3 papers
cs.CV2026
ExFusion: Efficient Transformer Training via Multi-Experts Fusion
Jiacheng Ruan, Daize Dong, Xiaoye Qu +5
Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable com…
cs.CV2026
Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models
Tao Xia, Jiawei Liu, Yukun Zhang +3
Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image edit…
cs.CV2025
Hybrid Global-Local Representation with Augmented Spatial Guidance for Zero-Shot Referring Image Segmentation
Ting Liu, Siyuan Li
Recent advances in zero-shot referring image segmentation (RIS), driven by models such as the Segment Anything Model (SAM) and CLIP, have made substantial progress in aligning visu…