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.

I am a core contributor to ORBIT-2, an exascale climate foundation model pretrained on the Frontier supercomputer. The work received the Best Paper Award at SC 2025 and is a ACM Gordon Bell Prize finalist. ORBIT-2 has since been integrated into NVIDIA's enterprise climate AI stack, powering large-scale forecasting services that reach millions of users worldwide.

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 xxiao [at] uab (dot) edu

Research Interest

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

Language Model & Pretraining & Post-training: [ICML'26] [CVPR'26] [SC'25]
Efficient Model Adaptation: [ACL'26] [ACL Findings'26] [TMLR'26] [ACM MM'25] [NeurIPS'25] [EMNLP Findings'25]
Efficient-Computer Vision: [CVPR'26] [CVPR'26] [AAAI'26] [ICCV'25] [COLM'25]

News

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 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!

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

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] [Code]

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 [Project] [Paper]

Xi Xiao, Yunbei Zhang, Lin Zhao, Yiyang Liu, et al.
Prompt-based Adaptation in Large-scale Vision Models: A Survey
TMLR 2026 [Paper] [Resources]
A comprehensive survey of visual prompt tuning and prompting for large vision models

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] [Code]

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 [Project] [Paper] [Code]

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] [Code] [AMD story]
Best Paper Award, Gordon Bell Prize Finalist
In collaboration with ORNL, RIKEN, AMD, and NVIDIA

Other Publications

2026

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 (Eric) Zhao, Youngeun Kim, Tianyang Wang, Jihun Hamm, Smita Krishnaswamy, Jun (Luke) Huan, Chandan Reddy

Agent Harness Engineering: A Survey

2026 Paper Code
Mengchen Fan, Baocheng Geng, Xi Xiao, Tianyang Wang, Siyuan Mei, Pulin Che, Xiaoqian Jiang, Qizhen Lan

Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation

MICCAI 2026 Early Accept (Top 9%)
Xi Xiao, Aristeidis Tsaris, Anika Tabassum, John Lagergren, Larry M. York, Tianyang Wang, Xiao Wang

FOCUS: Fused Observation of Channels for Unveiling Spectra

ICME 2026 Paper
Hao Zhang, Zhenjia Li, Runfeng Bao, Xi Xiao, Yifan Gao, Heng Zhang, Shuyang Zhang, Bo Huang, Yuhang Wu, Tianyang Wang, Hao Xu

HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance

ACL Findings 2026 Paper
Yuxiang Wei, Yanteng Zhang, Xi Xiao, Chengxuan Qian, Tianyang Wang, Vince D. Calhoun

fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding

CVPR 2026 Paper Code
Chenrui Ma, Xi Xiao, Tianyang Wang, Xiao Wang, Yanning Shen

Learning Straight Flows: Variational Flow Matching for Efficient Generation

CVPR 2026 Paper
Lin Zhao, Xinru Jiang, Xi Xiao, Qihui Fan, Lei Lu, Yanzhi Wang, Xue Lin, Octavia Camps, Pu Zhao, Jianyang Gu

HIERAMP: Coarse-to-Fine Autoregressive Amplification for Generative Dataset Distillation

CVPR 2026 Paper
Yu Li, Da Chang, Xi Xiao

KG-SAM: Injecting Anatomical Knowledge into Segment Anything Models via Conditional Random Fields

ICASSP 2026 Oral Paper
Zhuxuanzi Wang, Mingqiao Mo, Xi Xiao, Chen Liu, Chenrui Ma, Yunbei Zhang, Xiao Wang, Smita Krishnaswamy, Tianyang Wang

CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models

ICASSP 2026 Oral Paper
Chenrui Ma, Xi Xiao, Tianyang Wang, Xiao Wang, Yanning Shen

CAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement

AAAI 2026 Paper Code
Xi Xiao, Yunbei Zhang, Janet Wang, Lin Zhao, Yuxiang Wei, Hengjia Li, Yanshu Li, Xiao Wang, Swalpa Kumar Roy, Hao Xu, Tianyang Wang

RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding

WACV 2026 Paper
Xi Xiao, Zhuxuanzi Wang, Mingqiao Mo, Chen Liu, Chenrui Ma, Yanshu Li, Smita Krishnaswamy, Xiao Wang, Tianyang Wang

Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection

WACV 2026 Paper Code
Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, Vince D. Calhoun

