Hi, I'm Haotian Sun.
I'm a fourth-year Ph.D. student in Machine Learning at Georgia Institute of Technology, co-advised by Dr. Bo Dai and Dr. Chao Zhang. I am also fortunate to work closely with Dr. Nan Du as a research intern at Apple.
My research focuses on large-scale multi-modal foundation models, with a core emphasis on building scalable, adaptive, and highly personalized generative systems. I also work on LLM adaptation for black-box models and agentic planning.
I've had the privilege of collaborating with researchers at
Apple,
Georgia Tech,
CentraleSupélec,
and 
Xi'an Jiaotong University.
News
- Sep 2025 AmorLIP accepted to NeurIPS 2025.
- Sep 2025 Matryoshka Pilot accepted to NeurIPS 2025 (co-author).
- May 2025 Started my second research internship at Apple, Foundation Model Team, working on unified multi-modal diffusion.
- Jan 2025 EC-DIT accepted to ICLR 2025.
- Jan 2025 Spectral Representation for Causal Estimation accepted to AISTATS 2025.
- May 2024 Started my first research internship at Apple, Foundation Model Team, advised by Dr. Nan Du.
- May 2024 BBox-Adapter accepted to ICML 2024 as a Spotlight (top 3.5%).
Featured Publications
AmorLIP: Efficient Language-Image Pretraining via Amortization
, Yitong Li , Yuchen Zhuang , Niao He , Hanjun Dai , Bo Dai
Accepted at NeurIPS'25
Vision-language pretraining, CLIP, Amortized inference
EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing
, Tao Lei , Bowen Zhang , Yanghao Li , Haoshuo Huang , Ruoming Pang , Bo Dai , Nan Du
Accepted at ICLR'25
MoE, Diffusion, Text-to-image synthesis
HYDRA: Model Factorization Framework for Black-Box LLM Personalization
Yuchen Zhuang , , Yue Yu , Rushi Qiang , Qifan Wang , Chao Zhang , Bo Dai
Accepted at NeurIPS'24
Black-box LLMs, Personalization, Recommendation
BBox-Adapter: Lightweight Adapting for Black-Box Large Language Models
, Yuchen Zhuang* , Wei Wei , Chao Zhang , Bo Dai
Accepted at ICML'24 (Spotlight, top 3.5%)
Black-box LLMs, Adaptation, Plug-and-play
AdaPlanner: Adaptive Planning from Feedback with Language Models
, Yuchen Zhuang* , Lingkai Kong , Bo Dai , Chao Zhang
Accepted at NeurIPS'23
Closed-loop adaptive planning, LLM agent, Code interface, Skill discovery
ToolQA: A Dataset for LLM Question Answering with External Tools
Yuchen Zhuang , Yue Yu , Kuan Wang , , Chao Zhang
Accepted at NeurIPS'23 (Datasets and Benchmarks Track)
LLM evaluation, Dataset curation, Tool use