Daiqing Qi @ Microsoft

Daiqing Qi

I am building Copilot at Microsoft. I am broadly interested in multimodal foundation models (MLLMs, VLMs) and LLM agents.

Previously, I received my PhD from UVA, working with Dr. Sheng Li. I also spent time at Adobe Research and Amazon. I co-organized workshops on Generative AI for Photography and Educational Assessment at WACV'26 and NeurIPS'24.

I am interested in photography. See selected photographs and earlier work.

Scholar LinkedIn Twitter Portfolio Microsoft Research

Publications

Full list on Publications and 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
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
PaperCode
Easy Regional Contrastive Learning of Expressive Fashion Representations
Daiqing Qi, H Zhao, S Li
PaperCode
Generalizing (CLIP) to Unseen Domains via Text-guided Augmentation
Daiqing Qi, H Zhao, A Zhang, S Li
PaperCode
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation
Daiqing Qi, H Zhao, Z Wei, S Li
PaperCode
Revealing an Overlooked Challenge in Class-Incremental Graph Learning
Daiqing Qi, H Zhao, X Jia, S Li
PaperCode
Better Generative Replay for Continual Federated Learning
Daiqing Qi, H Zhao, S Li
PaperCode

Recipient

ICML Gold Reviewer Award2026 NeurIPS Scholar Award2025 ICLR Notable Reviewer Award2025

Work Experience

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

Connect

Feel free to reach me at daiqing98@gmail.com.

Publications

Full publications on Google Scholar

2026

PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
L Yang, Daiqing Qi, W Zhang, A Li, Y Yang, Y Li, Y Kong, H Zheng, Z Zhang, Z Lin, V Jampani, S Li
VITAL: Visual-Text Invariance Tests for Text-Prior Reliance in Multimodal Language Models
P Wang, Daiqing Qi, T Wang, W Zhang, L Yang, S Li
Adaptive Content-Contrastive Decoding for Tabular Language Models
H Yuan, M Hu, Daiqing Qi, V Datla, A Samuel, S Li
HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding
Y Yang, Y Li, Daiqing Qi, L Yang, T Wang, W Zhang, S Li, K Lam
Paper

2025

Improve Temporal Reasoning in MLLMs via Video Contrastive Decoding
Daiqing Qi, D Guo, H Yuan, H Zhao, M Hu, L Yang, S Li
PaperCode
VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
L Yang, J Song, T Wang, Daiqing Qi, W Shi, Y Liu, S Li
Paper
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
PaperCode
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
Paper
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Yunlong Tang, Jing Bi, ..., Daiqing Qi, ..., Chenliang Xu
PaperGithub
The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning
Wenqian Ye, Luyang Jiang, ..., Daiqing Qi, ..., Aidong Zhang
Paper

2024

Easy Regional Contrastive Learning of Expressive Fashion Representations
Daiqing Qi, H Zhao, S Li
PaperCode
Generalizing (CLIP) to Unseen Domains via Text-guided Augmentation
Daiqing Qi, H Zhao, A Zhang, S Li
PaperCode
Tag-grounded Visual Instruction Tuning with Retrieval Augmentation
Daiqing Qi, H Zhao, Z Wei, S Li
PaperCode
Revealing an Overlooked Challenge in Class-Incremental Graph Learning
Daiqing Qi, H Zhao, X Jia, S Li
Paper
A Survey of Trustworthy Representation Learning across Domains
Ronghang Zhu, Dongliang Guo, Daiqing Qi, Zhixuan Chu, Xiang Yu, Sheng Li
Paper

2023

Better Generative Replay for Continual Federated Learning
Daiqing Qi, H Zhao, S Li
PaperCode

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 used to play the Auto Battler game and was ranked #52 among the top 100 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