4D Multimodal Co-Attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis

WACV 2026 Paper
Aokun Liang, Xi Xiao, Xiangyun Hu, Tao Ke, Tianyang Wang, Yibing Xiong, Huiwei Jiang, Xiao Wang

GeoPriorCLIP: A Foundational Remote Sensing Vision-Language Model Enhanced with Cascaded Geographic Information Priors

Geo-spatial Information Science Paper
Shunlei Li, Longsen Gao, Jin Wang, Chang Che, Xi Xiao, Jiuwen Cao, Yingbai Hu, Hamid Reza Karimi

Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control

Information Fusion Paper
Chenshen Huang*, Haoyun Xia*, Xi Xiao*, Hong Chen, Yiqing Jiang, Yahui Lyu, Zhizhan Ni, Tianyang Wang, Ning Wang, Qi Huang

Geometric Multi-Instance Learning for Weakly Supervised Gastric Cancer Segmentation

npj Digital Medicine Paper

2025

Yuxiang Wei, Yanteng Zhang, Xi Xiao, Tianyang Wang, Xiao Wang, Vince D. Calhoun

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

NeurIPS 2025 Paper Code
Hao Zhang, Bo Huang, Zhenjia Li, Xi Xiao, Hui Yi Leong, Zumeng Zhang, Xinwei Long, Tianyang Wang, Hao Xu

Sensitivity-LoRA: Low-Load Sensitivity-Based Fine-Tuning for Large Language Models

EMNLP Findings 2025 Paper
Xi Xiao, Zhengji Li, Wentao Wang, Jiacheng Xie, Houjie Lin, Swalpa Kumar Roy, Tianyang Wang, Min Xu

TD-RD: A Top-Down Benchmark with Real-Time Framework for Road Damage Detection

ICASSP 2025 Paper
Yanshu Li, Yi Cao, Hongyang He, Qisen Cheng, Xiang Fu, Xi Xiao, Tianyang Wang, Ruixiang Tang

M²IV: Towards Efficient and Fine-Grained Multimodal In-Context Learning via Representation Engineering

COLM 2025 Paper
Xi Xiao, Yunbei Zhang, Thanh-Huy Nguyen, Ba-Thinh Lam, Janet Wang, Lin Zhao, Jihun Hamm, Tianyang Wang, Xingjian Li, Xiao Wang, Hao Xu, Tianming Liu, Min Xu

Describe Anything in Medical Images

ICML 2025 Workshop on FM4LS Paper
Xi Xiao, Yunbei Zhang, Yanshu Li, Xingjian Li, Tianyang Wang, Jihun Hamm, Xiao Wang, Min Xu

Visual Variational Autoencoder Prompt Tuning

CVPR 2025 Workshop on FGVC Paper

Education

Ph.D. in Computer Science, University of Alabama at Birmingham
01/2024 – 05/2028 (Expected)
Birmingham, Alabama, USA

Bachelor’s Degree in Artificial Intelligence, Sichuan University Jincheng College
09/2019 – 06/2023
Chengdu, Sichuan, China

Experience

Applied Scientist Intern, Amazon (AWS AI Labs)
05/2026 – Present
Seattle, Washington, USA
Supervised by Dr. Eric Zhao and Dr. Youngeun Kim on MLLM Reasoning / Understanding.

Research Scientist Intern, Oak Ridge National Laboratory
05/2025 – 05/2026
Knoxville, Tennessee, USA
Supervised by Dr. Xiao Wang on MLLM's post-training, and exascale distributed pretraining.

Awards & Honors

[2026] ICML 2026 Silver Reviewer.
[2025] Best Paper Award, SC 2025 for ORBIT-2: Scaling Exascale Vision Foundation Models for Weather and Climate Downscaling.
[2025] Finalist, ACM Gordon Bell Prize (team award) for exascale climate foundation modeling on Frontier.
[2025] Tinker Research Grant ($5,000) from Thinking Machines Lab to support research on efficient post-training of large-scale models.

Miscellanea

Talks & Media

AMD story on ORBIT-2 and Frontier exascale climate modeling
UAB News: UAB students' research wins Best Paper Award at an international computing conference
More invited talks and interviews coming soon.

Academic Service

Reviewer for MICCAI 2026, ICML 2026, CVPR 2026, ECCV 2026, AAAI 2026, NeurIPS 2025, ACM MM 2025, TMLR, IEEE TCSVT, IEEE TMM, IEEE TSMCA, npj Digital Medicine, MSSP.