Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models

TL;DR

This paper introduces Neural Implicit Action Fields (NIAF), a novel approach that models actions as continuous functions, enabling more precise, differentiable, and physically plausible motion trajectories in vision-language-action systems.

Contribution

NIAF shifts action prediction from discrete waypoints to continuous functions, utilizing a hierarchical spectral modulator and learnable motion prior for high-resolution, differentiable trajectories.

Findings

Achieves state-of-the-art on CALVIN and LIBERO benchmarks.

Enables stable impedance control in real-world experiments.

Provides explicit supervision of velocity, acceleration, and jerk.

Abstract

Despite the rapid progress of Vision-Language-Action (VLA) models, the prevailing paradigm of predicting discrete waypoints remains fundamentally misaligned with the intrinsic continuity of physical motion. This discretization imposes rigid sampling rates, lacks high-order differentiability, and introduces quantization artifacts that hinder precise, compliant interaction. We propose Neural Implicit Action Fields (NIAF), a paradigm shift that reformulates action prediction from discrete waypoints to continuous action function regression. By utilizing an MLLM as a hierarchical spectral modulator over a learnable motion prior, NIAF synthesizes infinite-resolution trajectories as continuous-time manifolds. This formulation enables analytical differentiability, allowing for explicit supervision of velocity, acceleration, and jerk to ensure mathematical consistency and physical plausibility. Our approach achieves state-of-the-art results on CALVIN and LIBERO benchmarks across diverse backbones. Furthermore, real-world experiments demonstrate that NIAF enables stable impedance control, bridging the gap between high-level semantic understanding and low-level dynamic execution.