17 papers
Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating
Sicheng Wang, Xiangyang Zhu, Han Wang +6
Prior work has shown that fine-tuning large language models on malicious or incorrect outputs in narrow domains can induce broad misalignment and harmful behavior, a phenomenon kno…
Generalizable Video Quality Assessment via Weak-to-Strong Learning
Linhan Cao, Wei Sun, Xiangyang Zhu +6
Video quality assessment (VQA) seeks to predict the perceptual quality of a video in alignment with human visual perception, serving as a fundamental tool for quantifying quality d…
VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning
Linhan Cao, Wei Sun, Weixia Zhang +6
Video quality assessment (VQA) aims to objectively quantify perceptual quality degradation in alignment with human visual perception. Despite recent advances, existing VQA models s…
QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding
Linhan Cao, Wei Sun, Weixia Zhang +6
Visual quality assessment (VQA) is increasingly shifting from scalar score prediction toward interpretable quality understanding -- a paradigm that demands \textit{fine-grained spa…
ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
Zitong Xu, Huiyu Duan, Xiaoyu Wang +6
With the rapid advancement of generative models, powerful image editing methods now enable diverse and highly realistic image manipulations that far surpass traditional deepfake te…
KidVis: Do Multimodal Large Language Models Possess the Visual Perceptual Capabilities of a 6-Year-Old?
Xianfeng Wang, Kaiwei Zhang, Qi Jia +3
While Multimodal Large Language Models (MLLMs) have demonstrated impressive proficiency in high-level reasoning tasks, such as complex diagrammatic interpretation, it remains an op…