6 papers
DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
Yuqing Chen, Lin Liu, Haisu Wu +4
Video object removal frequently struggles to eliminate target objects and their associated complex physical effects (e.g., smoke and light) in real-world scenes. We attribute this…
Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation
Yuyang Huang, Yabo Chen, Junyu Zhou +5
Source-free domain adaptation (SFDA) is a challenging task that tackles domain shifts using only a pre-trained source model and unlabeled target data. Existing SFDA methods are res…
GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs
Guanghao Zheng, Bowen Shi, Mingxing Xu +8
Vision encoders are indispensable for allowing impressive performance of Multi-modal Large Language Models (MLLMs) in vision language tasks such as visual question answering and re…
METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models
Yuchen Liu, Yaoming Wang, Bowen Shi +5
Vision encoders serve as the cornerstone of multimodal understanding. Single-encoder architectures like CLIP exhibit inherent constraints in generalizing across diverse multimodal…
Refining Alignment Framework for Diffusion Models with Intermediate-Step Preference Ranking
Jie Ren, Yuhang Zhang, Dongrui Liu +2
Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label betwee…
UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding
Bowen Shi, Peisen Zhao, Zichen Wang +8
Vision-language foundation models, represented by Contrastive Language-Image Pre-training (CLIP), have gained increasing attention for jointly understanding both vision and textual…