视觉-语言-动作论文趋势 2023–2026

VLA 与端到端驾驶

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,639 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

视觉-语言-动作论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023883034105257
20241082962130329
20251086433140345
2026204113126265708

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

全部视觉-语言-动作论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 108 篇，第 1 / 3 页

  1. NeurIPS 20243DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
  2. NeurIPS 2024A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
  3. NeurIPS 2024Accelerating Transformers with Spectrum-Preserving Token Merging
  4. NeurIPS 2024ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
  5. NeurIPS 2024Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
  6. NeurIPS 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
  7. NeurIPS 2024AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
  8. NeurIPS 2024Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
  9. NeurIPS 2024Are We on the Right Way for Evaluating Large Vision-Language Models?
  10. NeurIPS 2024Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
  11. NeurIPS 2024BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
  12. NeurIPS 2024BendVLM: Test-Time Debiasing of Vision-Language Embeddings
  13. NeurIPS 2024Biologically Inspired Learning Model for Instructed Vision
  14. NeurIPS 2024CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
  15. NeurIPS 2024CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
  16. NeurIPS 2024ClevrSkills: Compositional Language And Visual Reasoning in Robotics
  17. NeurIPS 2024Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
  18. NeurIPS 2024CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
  19. NeurIPS 2024Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
  20. NeurIPS 2024Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
  21. NeurIPS 2024ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
  22. NeurIPS 2024Demystify Mamba in Vision: A Linear Attention Perspective
  23. NeurIPS 2024DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
  24. NeurIPS 2024Depth Anything V2
  25. NeurIPS 2024Dissecting Query-Key Interaction in Vision Transformers
  26. NeurIPS 2024Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
  27. NeurIPS 2024Efficient Temporal Action Segmentation via Boundary-aware Query Voting
  28. NeurIPS 2024Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers
  29. NeurIPS 2024Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
  30. NeurIPS 2024Exploring Token Pruning in Vision State Space Models
  31. NeurIPS 2024Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
  32. NeurIPS 2024Flexible Context-Driven Sensory Processing in Dynamical Vision Models
  33. NeurIPS 2024FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
  34. NeurIPS 2024Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
  35. NeurIPS 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
  36. NeurIPS 2024Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
  37. NeurIPS 2024How many classifiers do we need?
  38. NeurIPS 2024HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
  39. NeurIPS 2024HydraViT: Stacking Heads for a Scalable ViT
  40. NeurIPS 2024Image2Struct: Benchmarking Structure Extraction for Vision-Language Models
  41. NeurIPS 2024Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
  42. NeurIPS 2024InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
  43. NeurIPS 2024IPO: Interpretable Prompt Optimization for Vision-Language Models
  44. NeurIPS 2024JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
  45. NeurIPS 2024Latent Intrinsics Emerge from Training to Relight
  46. NeurIPS 2024Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
  47. NeurIPS 2024Learning Group Actions on Latent Representations
  48. NeurIPS 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression
  49. NeurIPS 2024Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
  50. NeurIPS 2024Learning Where to Edit Vision Transformers

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 查视觉-语言-动作在 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": "vision-language-action"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「机器人与具身」下的其他主题