Dongya Jia
Scholar

Dongya Jia

Google Scholar ID: o2ucdzsAAAAJ
ByteDance Seed
Generative ModelLLMAudio Generation
Google Scholar↗
Citations & Impact
All-time
Citations
478
 
H-index
11
 
i10-index
13
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
8 items
On the Distillation Loss Functions of Speech VAE for Unified Reconstruction, Understanding, and Generation
2026
Cited
0
SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
2025
Cited
0
Heptapod: Language Modeling on Visual Signals
2025
Cited
0
Vevo2: Bridging Controllable Speech and Singing Voice Generation via Unified Prosody Learning
2025
Cited
0
Sounding that Object: Interactive Object-Aware Image to Audio Generation
2025
Cited
0
MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation
2025
Cited
0
DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
2025
Cited
0
Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions
2024
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)