hkchengrex.com

Rex Cheng's personal site, hkchengrex.com, is the central hub for his research output. From the homepage you can reach his GitHub, Google Scholar, and CV directly, and every listed paper links out to a project page, code repository, and arXiv preprint. If you want his papers, open-source implementations, or academic record, start there rather than searching each platform separately.

Who Rex Cheng is

Ho Kei (Rex) Cheng is a research scientist at Luma AI, working on multimodal foundation models. He completed his PhD at the University of Illinois Urbana-Champaign, advised by Alexander Schwing. During his PhD he interned at Adobe Research, Kaiber, Sony AI, and Meta FAIR/MSL. Before that he studied at The Hong Kong University of Science and Technology, advised by Yu-Wing Tai and Chi Keung Tang.

Links available from the homepage

The site's top-level navigation points to three profiles:

• GitHub — source code for his projects
• Google Scholar — publication list and citation record
• CV — full academic and industry history

These are the fastest routes to his code and publication record. The research entries below them repeat the same destinations at the paper level.

Research entries and where each one leads

Each selected research item on the page carries its own set of links. The pattern is consistent: a project page, a code repository, and an arXiv preprint, with some entries adding a demo.

How to use these links

• For the paper text: follow the arXiv link on the specific entry. That gives you the preprint version.
• For the implementation: follow the code link, which points to the GitHub repository for that project.
• For a quick trial without setup: MMAudio additionally lists a Space demo and a Replicate endpoint, so you can run it without cloning anything.
• For citation counts and the full publication list: use the Google Scholar link at the top of the page.
• For background and affiliation history: use the CV link.

One practical note: the page groups links per paper rather than in a single index, so if you are looking for a specific project, scan the research section for its title first, then take the link you need from that row.

Rex Cheng (Ho Kei Cheng) is a research scientist at Luma AI working on multimodal foundation models. His background combines a PhD at the University of Illinois Urbana-Champaign, earlier study at The Hong Kong University of Science and Technology, and research internships at Adobe Research, Kaiber, Sony AI, and Meta FAIR/MSL.

Current role

• Research scientist at Luma AI, working on multimodal foundation models.

Education

Industry research internships

During his PhD, he interned at:

• Adobe Research
• Kaiber
• Sony AI
• Meta FAIR/MSL

Research output

His site lists selected research with links to project pages, code, and arXiv papers, including:

• SAM 3: Segment Anything with Concepts (ICLR 2026) — a unified model for detection, segmentation, and tracking of objects in images and video using text, exemplar, and visual prompts.
• The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation (ICCV 2025) — condition-aware coupling of prior and data samples for straighter flows.
• MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis (CVPR 2025) — synchronized audio generation from video or text.
• Putting the Object Back into Video Object Segmentation (CVPR 2024 Highlight) — an object transformer combining pixel-level and object-level features.

The site also links to his GitHub, Google Scholar, and CV for further detail.

hkchengrex.com is the personal academic homepage of Ho Kei (Rex) Cheng, a research scientist at Luma AI. The site is a single-page profile that lists his current role, education, industry internships, and selected research publications, with links out to his GitHub, Google Scholar, and CV. It is a portfolio-style research page rather than a blog, product, or company site.

Who is Rex Cheng?

Rex Cheng is a computer vision and machine learning researcher. According to his homepage:

• Current role: Research scientist at Luma AI, working on multimodal foundation models.
• PhD: University of Illinois Urbana-Champaign, advised by Alexander Schwing.
• Internships during his PhD: Adobe Research, Kaiber, Sony AI, and Meta FAIR/MSL.
• Earlier education: The Hong Kong University of Science and Technology, advised by Yu-Wing Tai and Chi Keung Tang.

The page also links to his GitHub, Google Scholar profile, and CV, which are the main places to go for code, citation metrics, and a full publication list.

What research is featured on the site?

The homepage highlights a selection of papers, each with a project page, code, and arXiv link where available. The featured work spans segmentation, video object segmentation, generative modeling, and video-to-audio synthesis.

Several entries include embedded videos that play on hover, plus links to project pages, code repositories, arXiv preprints, and in the MMAudio case a Space demo and Replicate deployment.

When is this site useful to you?

• If you are researching a specific method (for example, video object segmentation or video-to-audio synthesis), the site is a fast index into project pages and code repositories.
• If you want to follow Rex Cheng's work, the Google Scholar and GitHub links are the better long-term sources, since the homepage only shows selected research.
• If you need his professional background for a talk introduction, collaboration inquiry, or citation context, the education and internship history above is the relevant part.

The site does not list pricing, services, or contact details beyond the external profile links, so it is not a commercial or support resource.

hkchengrex.com is the personal academic site of Ho Kei (Rex) Cheng, a research scientist at Luma AI working on multimodal foundation models. The site's "Selected Research" section lists his representative papers, each with links to a project page, code, and arXiv preprint where available. The work clusters around computer vision and generative modeling: segmentation and tracking in images and video, video-to-audio synthesis, and flow-based generation.

Research areas covered

The featured papers fall into three broad themes:

• Segmentation and tracking — unified models for detecting, segmenting, and tracking objects across images and video, using text, exemplar, and visual prompts.
• Video-to-audio synthesis — generating synchronized audio from video or text inputs.
• Generative modeling and optimal transport — improving conditional flow-based generation through better coupling of prior and data distributions.

Featured papers

Each entry links to a project page, code repository, and arXiv paper; MMAudio additionally links a Space demo and Replicate.

Background and affiliations

Cheng is currently a research scientist at Luma AI. He completed his PhD at the University of Illinois Urbana-Champaign, advised by Alexander Schwing, and interned at Adobe Research, Kaiber, Sony AI, and Meta FAIR/MSL. He was previously at The Hong Kong University of Science and Technology, advised by Yu-Wing Tai and Chi Keung Tang. The site links to his GitHub, Google Scholar, and CV.

How to use the site

If you want to follow a specific line of work, start from the paper entry and use its code or project page link rather than searching elsewhere — the site groups the canonical links for each project in one place. For current affiliation or publication updates, the CV and Google Scholar links are the most reliable starting points.