Scholar
Xiaoke Huang
Google Scholar ID: BD9AT04AAAAJ
University of California, Santa Cruz
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
334
H-index
8
i10-index
7
Publications
14
Co-authors
35
list available
Contact
Email
xhuan192@ucsc.edu
CV
Open ↗
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
10 items
VecGlypher: Unified Vector Glyph Generation with Language Models
2026
Cited
0
OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory
2025
Cited
0
Scaling Zero-Shot Reference-to-Video Generation
2025
Cited
0
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
2025
Cited
0
MedVLSynther: Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs
2025
Cited
0
Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
2025
Cited
0
MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
2025
Cited
0
Knowledge or Reasoning? A Close Look at How LLMs Think Across Domains
2025
Cited
0
Load more
Resume (English only)
Academic Achievements
CVPR 2024: 'Segment and Caption Anything' (enhancing SAM with regional captioning)
NeurIPS 2022: 'OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression'
CVPR 2021: Paper on uncertainty-aware ordinal regression
IEEE TMM 2023: 'SD-NeRF: Lifelike Talking Head Animation via Spatially-adaptive Dual-driven NeRFs'
2023 Preprint: 'EMA: Efficient Meshy Neural Fields for Animatable Human Avatars'
Multiple preprints on multimodal medical reasoning accepted by ML4H’25
CVPR 2025 paper on visual compression with LLMs, featured in Hugging Face Daily Papers
ACM-ICPC Jiangsu Provincial Silver Medal (2018)
ICPC Asia Regional Bronze Medals (Nanchang, Xuzhou, Shanghai, 2019)
Background
Ph.D. student at the University of California, Santa Cruz (UCSC)
Research focuses on multimodal and reasoning models, media generation, and AI for healthcare
Interested in building scalable environments for agentic learning
Master's research involved vision–language learning and 3D reconstruction/generation of digital humans
Bachelor's degree from Beijing Normal University
Co-authors
35 total
Jiwen Lu (鲁继文)
Professor, Department of Automation, Tsinghua University
Yansong Tang (唐彦嵩)
Associate Professor, Tsinghua University
Wanhua Li
Harvard University
Yuyin Zhou
Assistant Professor, Computer Science and Engineering, Genomics Institute, UC Santa Cruz
Zheng Zhu (朱政)
Co-founder & Chief Scientist of GigaAI
Juncheng Wu
University of California, Santa Cruz
Xubing Ye
Tsinghua University
Yixiao Ge (葛艺潇)
XPENG Robotics
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up