7 papers
Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation
Zhe Li, Honghao Qiao, Zhixin Xu +3
RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, g…
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
Zichuan Wang, Songlin Yang, Bo Peng +4
Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image. Prior work largely attributes this to insufficient v…
DREAM: A Benchmark Study for Deepfake photoREalism AssessMent
Bo Peng, Zichuan Wang, Sheng Yu +3
Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem…
Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models
Zhenchen Tang, Songlin Yang, Zichuan Wang +4
Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks…
Revisiting MLLM Based Image Quality Assessment: Errors and Remedy
Zhenchen Tang, Songlin Yang, Bo Peng +2
The rapid progress of multi-modal large language models (MLLMs) has boosted the task of image quality assessment (IQA). However, a key challenge arises from the inherent mismatch b…
HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images
Zichuan Wang, Bo Peng, Songlin Yang +2
Although recent text-to-image (T2I) models have significantly improved the overall visual quality of generated images, they still struggle in the generation of accurate details in…