应用 · robotics论文趋势 2023–2026

主要结论

• 应用 · robotics论文从 2023 年的 7 篇增长到 2026 年的 252 篇，三年间扩大到约 36 倍。
• ICML 是发应用 · robotics论文最多的会议，2023–2026 年共 194 篇，占四个会议总量的 49%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 111 篇。
• 在「应用领域」的 10 个主题里，它的 2026 年论文数排第 6；同组增长最快的应用 · health medicine是 61 倍，应用 · robotics是 36 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 2026AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking
• ICML 2026Cross-Tactile Sensor Representation Learning
• ICLR 2026DexMove: Learning Tactile-Guided Non-Prehensile Manipulation with Dexterous Hands
• CVPR 2026DeDelayed Deleting Remote Inference Delay via On-Device Correction
• NeurIPS 2025$\textit{HiMaCon:}$ Discovering Hierarchical Manipulation Concepts from Unlabeled Multi-Modal Data
• ICML 2025DexScale: Automating Data Scaling for Sim2Real Generalizable Robot Control
• ICLR 2025Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery
• CVPR 2025Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics
• NeurIPS 2024BAKU: An Efficient Transformer for Multi-Task Policy Learning
• ICLR 2024Course Correcting Koopman Representations
• CVPR 2024PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness
• ICML 2023Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation
• ICLR 2023PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm
• CVPR 2023FLEX: Full-Body Grasping Without Full-Body Grasps
• NeurIPS 2026Compositional Training-Free Diffusion Planning for Long-Horizon Multiple Reach-Avoid Tasks
• ICML 2026DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile Adapter
• ICLR 2026Difference-Aware Retrieval Polices for Imitation Learning
• NeurIPS 2025Enhancing LLM Planning for Robotics Manipulation through Hierarchical Procedural Knowledge Graphs
• ICML 2025Hierarchical Equivariant Policy via Frame Transfer
• ICLR 2025EqNIO: Subequivariant Neural Inertial Odometry

全部应用 · robotics论文

共 156 篇，第 3 / 4 页

101. ICML 2026PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation
102. ICML 2026Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation
103. ICML 2026Plug-and-Play Label Map Diffusion for Universal Goal-Oriented Navigation
104. ICML 2026Predicting What Matters: Robust Generalist Robot Policy Learning via Future Semantic Mask
105. ICML 2026Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
106. ICML 2026ProAct: A Benchmark and Multimodal Framework for Structure-Aware Proactive Response
107. ICML 2026PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
108. ICML 2026RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
109. ICML 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
110. ICML 2026Recovering Hidden Reward in Diffusion-Based Policies
111. ICML 2026Reflex: Real-Time Vision-Language-Action Control through Streaming Inference
112. ICML 2026ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
113. ICML 2026Rethinking Instruction Drift as a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning
114. ICML 2026RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
115. ICML 2026RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies
116. ICML 2026RoboOmni: Actions Are Just Another Modality for Vision-Language Models
117. ICML 2026RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
118. ICML 2026SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning
119. ICML 2026SafeDec: Constrained Decoding for Safe Autoregressive Generalist Robot Navigation Policies
120. ICML 2026SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific Robotics
121. ICML 2026Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation
122. ICML 2026Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
123. ICML 2026SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models
124. ICML 2026Scaling by Diversified Experience for Vision-Language-Action Models
125. ICML 2026Scaling Real-World Robot Policy Evaluation via Discrete Diffusion World Model
126. ICML 2026See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
127. ICML 2026Seeing Realism from Simulation: Efficient Video Transfer for Vision-Language-Action Data Augmentation
128. ICML 2026Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation
129. ICML 2026Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
130. ICML 2026SkillNet: Hierarchical Skill Modeling for Compositional Generalization in Vision-Language Action Models
131. ICML 2026SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-Body Manipulation
132. ICML 2026Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning
133. ICML 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Action
134. ICML 2026SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
135. ICML 2026Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
136. ICML 2026SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
137. ICML 2026SPUR: Scale-Partitioned Uncertainty Rectification for Robust UAV-on-UAV Interception
138. ICML 2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction
139. ICML 2026Structured 4D Latent Predictive Model for Robot Planning
140. ICML 2026Tabero: Learning Gentle Manipulation with Closed-Loop Force Feedback from Vision, Touch, and Language
141. ICML 2026TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation
142. ICML 2026The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space
143. ICML 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
144. ICML 2026Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
145. ICML 2026UAV$^2$: A Unified and Adaptive Scheduling Framework for UAV Autopilot System with Reinforcement Learning
146. ICML 2026UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
147. ICML 2026UniMapping: Unified SLAM Framework for Map-Centric Embodied Perception
148. ICML 2026Vision-Language-Action Pretraining from Large-Scale Human Videos
149. ICML 2026VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
150. ICML 2026VLANeXt: Recipes for Building Strong VLA Models

常见问题

2023–2026 年四大会议一共有多少篇应用 · robotics论文？

共 393 篇，按年份分别是 2023 年 7 篇、2024 年 65 篇、2025 年 69 篇、2026 年 252 篇。

NeurIPS 2026 有多少篇应用 · robotics论文？

NeurIPS 2026 有 69 篇应用 · robotics论文，上一届是 6 篇。

ICLR 2026 有多少篇应用 · robotics论文？

ICLR 2026 有 26 篇应用 · robotics论文，上一届是 23 篇。

ICML 2026 有多少篇应用 · robotics论文？

ICML 2026 有 156 篇应用 · robotics论文，上一届是 36 篇。

CVPR 2026 有多少篇应用 · robotics论文？

CVPR 2026 有 1 篇应用 · robotics论文，上一届是 4 篇。

哪个会议的应用 · robotics论文最多？

ICML，2023–2026 年共 194 篇。