视觉-语言-动作论文趋势 2023–2026

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。

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 1,639 篇，第 12 / 33 页

551. NeurIPS 2026Diving-R1: Empowering Multimodal LLMs with Traceable Progressive Reasoning for Interpretable Diving Action Quality Assessment
552. NeurIPS 2026Do Glimpse Policies See Like Humans? A Behavioral Audit Reveals Dissociated Viewing Priors in Classification-Trained Active Vision
553. NeurIPS 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
554. NeurIPS 2026DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
555. NeurIPS 2026DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
556. NeurIPS 2026E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion
557. NeurIPS 2026EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
558. NeurIPS 2026Efficient Computation and Best-Response Dynamics in Anonymous Two-Action Games with Linear Utilities
559. NeurIPS 2026EgoStream: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric Vision
560. NeurIPS 2026ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models
561. NeurIPS 2026Enabling VLA Action Self-Verification via VLM Token Probability Bucketing
562. NeurIPS 2026EnvTrap: Revealing the Environment-Only Attack Surface in Embodied AI via Consequence-Blind Action Execution
563. NeurIPS 2026EpiStream: Utility-Aware Temporal Abstraction for Dense-Action Streams
564. NeurIPS 2026Evaluating Deployable Inference-Time Error Prediction in Vision MoEs
565. NeurIPS 2026Evaluating Spatiotemporal Reasoning of Vision-Language Models in Atari Gameplay
566. NeurIPS 2026Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies
567. NeurIPS 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
568. NeurIPS 2026Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving
569. NeurIPS 2026Exploring the Limits of Compositional Generalization in Vision-Language-Action Manipulation
570. NeurIPS 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?
571. NeurIPS 2026FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
572. NeurIPS 2026FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
573. NeurIPS 2026Focus Matters: Attention-Value Dynamics for Hallucination Mitigation in Vision-Language Models
574. NeurIPS 2026FocusNav: Learning Task-directed Perception via Action-Aware Future Reconstruction in Vision-and-Language Navigation
575. NeurIPS 2026FocusVLA: Hijacking Attention to Break Visual Token Pruning in Vision-Language-Action Models
576. NeurIPS 2026ForesightFlow: Self-Guided Flow Matching for Improving Vision-Language-Action Models
577. NeurIPS 2026FreeAct: Demonstration-Free Robot Adaptation via Action-Grounded Generated Videos
578. NeurIPS 2026From Seeing to Foreseeing: Unleashing LVLM Thinking in Dynamic Latent Space
579. NeurIPS 2026From Views to Worlds: Active Exploration over 3D Worlds for Vision-Language Models
580. NeurIPS 2026Generation-for-Understanding with Structured Action Scripts for Embodied Multimodal Learning
581. NeurIPS 2026GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations
582. NeurIPS 2026HEED: Density-Weighted Residual Alignment for Hybrid Vision-Language Model Distillation
583. NeurIPS 2026Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
584. NeurIPS 2026Higher-Order Action Supervision Makes A Strong Policy Class
585. NeurIPS 2026HyrCap: Hybrid Rank-Calibration of Action Proposals for Temporal Event Understanding
586. NeurIPS 2026I-Perceive: A Foundation Model for Vision-Language Active Perception
587. NeurIPS 2026In-Context Learning Can Help Vision Language Models Overcome Training Prior
588. NeurIPS 2026In-Context Learning for Remote Sensing Vision: A Semantic-Aware Rotation-Robust Diffusion Framework
589. NeurIPS 2026Incentivizing Medical Vision Capabilities from Large-Scale Multimodal Pre-training
590. NeurIPS 2026Intend, Reflect, Refine: An Adaptive Multimodal Reflection Framework for Autonomous Driving
591. NeurIPS 2026LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matching
592. NeurIPS 2026Learning CLI Agents with Structured Action Credit under Selective Observation
593. NeurIPS 2026Learning Deployable Causal Action Geometry under Temporal Non-Stationarity
594. NeurIPS 2026Learning Fine-Grained Vision-Language Alignment from Discriminative Part Descriptions
595. NeurIPS 2026Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
596. NeurIPS 2026Learning to Ask: Metacognitive Action Policy for Large and Small Language Model Collaboration
597. NeurIPS 2026LEGO: Sizing Rules for Budget-Aware Dense-to-MoE Conversion of Vision-Language Models
598. NeurIPS 2026LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
599. NeurIPS 2026Lipschitz Dueling Bandits over Continuous Action Spaces
600. NeurIPS 2026LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

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。