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 708 篇，第 14 / 15 页

651. NeurIPS 2026RotVLA: Rotational Latent Action for Vision-Language-Action Model
652. NeurIPS 2026RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers
653. NeurIPS 2026Say the Same, Act Differently: Text-Orthogonal Action Subspaces in Reasoning Vision-Language-Action Models
654. NeurIPS 2026SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema
655. NeurIPS 2026SEAR: Sample Efficient Action Chunking Reinforcement Learning
656. NeurIPS 2026See it to Place it: Evolving Macro Placements with Vision Language Models
657. NeurIPS 2026Segment and Select: Vision-Language Segmentation in 3D Scenarios
658. NeurIPS 2026SelfCritic-VLA: Language as Intrinsic Critic for Vision Language Action Models in Autonomous Driving
659. NeurIPS 2026Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language Models
660. NeurIPS 2026Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
661. NeurIPS 2026SF-DST: Adapting Vision-Language Models for Anomaly Detection via Asymmetric Modulation and A-LoRA
662. NeurIPS 2026Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
663. NeurIPS 2026SimVLA: Attributing Gains in VLA Models Through Controlled Ablation
664. NeurIPS 2026SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers
665. NeurIPS 2026Sophon: A Procedural Diagnostic for Spatial Reasoning in Vision-Language Models
666. NeurIPS 2026SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models
667. NeurIPS 2026Spatial Representation Distillation and Knowledge Routing for Vision-Language-Action Models
668. NeurIPS 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
669. NeurIPS 2026SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models
670. NeurIPS 2026Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
671. NeurIPS 2026State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods
672. NeurIPS 2026Static-Dynamic Disentanglement for Efficient Multi-Frame Vision-Language-Action Models
673. NeurIPS 2026StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models
674. NeurIPS 2026SurGe: Improved Surface Geometry in Point Maps
675. NeurIPS 2026Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces
676. NeurIPS 2026The Sign Code: The Hidden Binary Nature of Deep Networks
677. NeurIPS 2026Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
678. NeurIPS 2026Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous Driving
679. NeurIPS 2026TopoCurve: Geometry-Aware Topology Reasoning via Bézier Curves in Autonomous Driving
680. NeurIPS 2026Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
681. NeurIPS 2026Towards Generalizable Data Valuation: Learning an End-to-end Deep Model to Compute Shapley Values
682. NeurIPS 2026Towards Reliable VLM Judges: State-Conditional Invariance and Presentation-Aware Diagnostics
683. NeurIPS 2026TrAction: Action Recognition with Sparse Trajectories
684. NeurIPS 2026Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
685. NeurIPS 2026Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
686. NeurIPS 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
687. NeurIPS 2026Two-Fidelity Best-Action Identification for Stochastic Minimax Tree
688. NeurIPS 2026Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models
689. NeurIPS 2026UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
690. NeurIPS 2026UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
691. NeurIPS 2026V1-Inspired Dynamic Vision System: A Bio-Plausible Video Embedding Framework with Decoupled Shape–Color Pathways and Long-Range Spatiotemporal Perception
692. NeurIPS 2026VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
693. NeurIPS 2026VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
694. NeurIPS 2026ViLo: LiDAR Localization with Vision-Language Priors
695. NeurIPS 2026VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology
696. NeurIPS 2026Vision Token Pruning via Query-Vision Interaction Decomposition
697. NeurIPS 2026Vision Transformers Learn Gestalt-Like Figure-Ground Cues from Natural Images
698. NeurIPS 2026Vision-Language Grounding as Bidirectional Concept Correspondence
699. NeurIPS 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
700. NeurIPS 2026VISTA: Support-Anchored Value Targeting for Fast Flow-Based Vision-Language-Action Policies

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。