Daiqing Qi

PhD Candidate, University of Virginia
Email: daiqing98 [at] gmail.com
Daiqing Qi

I am currently a PhD student at the University of Virginia, advised by Dr. Sheng Li. I work on Multimodal Intelligence. Specifically, I am interested in:

  • Visual understanding and reasoning with MLLMs (post-training, test-time scaling)
  • Vision–Language alignment (VLMs, MLLMs)
  • Multimodal LLM agents
I am also interested in applications of Generative AI and co-organized workshops on GenAI for Photography and Education at WACV'26 and NeurIPS'24.
News: I'm currently seeking full-time industry opportunities. Feel free to reach out if you're interested.

Experience

Selected Publications

Daiqing Qi et al., Improve Temporal Reasoning in MLLMs via Video Contrastive Decoding Neural Information Processing Systems (NeurIPS) 2025
Daiqing Qi et al., The Photographer's Eye: Teach MLLMs to See and Critique like Photographers IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025
Daiqing Qi et al., Easy Regional Contrastive Learning of Expressive Fashion Representations Neural Information Processing Systems (NeurIPS) 2024
Daiqing Qi et al., Generalizing (CLIP) to Unseen Domains via Text-guided Augmentation European Conference on Computer Vision (ECCV) 2024
Daiqing Qi et al., Tag-grounded Visual Instruction Tuning with Retrieval Augmentation Empirical Methods in Natural Language Processing, Main Track (EMNLP) 2024
Daiqing Qi et al., Revealing an Overlooked Challenge in Class-Incremental Graph Learning Transactions on Machine Learning Research (TMLR) 2024
Daiqing Qi et al., Better Generative Replay for Continual Federated Learning International Conference on Learning Representations (ICLR) 2023

Recipient

NeurIPS Scholar Award, 2025
ICLR Notable Reviewer, 2025

Organized Workshops

GenAI for Photography
The First Workshop on Generative AI for Photography
WACV 2026
Website
Educational Assessment Workshop
The First Workshop on Large Foundation Models for Educational Assessment
NeurIPS 2024
Website

Selected Publications

Full publications on Google Scholar
Improve Temporal Reasoning in MLLMs via Video Contrastive Decoding
Daiqing Qi, D Guo, H Yuan, H Zhao, M Hu, L Yang, S Li
NeurIPS 2025
PaperCode
The Photographer's Eye: Teach MLLMs to See and Critique like Photographers
Daiqing Qi, H Zhao, J Shi, S Jenni, Y Fan, F Dernoncourt, S Cohen, S Li
CVPR 2025
PaperCode
Easy Regional Contrastive Learning of Expressive Fashion Representations
Daiqing Qi, H Zhao, S Li
NeurIPS 2024
PaperCode
Generalizing (CLIP) to Unseen Domains via Text-guided Augmentation
Daiqing Qi, H Zhao, A Zhang, S Li
ECCV 2024
PaperCode
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation
Daiqing Qi, H Zhao, Z Wei, S Li
EMNLP 2024 (Main Track)
PaperCode
Revealing an Overlooked Challenge in Class-Incremental Graph Learning
Daiqing Qi, H Zhao, X Jia, S Li
TMLR 2024 (Transactions on Machine Learning Research)
Paper
Better Generative Replay for Continual Federated Learning
Daiqing Qi, H Zhao, S Li
ICLR 2023
PaperCode
VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
L Yang, J Song, T Wang, Daiqing Qi, W Shi, Y Liu, S Li
arXiv 2025
Paper
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
M Hu, H Wu, Z Guan, R Zhu, D Guo, Daiqing Qi, S Li
EMNLP 2025 (Findings Track)
Paper

Organization of Workshops, Surveys and Tutorials

The First Workshop on Generative AI for Photography
I-Sheng Fang, Daiqing Qi, Yu Yuan, Kuan-Chuan Peng, Jun-Cheng Chen
WACV 2026 (Workshop Organization)
Website
The First Workshop on Large Foundation Models for Educational Assessment
Sheng Li, Dongliang Guo, Daiqing Qi, Zhongmin Cui, Jiasen Lu, Deborah Harris, Shumin Jing
NeurIPS 2024 (Workshop Organization)
Website
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Yunlong Tang, Jing Bi, ..., Daiqing Qi, ..., Chenliang Xu
arXiv 2025
PaperGithub
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye, Luyang Jiang, ..., Daiqing Qi, ..., Aidong Zhang
TMLR 2025
Paper
A Survey of Trustworthy Representation Learning across Domains
Ronghang Zhu, Dongliang Guo, Daiqing Qi, Zhixuan Chu, Xiang Yu, Sheng Li
TKDD 2024
Paper

Service

Organizer / Program Chair:
WACV 2026 Workshop on Generative AI for Photography
NeurIPS 2024 Workshop on Large Foundation Models for Educational Assessment
Reviewer / PC Member:
Neural Information Processing Systems (NeurIPS)
International Conference on Learning Representations (ICLR)
International Conference on Machine Learning (ICML)
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
European Conference on Computer Vision (ECCV)
Transactions on Machine Learning Research (TMLR)

Teaching

DS 4002: Data Science Project Course (Spring 2023)
CS 5012: Foundations of Computer Science (Fall 2022)

Misc

I am interested in photography. Some of them are available here. I used to play the Auto Battler game and was among top 100 (ranked #52) best players nationwide.
Links:
The Americans - Jack Kerouac
Manifesto of Surrealism - Andre Breton
More is Different - P.W. Anderson
A Journey to the End of the World (of Minecraft)
Mon Amour, Mon Amour..., from Museum by Elyon. Most of the beats are Nujabes and Premier influence