8 papers
PaQ-DETR: Learning Pattern and Quality-Aware Dynamic Queries for Object Detection
Zhengjian Kang, Jun Zhuang, Kangtong Mo +3
Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still…
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…
Dual-R-DETR: Resolving Query Competition with Pairwise Routing in Transformer Decoders
Ye Zhang, Qi Chen, Wenyou Huang +2
Detection Transformers (DETR) formulate object detection as a set prediction problem and enable end-to-end training without post-processing. However, object queries in DETR interac…
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulation
Jun Zhuang, Haibo Jin, Ye Zhang +4
Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work…
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…
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…