14 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…
A: Towards Advertising Aesthetic Assessment
Kaiyuan Ji, Yixuan Gao, Lu Sun +7
Advertising images significantly impact commercial conversion rates and brand equity, yet current evaluation methods rely on subjective judgments, lacking scalability, standardized…
MACEval: A Multi-Agent Continual Evaluation Network for Large Models
Zijian Chen, Yuze Sun, Yuan Tian +2
Hundreds of benchmarks dedicated to evaluating large models have been presented over the past few years. However, most of them remain closed-ended and are prone to overfitting due…
Image Quality Assessment for Embodied AI
Chunyi Li, Jiaohao Xiao, Jianbo Zhang +8
Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories, with various distortions in the Real-world limiting its application. Traditional…
ROFI: A Deep Learning-Based Ophthalmic Sign-Preserving and Reversible Patient Face Anonymizer
Yuan Tian, Min Zhou, Yitong Chen +19
Patient face images provide a convenient mean for evaluating eye diseases, while also raising privacy concerns. Here, we introduce ROFI, a deep learning-based privacy protection fr…
SMC++: Masked Learning of Unsupervised Video Semantic Compression
Yuan Tian, Xiaoyue Ling, Cong Geng +3
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream v…