Xi Xiao

Xi Xiao

I am a third-year Ph.D. student in Computer Science at the University of Alabama at Birmingham, co-advised by Prof. Tianyang Wang and Prof. Min Xu. I'm also a student researcher at Oak Ridge National Laboratory working with Dr. Xiao Wang since May 2025.

Open to research internships, visiting opportunities, and collaborations. If my work aligns with your interests or you just want to say Hi, I'd be delighted to connect:)

Scholar GitHub LinkedIn


Experience

05/2026 - Present
Applied Scientist Intern @ Amazon AGI
Seattle, Washington, USA
Supervised by Dr. Eric Zhao, Dr. Xiang Xu, and Dr. Youngeun Kim on MLLM Reasoning / Understanding.
05/2025 - 05/2026
Research Scientist Intern @ Oak Ridge National Laboratory
Knoxville, Tennessee, USA
Supervised by Dr. Xiao Wang on MLLM post-training and exascale distributed pretraining.

Education

01/2024 - 05/2028
Ph.D. in Computer Science
University of Alabama at Birmingham
Birmingham, Alabama, USA · Expected 2028
09/2019 - 06/2023
Bachelor's Degree in Artificial Intelligence
Sichuan University Jincheng College
Chengdu, Sichuan, China


Research Interest

I have broad interests in Computer Vision and Language Models. Recently, I'm focusing on MLLM Agent and their Reasoning methods.



News

2026
  • [06] Five papers accepted by ECCV 2026!
  • [05] New preprint is out: Agent Harness Engineering: A Survey.
  • [05] Recognized as an ICML 2026 Silver Reviewer.
  • [05] One paper accepted by MICCAI 2026!
  • [05] Join Amazon AGI as an Applied Scientist Intern!
  • [04] One paper accepted by ICML 2026!
  • [04] Two papers accepted by ACL 2026 (one Main conference, one Findings)! See you in San Diego!
  • [03] One paper accepted by ICME 2026!
  • [02] Three papers accepted by CVPR 2026! See you in Denver!
  • [01] One paper accepted by Transactions on Machine Learning Research!
  • [01] Two papers accepted by ICASSP 2026 Oral 🏆!
2025
  • [12] 🎉 Received a Tinker Research Grant ($5,000) from Thinking Machines Lab to support my post-training related research!
  • [11] One paper accepted by SC 2025 — Best Paper Award 🏆 Deeply honored to be the only student author.
  • [11] 🎉 Big News: Our Work Was Featured by AMD! Read the story
  • [11] Two papers accepted by WACV 2026!
  • [11] One paper accepted by AAAI 2026!
  • [09] One paper accepted by NeurIPS 2025! See you in San Diego!
  • [09] One paper accepted by WACV 2026! Round 1 Acceptance (85/1329 ≈ 6.4%)
  • [08] One paper accepted by EMNLP 2025 (Findings)!
  • [07] Our work selected as a finalist for the ACM Gordon Bell Prize 🏆
  • [07] One paper accepted by COLM 2025!
  • [07] One paper accepted by ACM MM 2025!
  • [06] One paper accepted by ICCV 2025!
  • [05] One paper accepted by ECML-PKDD 2025!
  • [05] Join Oak Ridge National Laboratory as a Research Scientist Intern!
2024
  • [12] One paper accepted by ICASSP 2025!
  • [01] Started Ph.D. in Computer Science at the University of Alabama at Birmingham!


