5 papers
MISO: Model-Internal-State-Guided Optimization for Ranking Models
Yongzhe Zhang, Xiaoyu Deng, Yifan He +28
Ranking models are repeatedly refined within established model families, yet the choice of which component to scale, replace, or retire is often guided by expensive trial-and-error…
V-CORE: Temporally Consistent Video Understanding for Video-LLM
Zhengjian Kang, Qi Chen, Rui Liu +4
Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temp…
LP-DETR: Layer-wise Progressive Relations for Object Detection
Zhengjian Kang, Ye Zhang, Xiaoyu Deng +2
This paper presents LP-DETR (Layer-wise Progressive DETR), a novel approach that enhances DETR-based object detection through multi-scale relation modeling. Our method introduces l…
ChallengeMe: An Adversarial Learning-enabled Text Summarization Framework
Xiaoyu Deng, Ye Zhang, Tianmin Guo +3
The astonishing performance of large language models (LLMs) and their remarkable achievements in production and daily life have led to their widespread application in collaborative…
CoVis: A Collaborative Framework for Fine-grained Graphic Visual Understanding
Xiaoyu Deng, Zhengjian Kang, Xintao Li +2
Graphic visual content helps in promoting information communication and inspiration divergence. However, the interpretation of visual content currently relies mainly on humans' per…