Latticethe structure behind the noise

Papers Digest Topics Selected Labs Collections FAQ

Created by Flynn Lachendro

Papers Digest Topics Labs Saved

Search

Search papers, labs, and topics across Lattice.

Built by Flynn Lachendro·𝕏 / Twitter·RSS··FAQ·Glossary·Privacy

Jingyu Li | Lattice

Jingyu Li

LIGHTSPEED, Tencent

Papers on Lattice

1

Total citations

0

Topics

2

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (1)Speech & Audio (1)

Frequent co-authors

Zheqi Dai (1)Guangyan Zhang (1)Zhen Ye (1)Haolin He (1)

Papers (1)

Jun 16, 2026

3w ago·also HKUST, LIGHTSPEED, Tencent AI

One-Step Token-to-Waveform Generation with MeanFlow in Latent Space

Achieving one-step audio waveform generation with a 17× speedup while preserving quality could revolutionize TTS systems.

Zheqi Dai, Guangyan Zhang, Zhen Ye +5

Multimodal Models Speech & Audio

Qiuqiang Kong (1)