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 93 篇，第 2 / 2 页

51. ICLR 2025LASeR: Towards Diversified and Generalizable Robot Design with Large Language Models
52. ICLR 2025Learning Geometric Reasoning Networks For Robot Task And Motion Planning
53. ICLR 2025Physics of Language Models: Part 3.2, Knowledge Manipulation
54. ICLR 2025Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation
55. ICLR 2025RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
56. ICLR 2025ReGen: Generative Robot Simulation via Inverse Design
57. ICLR 2025Revisit Micro-batch Clipping: Adaptive Data Pruning via Gradient Manipulation
58. ICLR 2025Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets
59. ICLR 2025SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
60. ICLR 2025Subtask-Aware Visual Reward Learning from Segmented Demonstrations
61. ICLR 2025TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning
62. ICLR 2025TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
63. ICLR 2025Vision Language Models are In-Context Value Learners
64. ICLR 2025What Matters in Learning from Large-Scale Datasets for Robot Manipulation
65. ICLR 2025What's the Move? Hybrid Imitation Learning via Salient Points
66. ICLR 2024ASID: Active Exploration for System Identification in Robotic Manipulation
67. ICLR 2024CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects
68. ICLR 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
69. ICLR 2024Grounding Language Plans in Demonstrations Through Counterfactual Perturbations
70. ICLR 2024Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response
71. ICLR 2024Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
72. ICLR 2024Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
73. ICLR 2024Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
74. ICLR 2024Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency
75. ICLR 2024Robot Fleet Learning via Policy Merging
76. ICLR 2024RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
77. ICLR 2024Score Models for Offline Goal-Conditioned Reinforcement Learning
78. ICLR 2024SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
79. ICLR 2024Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
80. ICLR 2024Vision-Language Foundation Models as Effective Robot Imitators
81. ICLR 2024What Matters to You? Towards Visual Representation Alignment for Robot Learning
82. ICLR 2023Adversarial Imitation Learning with Preferences
83. ICLR 2023Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
84. ICLR 2023DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
85. ICLR 2023DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation
86. ICLR 2023Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
87. ICLR 2023FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
88. ICLR 2023From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
89. ICLR 2023Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance
90. ICLR 2023Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
91. ICLR 2023SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
92. ICLR 2023Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
93. ICLR 2023VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

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。