activity
20242026
most citedEfficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2026

ARGaze: Autoregressive Transformers for Online Egocentric Gaze Estimation

Jia Li, Wenjie Zhao, Shijian Deng +6

Online egocentric gaze estimation predicts where a camera wearer is looking from first-person video using only past and current frames, a task essential for augmented reality and a…

cs.CV2025

Explainable AI-Generated Image Detection RewardBench

Michael Yang, Shijian Deng, William T. Doan +4

Conventional, classification-based AI-generated image detection methods cannot explain why an image is considered real or AI-generated in a way a human expert would, which reduces…

cs.CV2025

Toward Gaze Target Detection of Young Autistic Children

Shijian Deng, Erin E. Kosloski, Siva Sai Nagender Vasireddy +6

The automatic detection of gaze targets in autistic children through artificial intelligence can be impactful, especially for those who lack access to a sufficient number of profes…

cs.CL2025

Self-Improvement in Multimodal Large Language Models: A Survey

Shijian Deng, Kai Wang, Tianyu Yang +2

Recent advancements in self-improvement for Large Language Models (LLMs) have efficiently enhanced model capabilities without significantly increasing costs, particularly in terms…

cs.CL20241 cited

Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach

Shijian Deng, Wentian Zhao, Yu-Jhe Li +4

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themsel…

cs.CV2024

Continual Audio-Visual Sound Separation

Weiguo Pian, Yiyang Nan, Shijian Deng +3

In this paper, we introduce a novel continual audio-visual sound separation task, aiming to continuously separate sound sources for new classes while preserving performance on prev…