13 citations · 15 across the 10 of their papers we have counts for
11 papers
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
Lehan Yang, Daiqing Qi, Wenhao Zhang +9
Representation alignment (REPA) accelerates diffusion transformer training, but its alignment targets are almost exclusively semantic encoders such as DINOv2 and CLIP. Recent analy…
HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding
Yiqing Yang, Yun Li, Daiqing Qi +5
Key frame selection is essentially a set-level optimization problem: the quality of the selected subset depends on the interactions among frames, rather than the score of any singl…
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
Yolo Y. Tang, Jing Bi, Pinxin Liu +24
Video understanding represents the most challenging frontier in computer vision, requiring models to reason about complex spatiotemporal relationships, long-term dependencies, and…
The Photographer Eye: Teaching Multimodal Large Language Models to Understand Image Aesthetics like Photographers
Daiqing Qi, Handong Zhao, Jing Shi +5
While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky. Photographer and curator, Szarkowski insightfully revea…
ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
Yu Zhang, Yunqi Li, Yifan Yang +7
Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We intr…
VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
Lehan Yang, Jincen Song, Tianlong Wang +4
We propose a new task, video referring matting, which obtains the alpha matte of a specified instance by inputting a referring caption. We treat the dense prediction task of mattin…
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan +4
Retrieval-Augmented Generation (RAG) is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations and enhancing the domain-specific generation capabilit…
Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags
Daiqing Qi, Handong Zhao, Zijun Wei +1
Despite recent advances in the general visual instruction-following ability of Multimodal Large Language Models (MLLMs), they still struggle with critical problems when required to…
Trustworthy Representation Learning Across Domains
Ronghang Zhu, Dongliang Guo, Daiqing Qi +3
As AI systems have obtained significant performance to be deployed widely in our daily live and human society, people both enjoy the benefits brought by these technologies and suff…
Better Generative Replay for Continual Federated Learning
Daiqing Qi, Handong Zhao, Sheng Li
Federated learning is a technique that enables a centralized server to learn from distributed clients via communications without accessing the client local data. However, existing…
Less is More: Data-Efficient Complex Question Answering over Knowledge Bases
Yuncheng Hua, Yuan-Fang Li, Guilin Qi +3
Question answering is an effective method for obtaining information from knowledge bases (KB). In this paper, we propose the Neural-Symbolic Complex Question Answering (NS-CQA) mod…