CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation

Chaoyu Li, Deeparghya Dutta Barua, Fei Tao, Pooyan Fazli

arXiv

FrameOracle: Learning What to See and How Much to See in Videos

Chaoyu Li, Tianzhi Li, Fei Tao, Zhenyu Zhao, Ziqian Wu, Maozheng Zhao,

Juntong Song, Cheng Niu, Pooyan Fazli

International Conference on Machine Learning (ICML) , 2026

arXiv

ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs

Chaoyu Li, Yogesh Kulkarni, Pooyan Fazli

Annual Meeting of the Association for Computational Linguistics (ACL) , 2026

arXiv

VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models
for Video Understanding

Chaoyu Li, Eun Woo Im, Pooyan Fazli

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

arXiv Project

VideoA11y: Method and Dataset for Accessible Video Description

Chaoyu Li, Sid Padmanabhuni, Maryam S Cheema, Hasti Seifi, Pooyan Fazli

ACM SIGCHI Conference on Human Factors in Computing Systems (CHI) , 2025

arXiv Project

Infrared Action Detection in the Dark via Cross-Stream Attention Mechanism

Xu Chen*, Chenqiang Gao*, Chaoyu Li, Yi Yang, Deyu Meng

IEEE Transactions on Multimedia (TMM) , 2021

PDF

NTT CQUPT@TRECVID2019 ActEV: Activities in Extended Video

Yongqing Sun, Xu Chen, Chaoyu Li et al.

TREC Video Retrieval Evaluation (TRECVID), 2019

PDF

Face Anti-Spoofing Based on Multi-layer Domain Adaptation

Fengshun Zhou*, Chenqiang Gao*, Fang Chen, Chaoyu Li, Xindou Li, Feng Yang, Yue Zhao

IEEE International Conference on Multimedia & Expo Workshops (ICMEW) , 2019

PDF