Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916051671842816 |
|---|---|
| author | Liu, Haoyun Zhao, Jianzhuang Chang, Xinyuan Shi, Tianle Meng, Chuanzhang Tan, Jiayuan Xiong, Feng Lin, Tong Huo, Dongjie Xu, Mu Dong, SongLin Ma, Zhiheng Gong, Yihong Zhong, Sheng |
| author_facet | Liu, Haoyun Zhao, Jianzhuang Chang, Xinyuan Shi, Tianle Meng, Chuanzhang Tan, Jiayuan Xiong, Feng Lin, Tong Huo, Dongjie Xu, Mu Dong, SongLin Ma, Zhiheng Gong, Yihong Zhong, Sheng |
| contents | Despite the rapid progress of vision-language-action (VLA) models, the prevailing practice of predicting action chunks as discrete waypoints remains structurally misaligned with the intrinsic continuity of physical motion. This discretization arises naturally from fixed-rate robot data collection and the token-by-token prediction paradigm of large language models, but ties actions to rigid sampling rates, does not naturally support analytically consistent higher-order derivatives, and introduces quantization artifacts that hinder precise, compliant interaction. We propose Neural Implicit Action Fields (NIAF), which reformulates chunk-level action representation from discrete waypoints to continuous action functions. Using a vision-language model as a hierarchical spectral modulator over a learnable motion prior, NIAF synthesizes continuous-time action manifolds with arbitrary temporal resolution. This formulation enables analytical differentiation, allowing explicit supervision of velocity and regularization of higher-order derivative signals to promote mathematical consistency, physical plausibility, and control smoothness. Our approach achieves strong results on CALVIN and LIBERO across diverse backbones. Real-world experiments further confirm that NIAF supports stable impedance control, bridging policy-side action generation and execution-side smooth control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01766 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models Liu, Haoyun Zhao, Jianzhuang Chang, Xinyuan Shi, Tianle Meng, Chuanzhang Tan, Jiayuan Xiong, Feng Lin, Tong Huo, Dongjie Xu, Mu Dong, SongLin Ma, Zhiheng Gong, Yihong Zhong, Sheng Robotics Despite the rapid progress of vision-language-action (VLA) models, the prevailing practice of predicting action chunks as discrete waypoints remains structurally misaligned with the intrinsic continuity of physical motion. This discretization arises naturally from fixed-rate robot data collection and the token-by-token prediction paradigm of large language models, but ties actions to rigid sampling rates, does not naturally support analytically consistent higher-order derivatives, and introduces quantization artifacts that hinder precise, compliant interaction. We propose Neural Implicit Action Fields (NIAF), which reformulates chunk-level action representation from discrete waypoints to continuous action functions. Using a vision-language model as a hierarchical spectral modulator over a learnable motion prior, NIAF synthesizes continuous-time action manifolds with arbitrary temporal resolution. This formulation enables analytical differentiation, allowing explicit supervision of velocity and regularization of higher-order derivative signals to promote mathematical consistency, physical plausibility, and control smoothness. Our approach achieves strong results on CALVIN and LIBERO across diverse backbones. Real-world experiments further confirm that NIAF supports stable impedance control, bridging policy-side action generation and execution-side smooth control. |
| title | Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.01766 |