机器人操作论文趋势 2023–2026

主要结论

• 机器人操作论文从 2023 年的 44 篇增长到 2026 年的 135 篇，三年间扩大到约 3.1 倍。
• CVPR 是发机器人操作论文最多的会议，2023–2026 年共 97 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是应用 · robotics：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 29 篇。
• 在「机器人与具身」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的人形控制是 3.8 倍，机器人操作是 3.1 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 2026Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization
• ICML 2026Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
• ICLR 2026DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
• CVPR 2026AdaDexTrack Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking
• NeurIPS 2025$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
• ICML 2025STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization
• ICLR 2025Learning Geometric Reasoning Networks For Robot Task And Motion Planning
• CVPR 20253D-MVP: 3D Multiview Pretraining for Manipulation
• NeurIPS 2024SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
• ICML 2024Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning
• ICLR 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
• CVPR 2024GenH2R: Learning Generalizable Human-to-Robot Handover via Scalable Simulation Demonstration and Imitation
• NeurIPS 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
• ICML 2023MyoDex: A Generalizable Prior for Dexterous Manipulation
• ICLR 2023DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation
• CVPR 2023Autonomous Manipulation Learning for Similar Deformable Objects via Only One Demonstration
• NeurIPS 2026DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
• ICML 2026Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
• ICLR 2026Geometry-aware 4D Video Generation for Robot Manipulation
• CVPR 2026BiPreManip Learning Affordance-Based Bimanual Preparatory Manipulation through Anticipatory Collaboration

全部机器人操作论文

共 321 篇，第 2 / 7 页

51. ICLR 2026Generalizable Coarse-to-Fine Robot Manipulation via Language-Aligned 3D Keypoints
52. ICLR 2026Geometry-aware 4D Video Generation for Robot Manipulation
53. ICLR 2026HAMLET: Switch Your Vision-Language-Action Model into a History-Aware Policy
54. ICLR 2026Improving Diffusion Models for Class-imbalanced Training Data via Capacity Manipulation
55. ICLR 2026Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions
56. ICLR 2026Learning to Grasp Anything By Playing with Random Toys
57. ICLR 2026LeRobot: An Open-Source Library for End-to-End Robot Learning
58. ICLR 2026Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots
59. ICLR 2026Master Skill Learning with Policy-Grounded Synergy of LLM-based Reward Shaping and Exploring
60. ICLR 2026MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation
61. ICLR 2026Primary-Fine Decoupling for Action Generation in Robotic Imitation
62. ICLR 2026RAVEN: End-to-end Equivariant Robot Learning with RGB Cameras
63. ICLR 2026Real-Time Robot Execution with Masked Action Chunking
64. ICLR 2026ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation
65. ICLR 2026Remotely Detectable Robot Policy Watermarking
66. ICLR 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
67. ICLR 2026RoboOmni: Proactive Robot Manipulation in Omni-modal Context
68. ICLR 2026Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations
69. ICLR 2026Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
70. ICLR 2026Rodrigues Network for Learning Robot Actions
71. ICLR 2026SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
72. ICLR 2026SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
73. ICLR 2026Spatially Guided Training for Vision-Language-Action Model
74. ICLR 2026SpikePingpong: Spike Vision-based Fast-Slow Pingpong Robot System
75. ICLR 2026Streaming Drag-Oriented Interactive Video Manipulation: Drag Anything, Anytime!
76. ICLR 2026Translating Flow to Policy via Hindsight Online Imitation
77. ICLR 2026ViPRA: Video Prediction for Robot Actions
78. ICLR 2026VITA: Vision-to-Action Flow Matching Policy
79. ICLR 2026VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation
80. ICLR 2026When would Vision-Proprioception Policies Fail in Robotic Manipulation?
81. ICML 2026Cross-Embodiment Robot Foundation World Models with Latent Actions
82. ICML 2026DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
83. ICML 2026Demystifying Action Space Design for Robotic Manipulation Policies
84. ICML 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
85. ICML 2026Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
86. ICML 2026FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
87. ICML 2026From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
88. ICML 2026From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
89. ICML 2026Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking
90. ICML 2026Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
91. ICML 2026Hierarchical Policy Learning via Spectral Decomposition
92. ICML 2026Joint Navigation and Manipulation Planning with 3D Interaction Chains
93. ICML 2026Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained Problem
94. ICML 2026MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
95. ICML 2026Neural Control: Adjoint Learning Through Equilibrium Constraints
96. ICML 2026OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
97. ICML 2026Predicting What Matters: Robust Generalist Robot Policy Learning via Future Semantic Mask
98. ICML 2026ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
99. ICML 2026SafeDec: Constrained Decoding for Safe Autoregressive Generalist Robot Navigation Policies
100. ICML 2026Scaling Real-World Robot Policy Evaluation via Discrete Diffusion World Model

常见问题

2023–2026 年四大会议一共有多少篇机器人操作论文？

共 321 篇，按年份分别是 2023 年 44 篇、2024 年 46 篇、2025 年 96 篇、2026 年 135 篇。

NeurIPS 2026 有多少篇机器人操作论文？

NeurIPS 2026 有 30 篇机器人操作论文，上一届是 32 篇。

ICLR 2026 有多少篇机器人操作论文？

ICLR 2026 有 42 篇机器人操作论文，上一届是 23 篇。

ICML 2026 有多少篇机器人操作论文？

ICML 2026 有 25 篇机器人操作论文，上一届是 14 篇。

CVPR 2026 有多少篇机器人操作论文？

CVPR 2026 有 38 篇机器人操作论文，上一届是 27 篇。

哪个会议的机器人操作论文最多？

CVPR，2023–2026 年共 97 篇。