4 papers
CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment
Jiayue Cao, Zhicong Lu, Xuehan Sun +6
Reinforcement learning with verifiable rewards (RLVR) has successfully elicited the reasoning capabilities of large language models, motivating its extension to multimodal scenario…
CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models
Shuhan Xu, Siyuan Liang, Hongling Zheng +4
Diffusion-based image-to-video (I2V) models increasingly exhibit world-model-like properties by implicitly capturing temporal dynamics. However, existing studies have mainly focuse…
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
Shuhan Xu, Siyuan Liang, Hongling Zheng +6
Visual language models (VLMs) have made significant progress in image captioning tasks, yet recent studies have found they are vulnerable to backdoor attacks. Attackers can inject…
Learning from models beyond fine-tuning
Hongling Zheng, Li Shen, Anke Tang +5
Foundation models (FM) have demonstrated remarkable performance across a wide range of tasks (especially in the fields of natural language processing and computer vision), primaril…