Cheng Chang

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Speech & Audio (2)Multimodal Models (1)Architecture Design (Transformers, SSMs, MoE) (1)Open-Source Models & Weights (1)

Frequent co-authors

Y. Gong (2)Yitian Gong (2)Kuangwei Chen (2)Kuan-Yu Chen (2)

Papers (2)

Jul 26, 2026

Jul 26, 2026·also MOSI Intelligence, Shanghai Innovation, SJTU

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

Fine-grained cross-modal alignment in audio-video generation can dramatically enhance synchronization and quality, as shown by OmniVAE's innovative training approach.

Jun Zhan, Chenchen Yang, Y. Gong +24

Multimodal Models Speech & Audio

Mar 18, 2026

Mar 18, 2026·also MOSI Intelligence, Shanghai Innovation, SJTU, UESTC

MOSS-TTS Technical Report

Achieve controllable and scalable speech generation with MOSS-TTS, enabling zero-shot voice cloning and long-form synthesis.

Yitian Gong, Y. Gong, Botian Jiang +28

Architecture Design (Transformers, SSMs, MoE)Open-Source Models & Weights Speech & Audio

Search

Cheng Chang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)