6 papers
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
Ziqi Zhou, Weize Quan, Mining Tan +6
Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grain…
LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing
Weicheng Wang, Zhicheng Zhang, Zhongqi Zhang +6
Video editing aims to modify input videos according to user intent. Recently, end-to-end training methods have garnered widespread attention, constructing paired video editing data…
VGA-Bench: A Unified Benchmark and Multi-Model Framework for Video Aesthetics and Generation Quality Evaluation
Longteng Jiang, DanDan Zheng, Qianqian Qiao +7
The rapid advancement of AIGC-based video generation has underscored the critical need for comprehensive evaluation frameworks that go beyond traditional generation quality metrics…
VADB: A Large-Scale Video Aesthetic Database with Professional and Multi-Dimensional Annotations
Qianqian Qiao, DanDan Zheng, Yihang Bo +7
Video aesthetic assessment, a vital area in multimedia computing, integrates computer vision with human cognition. Its progress is limited by the lack of standardized datasets and…
ARGenSeg: Image Segmentation with Autoregressive Image Generation Model
Xiaolong Wang, Lixiang Ru, Ziyuan Huang +4
We propose a novel AutoRegressive Generation-based paradigm for image Segmentation (ARGenSeg), achieving multimodal understanding and pixel-level perception within a unified framew…
PruneHal: Reducing Hallucinations in Multi-modal Large Language Models through Adaptive KV Cache Pruning
Fengyuan Sun, Hui Chen, Xinhao Xu +5
While multi-modal large language models (MLLMs) have made significant progress in recent years, the issue of hallucinations remains a major challenge. To mitigate this phenomenon,…