# Lingchu Intelligence and collaborators propose FAFM, a continuous action generation method for heterogeneous-frequency data, accepted to NeurIPS 2026

- Source: PsiBot/灵初智能
- Published: 2026-11-03T06:35:53.000Z
- RoboHot: https://robohot.news/en/items/zv9fhv305k5roerlqaxmodylc
- Original: https://www.psibot.ai/neurips-2026-%e8%ae%a9%e6%9c%ba%e5%99%a8%e4%ba%ba%e5%8a%a8%e4%bd%9c%e8%bf%9e%e7%bb%ad%e8%80%8c%e7%a8%b3%e5%ae%9a%ef%bc%81fafm%e5%b8%a6%e6%9d%a5%e9%9d%a2%e5%90%91%e5%bc%82%e9%a2%91%e6%95%b0%e6%8d%ae/

## Summary

Lingchu Intelligence, together with Beihang University, Peking University, and The Chinese University of Hong Kong, proposed a frequency-aware flow matching method called FAFM; the paper was accepted to the NeurIPS 2026 main conference. The method uses the discrete cosine transform (DCT-II) to represent actions as frequency-domain coefficients corresponding to real time, performs flow matching in coefficient space and constrains the first-order time derivative, requires no additional learnable parameters, and can be used independently or integrated into VLA models such as π₀ and π₀.₅.

## Why it matters

The paper presents a frequency-domain action representation that adds no learnable parameters and can be integrated into existing VLA models, offering a transferable approach for joint training on heterogeneous-frequency data.