Skip to content

Explicit Kinematic Guidance from Analytic Concepts for Vision-Language-Action Models

Jul 2026 · arXiv.org · Vol abs/2607.26513 · 0 citations · 36 references
Computer Science

TL;DR

A Concept Expert module is constructed for VLA to build executable Analytic Concepts that represent objects as explicit, programmatic blueprints that provide explicit, high-quality guidance for VLA fine-tuning through dense, programmatic manipulation rewards and precise spatial guidance.

Abstract

Current Vision-Language-Action (VLA) models rely mainly on 2D inputs, neglecting the rich object structural information and commonsense knowledge inherent in the 3D physical world. This deficiency restricts their spatial awareness and adaptability for complex, high-precision manipulation. To bridge this crucial gap, we construct a Concept Expert module for VLA to build executable Analytic Concepts that represent objects as explicit, programmatic blueprints. Our mechanism operates in two synergistic phases: First, prior to VLA inference, the Concept Expert leverages 3D information from Vision Foundation Models (VFMs) to estimate the initial kinematic and structural parameters. Second, throughout the manipulation process, the VLA model utilizes its inherent capability to dynamically track the dynamic concept parameters, continuously aligning them with observational changes to ensure persistent accuracy. Once established, the Analytic Concepts provide explicit, high-quality guidance for VLA fine-tuning through (1) dense, programmatic manipulation rewards and (2) precise spatial guidance. This formulation allows VLA models to learn physically grounded interaction behaviors while maintaining end-to-end learning flexibility. Our experimental results show consistent improvements in success rate and learning efficiency across supervised and reinforcement learning settings, demonstrating the effectiveness of structured, concept-based guidance for VLA post-training.

View source

Similar papers

Preprint Sep 2026

Topology-Informed Visual Prompting For Vision Language Action Policies

This work presents a topology-guided visual-prompting framework that uses simulation-based planning to augment a nominal demonstration dataset and provides vision-based guidance at deployment and outperforms a VLA fine-tuned only on nominal demonstrations and a VLM-prompting baseline that can remove topology-relevant i...

Hao-Yang Wu, Abhinav Kumar, Dmitry Berenson · 0 citations
#artificial intelligence Preprint Aug 2026

PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models

PHR-VLA introduces a lightweight auxiliary future head that, during training, aligns the VLA's internal representations with latent dynamics extracted from future observations, demonstrating that privileged latent dynamics alignment provides an effective training signal for improving anticipatory reasoning in VLA polic...

Davood Soleymanzadeh, Kai-Di Zhang, Zhi-Yuan Zhang et al. · 2 citations
Preprint Aug 2026

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

GaussVLA is proposed, a Mamba-based VLA that incorporates two custom modules: Gaussian Spatial Tokenizer (GST) to lift frozen semantic and depth features into compact 3D Gaussian tokens, and Depth-Aware Chain-of-Thought (DA-CoT) that performs structured, non-autoregressive geometric reasoning under language and flow-ti...

MD SELIM SAROWAR, Md Tanvir Islam, Sungho Kim et al. · 1 citation
Preprint Sep 2026

HINT: Human-Intent Inception for Long-Horizon Robot Manipulation

HINT (Human-INTent INcepTion), an agentic framework inspired by the human manipulation principles: semantic intent changes sparsely at manipulation-pattern transitions, whereas continuous control primarily depends on the evolving object-hand relationship.

Ming-Yu Mei, Haojie Xu, Shi-Hao Jin et al. · 0 citations
Sep 2026

MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligence

MachEmbodied-U0, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture, is presented, a unified embodied foundation model connecting understanding and generation experts through a Mixture-of-Transformers architecture that combines competitive...

Hao-Ran Wen, Wen-Fu Wang, Kun-Song Shi et al. · 1 citation
Preprint Sep 2026

Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D

This paper proposes Bridge3D, a method that integrates both implicit and explicit 3D geometry guidance into pre-trained 2D VLA models, enabling them to see and act in 3D, and introduces two strategies that enriches visual tokens with features from 3D foundation models to improve seeing and acting in 3D.

Hao-Xuan Li, Si-Xu Yan, Liang-Hui Zhu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.