mlsanityData to 14 Oct 2026

KineVLA: Towards Kinematics-Aware Vision-Language-Action Models with Bi-Level Action Decomposition

arXiv 2603.17524 ↗First posted 18 Mar 2026cs.RO cs.AIcited by 1

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must follow instruction-specified execution constraints, including interaction targets, motion patterns, spatial relations, and terminal configurations. This setting exposes a limitation of goal-oriented VLAs: trajectories that complete the same task are not interchangeable when the instruction specifies how the task must be executed. We propose ExecVLA, a framework that separates a goal-oriented component from an execution-specific component through a bi-level action representation and supervised bi-level reasoning tokens. We further introduce explicit goal-invariance and execution-predictability objectives so that the goal-level representation remains stable across executions of the same goal, while the execution-level representation retains the constraints that distinguish those executions. We construct execution-constraint-following datasets in simulation and on a Realman-75 robot, with goal and fine-grained reasoning annotations. Experiments on LIBERO and the real robot show improved goal completion and, more importantly, substantially more reliable adherence to instruction-specified execution constraints.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 25 of its 28 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

25 of 28 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025π0.5: a Vision-Language-Action Model with Open-World Generalization22 Apr
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 21

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  8. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  9. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  10. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 691
  11. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 339
  12. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 197
9 more
  1. 2025HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Modelcited by 181
  2. 2024Behavior Generation with Latent Actionscited by 160
  3. 2025ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulationcited by 91
  4. 2025VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizerscited by 70
  5. 2024QueST: Self-Supervised Skill Abstractions for Learning Continuous Controlcited by 53
  6. 2025VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedbackcited by 38
  7. 2024FoAR: Force-Aware Reactive Policy for Contact-Rich Robotic Manipulationcited by 33
  8. 2025FreeTacMan: Robot-free Visuo-Tactile Data Collection System for Contact-rich Manipulationcited by 21
  9. 2024NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026NebulaVLA: A Dual-Frequency Vision-Language-Action Model With Guide Action for Robotic Manipulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
  2. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  3. 2026CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts
  4. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  5. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
  6. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  7. 2026VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
  8. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines