Hai Huang
Hai Huang has 2 papers in our library, in 2024–2025, most of them on Efficient models & compression; often with Jialong Zuo, Minghui Fang, Mingyuan Zhou.
OpenAlex · ORCID · Wikidata · h-index 57 · 219 works · 11,307 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 39 times in our library · ⭐ Paper Stars ranking: #9968
Affiliations
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksArts and Humanities · 1 workLanguage and Linguistics · 1 workSignal Processing · 1 work
🧭 Topics 1Research subjects and languages the work is about.Efficient models & compression · 1 work
Works by year
2020s
Papers
- Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation (2024 · 32 citations)
Diffusion models produce excellent images, but sampling requires many passes through the network. For example, EDM uses 35 NFE on CIFAR-10 32x32 and 511 NFE on ImageNet 64x64. Score identity Distillation (SiD) compresses a pretrained diffusion model into a generator that creates an image in a single forward pass, and… - ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025 · 10 citations)
Text-to-speech systems have usually offered one of two abilities. Zero-shot models can copy an unseen speaker's voice but cannot change how that voice speaks. Style-controllable models follow textual style descriptions but cannot reproduce a chosen speaker's timbre. ControlSpeech combines both. It takes three inputs…
Co-authors here
- Jialong Zuo
- Minghui Fang
- Mingyuan Zhou
- Qian Chen
- Shengpeng Ji
- Siqi Zheng
- Wen Wang
- Xize Cheng
- Zehan Wang
- Zhendong Wang
- Zhou Zhao
- Ziyue Jiang
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/hai-huang/