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
- 视觉-语言-动作论文从 2023 年的 257 篇增长到 2026 年的 708 篇，三年间扩大到约 2.8 倍。
- CVPR 是发视觉-语言-动作论文最多的会议，2023–2026 年共 640 篇，占四个会议总量的 39%。
- 交叉方向里涨得最快的是应用 · computer vision：同时属于两个主题的论文从 2023 年的 21 篇增至 2026 年的 135 篇。
- 在「机器人与具身」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的人形控制是 3.8 倍，视觉-语言-动作是 2.8 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 88 | 30 | 34 | 105 | 257 |
| 2024 | 108 | 29 | 62 | 130 | 329 |
| 2025 | 108 | 64 | 33 | 140 | 345 |
| 2026 | 204 | 113 | 126 | 265 | 708 |
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 2026A Dual-Domain Vision Transformer with Spectral Positional Bias
- ICML 2026FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
- ICLR 2026Curvature-Guided Task Synergy for Skeleton based Temporal Action Segmentation
- CVPR 2026ActAvatar Temporally-Aware Precise Action Control for Talking Avatars
- NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
- ICML 2025Feasible Action Search for Bandit Linear Programs via Thompson Sampling
- ICLR 2025Action Sequence Augmentation for Action Anticipation
- CVPR 2025Active Event-based Stereo Vision
- NeurIPS 2024GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
- ICML 2024Causal Action Influence Aware Counterfactual Data Augmentation
- ICLR 2024Matrix Manifold Neural Networks++
- CVPR 2024End-to-End Spatio-Temporal Action Localisation with Video Transformers
- NeurIPS 2023Activity Grammars for Temporal Action Segmentation
- ICML 2023Algorithmic Collective Action in Machine Learning
- ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
- CVPR 20233Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition
- NeurIPS 2026A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
- ICML 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
- ICLR 2026EAST: Early Action Prediction Sampling Strategy with Token Masking
- CVPR 2026DarkShake-DVS Event-based Human Action Recognition under Low-light and Shaking Camera
全部视觉-语言-动作论文
共 345 篇，第 6 / 7 页
- NeurIPS 2025BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
- NeurIPS 2025BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
- NeurIPS 2025Bridging Brains and Concepts: Interpretable Visual Decoding from fMRI with Semantic Bottlenecks
- NeurIPS 2025ChatVLA-2: Vision-Language-Action Model with Open-World Reasoning
- NeurIPS 2025Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening
- NeurIPS 2025CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models
- NeurIPS 2025CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
- NeurIPS 2025Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
- NeurIPS 2025CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model
- NeurIPS 2025CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification
- NeurIPS 2025Computational Budget Should Be Considered in Data Selection
- NeurIPS 2025Cross-modal Associations in Vision and Language Models: Revisiting the Bouba-Kiki Effect
- NeurIPS 2025DEXTER: Diffusion-Guided EXplanations with TExtual Reasoning for Vision Models
- NeurIPS 2025Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition
- NeurIPS 2025Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition
- NeurIPS 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
- NeurIPS 2025DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
- NeurIPS 2025Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
- NeurIPS 2025Each Complexity Deserves a Pruning Policy
- NeurIPS 2025EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
- NeurIPS 2025EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation
- NeurIPS 2025Embodied Cognition Augmented End2End Autonomous Driving
- NeurIPS 2025Emerging Risks from Embodied AI Require Urgent Policy Action
- NeurIPS 2025End-to-End Vision Tokenizer Tuning
- NeurIPS 2025Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding
- NeurIPS 2025Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting
- NeurIPS 2025ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models
- NeurIPS 2025Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness
- NeurIPS 2025Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere
- NeurIPS 2025Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization
- NeurIPS 2025Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning
- NeurIPS 2025FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
- NeurIPS 2025FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
- NeurIPS 2025FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
- NeurIPS 2025FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network
- NeurIPS 2025From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D
- NeurIPS 2025From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
- NeurIPS 2025From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging
- NeurIPS 2025Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling
- NeurIPS 2025Glance2Gaze: Efficient Vision-Language Models from Glance Fusion to Gaze Compression
- NeurIPS 2025GoalLadder: Incremental Goal Discovery with Vision-Language Models
- NeurIPS 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
- NeurIPS 2025HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
- NeurIPS 2025HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
- NeurIPS 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
- NeurIPS 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- NeurIPS 2025Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization
- NeurIPS 2025Learning Robust Vision-Language Models from Natural Latent Spaces
- NeurIPS 2025Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection
- NeurIPS 2025Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common Corruptions
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"}
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。