activity
20242026
collaborators

14 papers

cs.CL2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.CV2025

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…