Vision-Language-Action papers, 2023–2026

Key findings

• Vision-Language-Action went from 257 papers in 2023 to 708 in 2026, roughly 2.8x in three years.
• CVPR publishes the most Vision-Language-Action work: 640 papers from 2023 to 2026, 39% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 21 in 2023 to 135 in 2026.
• Among the 5 topics under Robotics and Embodied AI, it ranks #1 by 2026 paper count; the fastest grower in the group, Humanoid Control, is up 3.8x versus 2.8x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Vision-Language-Action papers

708 papers, page 13 of 15

601. NeurIPS 2026Long-term Embodied Visual Tracking with Lightweight Vision-Language-Action Models
602. NeurIPS 2026LookThere! Sparse Vision by Reinforced Selection
603. NeurIPS 2026Lost on Campus: Evaluating Embodied Spatial Reasoning of Vision-Language Models in the Wild
604. NeurIPS 2026Masked Diffusion Vision-Language Models for Temporal Action Localization
605. NeurIPS 2026Measuring Coherence in Predictive Models
606. NeurIPS 2026MHWA: Multi-timescale Hierarchical World-Action Model
607. NeurIPS 2026Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?
608. NeurIPS 2026Mitigating Asymmetric Boundary Encroachment in Continual Learning of Vision-Language Models
609. NeurIPS 2026MM-SCALE: Evaluating Evidence-Grounded Moral Judgment in Vision-Language Models
610. NeurIPS 2026MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision
611. NeurIPS 2026Multi-Armed Bandits With Best-Action Queries
612. NeurIPS 2026Near-Optimal Learning in Parametric Bandits with Action-Dependent Coarsened Feedback
613. NeurIPS 2026NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Model
614. NeurIPS 2026Neural Garbage Collection: Learning to Forget while Learning to Reason
615. NeurIPS 2026No-Regret Caching with Delayed Hits
616. NeurIPS 2026Not Every Image Teaches Vision: Visual-Necessity-Gated Continual Learning for Multimodal Large Language Models
617. NeurIPS 2026NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
618. NeurIPS 2026NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
619. NeurIPS 2026Object Hallucination Mitigation in Large Vision-Language Models via Self-Vision Dual Masking and Uncertainty-Triggered Assembly
620. NeurIPS 2026OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models
621. NeurIPS 2026OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
622. NeurIPS 2026On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs
623. NeurIPS 2026OT-Robust3DVLA: A Wasserstein Barycenter is the Right Inductive Bias for Robust Multi-View 3D Vision-Language-Action Policies
624. NeurIPS 2026P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language Models
625. NeurIPS 2026PAPO-VLA: Planning-Aware Policy Optimization for Vision-Language-Action Models
626. NeurIPS 2026Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers
627. NeurIPS 2026Pathways of Visual Information Flow in Vision-Language Models
628. NeurIPS 2026Perception for Action in Latent World Models
629. NeurIPS 2026Phase-Adaptive Fusion: Spatio-Temporal Modulation for VLA Models
630. NeurIPS 2026Point Tracking Improves World Action Models
631. NeurIPS 2026Poison-then-Hide: Finetuning-Activated Backdoor Attack on Pretrained Vision Encoders
632. NeurIPS 2026PolyVision: Conditional Visual Scaling Via Dynamic Expert Routing For Vision-Centric MLLMs
633. NeurIPS 2026PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
634. NeurIPS 2026Post-Training Quantization with Gradient-Projected Fisher Approximation for Vision Transformers
635. NeurIPS 2026PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models
636. NeurIPS 2026PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA
637. NeurIPS 2026ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
638. NeurIPS 2026Profit Maximization in Bilateral Trade against a Smooth Adversary
639. NeurIPS 2026Progressive Pseudo-label Self-balancing Towards Unsupervised Vision-Language Models Adaptation
640. NeurIPS 2026Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
641. NeurIPS 2026RadarFlowPose: Vision-Inspired Coarse-to-Fine Skeleton Refinement with Flow Matching
642. NeurIPS 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
643. NeurIPS 2026Remembering What Matters: From Markovian to Subtask-Causal Memory in VLA Policies
644. NeurIPS 2026RePO-VLA: Recovery-Driven Policy Optimization for Vision-Language-Action Models
645. NeurIPS 2026Residual Expertise Is Not Decision Value
646. NeurIPS 2026Rethink Action Chunking in VLA Through Human Motor Control
647. NeurIPS 2026Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching
648. NeurIPS 2026Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
649. NeurIPS 2026Risk-Aware Action Repetition via Expected Skip Evaluation
650. NeurIPS 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models

FAQ

How many Vision-Language-Action papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,639 in total: 257 in 2023, 329 in 2024, 345 in 2025, 708 in 2026.

How many Vision-Language-Action papers are at NeurIPS 2026?

NeurIPS 2026 has 204 Vision-Language-Action papers, versus 108 the year before.

How many Vision-Language-Action papers are at ICLR 2026?

ICLR 2026 has 113 Vision-Language-Action papers, versus 64 the year before.

How many Vision-Language-Action papers are at ICML 2026?

ICML 2026 has 126 Vision-Language-Action papers, versus 33 the year before.

How many Vision-Language-Action papers are at CVPR 2026?

CVPR 2026 has 265 Vision-Language-Action papers, versus 140 the year before.

Which conference publishes the most Vision-Language-Action papers?

CVPR, with 640 papers from 2023 to 2026.