导航论文趋势 2023–2026
视觉导航与 SLAM
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 119 篇被归入该主题的论文。
主要结论
- 导航论文从 2023 年的 18 篇增长到 2026 年的 44 篇，三年间扩大到约 2.4 倍。
- CVPR 是发导航论文最多的会议，2023–2026 年共 57 篇，占四个会议总量的 48%。
- 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 3 篇增至 2026 年的 16 篇。
- 在「机器人与具身」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的人形控制是 3.8 倍，导航是 2.4 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 3 | 4 | 3 | 8 | 18 |
| 2024 | 6 | 4 | 4 | 18 | 32 |
| 2025 | 11 | 4 | 1 | 9 | 25 |
| 2026 | 9 | 11 | 2 | 22 | 44 |
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 2026LiteNav: Lightweight Map-free Outdoor Visual Navigation
- ICML 2026PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
- ICLR 2026OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
- CVPR 2026OctoNav Towards Generalist Embodied Navigation
- NeurIPS 2025DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
- ICML 2025A Model of Place Field Reorganization During Reward Maximization
- ICLR 2025Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel
- CVPR 2025CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
- NeurIPS 2024Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
- ICML 2024Leveraging Attractor Dynamics in Spatial Navigation for Better Language Parsing
- ICLR 2024End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
- CVPR 2024Dual-View Visual Contextualization for Web Navigation
- NeurIPS 2023FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation
- ICML 2023Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation
- ICLR 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
- CVPR 20233D-Aware Object Goal Navigation via Simultaneous Exploration and Identification
- NeurIPS 2026The limbic navigation system as a hierarchical RNN
- ICML 2026SafeDec: Constrained Decoding for Safe Autoregressive Generalist Robot Navigation Policies
- ICLR 2026Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance
- CVPR 2026STRNet Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation
全部导航论文
共 23 篇，第 1 / 1 页
- ICLR 2026Building spatial world models from sparse transitional episodic memories
- ICLR 2026CE-Nav: Flow-Guided Reinforcement Refinement for Cross-Embodiment Local Navigation
- ICLR 2026CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs?
- ICLR 2026Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance
- ICLR 2026From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learning
- ICLR 2026GRL-SNAM: Geometric Reinforcement Learning with Differential Hamiltonians for Navigation and Mapping in Unknown Environments
- ICLR 2026Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-Language Navigation
- ICLR 2026JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation
- ICLR 2026Lifelong Embodied Navigation Learning
- ICLR 2026OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
- ICLR 2026WARC-Bench: Web Archive based Benchmark for GUI Subtask Executions
- ICLR 2025Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel
- ICLR 2025Efficient Active Imitation Learning with Random Network Distillation
- ICLR 2025Navigation-Guided Sparse Scene Representation for End-to-End Autonomous Driving
- ICLR 2025Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology
- ICLR 2024End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
- ICLR 2024Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction
- ICLR 2024Multimodal Web Navigation with Instruction-Finetuned Foundation Models
- ICLR 2024Selective Visual Representations Improve Convergence and Generalization for Embodied AI
- ICLR 2023DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS
- ICLR 2023Emergence of Maps in the Memories of Blind Navigation Agents
- ICLR 2023Learning Simultaneous Navigation and Construction in Grid Worlds
- ICLR 2023Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查导航在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "navigation"}
常见问题
- 2023–2026 年四大会议一共有多少篇导航论文？
- 共 119 篇，按年份分别是 2023 年 18 篇、2024 年 32 篇、2025 年 25 篇、2026 年 44 篇。
- NeurIPS 2026 有多少篇导航论文？
- NeurIPS 2026 有 9 篇导航论文，上一届是 11 篇。
- ICLR 2026 有多少篇导航论文？
- ICLR 2026 有 11 篇导航论文，上一届是 4 篇。
- ICML 2026 有多少篇导航论文？
- ICML 2026 有 2 篇导航论文，上一届是 1 篇。
- CVPR 2026 有多少篇导航论文？
- CVPR 2026 有 22 篇导航论文，上一届是 9 篇。
- 哪个会议的导航论文最多？
- CVPR，2023–2026 年共 57 篇。