Xi Xiao

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'26a] [SC'25]
• Efficient Model Adaptation: [ACL'26] [ACL Findings'26] [TMLR'26] [ACM MM'25] [NeurIPS'25] [EMNLP Findings'25]
• Efficient-Computer Vision: [CVPR'26b] [CVPR'26c] [AAAI'26] [ICCV'25] [COLM'25]

News

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

Xi Xiao, Yunbei Zhang, Chen Liu, Lin Zhao, Jialin Chen, Tianchen Zhao, Xiang Xu, Smita Krishnaswamy, Tianyang Wang, Min Xu
FORGE: Form-Optimal Routing of Grounded Evidence for Frozen Language Agents
Preprint 2026 [Project]

---

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]

---

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
Preprint 2026 [Project]

---

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
Preprint 2026 [Project]

---

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

---

Xi Xiao, Xingjian Li, Cheng Han, Tianyang Wang, Guosheng Hu, Yunbei Zhang, Lin Zhao, Runmin Jiang, Xi Li, Xiao Wang, Min Xu
Prompting Vision Foundation Models with Cascaded Semantics
Preprint 2026 [Project]

---

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]

---

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]

---

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]

---

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]

---

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]

---

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

---

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