitation
69. ICLR 2026Procedural Mistake Detection via Action Effect Modeling
70. ICLR 2026Real-Time Robot Execution with Masked Action Chunking
71. ICLR 2026ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures
72. ICLR 2026ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
73. ICLR 2026Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
74. ICLR 2026Revisiting Multimodal Positional Encoding in Vision–Language Models
75. ICLR 2026RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots
76. ICLR 2026Robust Fine-tuning of Vision-Language-Action Robot Policies via Parameter Merging
77. ICLR 2026Rodrigues Network for Learning Robot Actions
78. ICLR 2026Scaling up Memory for Robotic Control via Experience Retrieval
79. ICLR 2026Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
80. ICLR 2026Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
81. ICLR 2026Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
82. ICLR 2026Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization
83. ICLR 2026Sim2Real VLA: Zero-Shot Generalization of Synthesized Skills to Realistic Manipulation
84. ICLR 2026SiNGER: A Clearer Voice Distills Vision Transformers Further
85. ICLR 2026SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
86. ICLR 2026Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
87. ICLR 2026SpatiaLab: Can Vision–Language Models Perform Spatial Reasoning in the Wild?
88. ICLR 2026Spatially Guided Training for Vision-Language-Action Model
89. ICLR 2026Subspace Kernel Learning on Tensor Sequences
90. ICLR 2026Time Optimal Execution of Action Chunk Policies Beyond Demonstration Speed
91. ICLR 2026To Sink or Not to Sink: Visual Information Pathways in Large Vision-Language Models
92. ICLR 2026Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
93. ICLR 2026TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models
94. ICLR 2026Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Diffusion Diffusion Process
95. ICLR 2026Unified Vision-Language-Action Model
96. ICLR 2026Unifying Diffusion and Autoregression for Generalizable Vision-Language-Action Model
97. ICLR 2026VADv2: End-to-End Autonomous Driving via Probabilistic Planning
98. ICLR 2026VEAttack: Downstream-agnostic Vision Encoder Attack against Large Vision Language Models
99. ICLR 2026Verifier-free Test-Time Sampling for Vision Language Action Models
100. ICLR 2026Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools

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。