Preprints (* indicates equal contribution)

Agent Harness Engineering preprint
Junjie Li*, Xi Xiao*, Yunbei Zhang*, Chen Liu*, Lin Zhao, Xiaoying Liao, Yingrui Ji, Janet Wang, Jianyang Gu, Yingqiang Ge, Weijie Xu, Xi Fang, Xiang Xu, Tianchen Zhao, Youngeun Kim, Tianyang Wang, Jihun Hamm, Smita Krishnaswamy, Jun Huan, Chandan Reddy
Agent Harness Engineering: A Survey
Preprint 2026 [Paper] [Project]
PTQ4SAM3 preprint
Xi Xiao, Yunbei Zhang, Lin Zhao, Janet Wang, Yanshu Li, Chenrui Ma, Pan Wang, Yuqi Li, Fuchen Li, Tianyang Wang, Xiao Wang
PTQ4SAM3: Semantics-Preserving Post-Training Quantization for Segment Anything Model 3
Preprint 2026 [Project]
Work conducted during an internship at ORNL
In collaboration with ORNL
Cascaded Semantics preprint
Xi Xiao, Xingjian Li, Cheng Han, Tianyang Wang, Guosheng Hu, Yunbei Zhang, Lin Zhao, Runmin Jiang, Xi Li, Xiao Wang, Min Xu
Prompting Large-Scale Vision Models with Cascaded Semantics
Preprint 2026 [Paper] [Project]


Selected Publications (see full list here; * indicates equal contribution)

Staying VIGILant preprint
Xi Xiao, Chen Liu, Chih-Ting Liao, Yunbei Zhang, Qizhen Lan, Yuxiang Wei, Lin Zhao, Janet Wang, Jianyang Gu, Muchao Ye, Tianyang Wang, Hao Xu
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
ECCV 2026 [Project]
Layer-specific prompt fusion preprint
Xi Xiao, Xingjian Li, Yunbei Zhang, Cheng Han, Tianming Liu, Tianyang Wang, Runmin Jiang, Jihun Hamm, Xiao Wang, Min Xu
Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
ECCV 2026 [Project]
StructLoRA overview
Xi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu, Yanshu Li, Lin Zhao, Guosheng Hu, Tianyang Wang, Hao Xu
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation
ACL 2026 [Paper] [Project]
Dispersion Loss overview
Chen Liu*, Xingzhi Sun*, Xi Xiao*, Alexandre Van Tassel*, Ke Xu, Kristof Reimann, Danqi Liao, Mark Gerstein, Tianyang Wang, Xiao Wang, Smita Krishnaswamy
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
ICML 2026 [Paper] [Project]
Prompt-based adaptation survey
Xi Xiao, Yunbei Zhang, Lin Zhao, Yiyang Liu, Xiaoying Liao, Zheda Mai, Xingjian Li, Xiao Wang, Hao Xu, Jihun Hamm, Xue Lin, Min Xu, Qifan Wang, Tianyang Wang, Cheng Han
Prompt-based Adaptation in Large-scale Vision Models: A Survey
TMLR 2026 [Paper] [Project]
Visual Instance-aware Prompt Tuning
Xi Xiao, Yunbei Zhang, Xingjian Li, Tianyang Wang, Xiao Wang, Yuxiang Wei, Jihun Hamm, Min Xu
Visual Instance-aware Prompt Tuning
ACM MM 2025 [Paper] [Project]
MagicID project
Hengjia Li*, Lifan Jiang*, Xi Xiao*, Tianyang Wang, Hongwei Yi, Boxi Wu, Deng Cai
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
ICCV 2025 [Paper] [Project]
ORBIT-2 climate foundation model
Xiao Wang, Jong-Youl Choi, Takuya Kurihaya, Isaac Lyngaas, Hong-Jun Yoon, Xi Xiao, David Pugmire, Ming Fan, Nasik M. Nafi, Aristeidis Tsaris, Ashwin M. Aji, Maliha Hossain, Mohamed Wahib, Dali Wang, Peter Thornton, Prasanna Balaprakash, Moetasim Ashfaq, Dan Lu
ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling
SC 2025 [Paper] [Project] [AMD story]
Best Paper Award, Gordon Bell Prize Finalist
Work conducted during an internship at ORNL
In collaboration with ORNL, RIKEN, AMD, and NVIDIA
View Other Publications


Awards & Honors



Miscellanea

Talks & Media

Academic Service

Conference Reviewer
Journal Reviewer
Professional Membership


Visitor Map