arxiv:2505.04410
Junjie Wang
xiaomoguhzz
AI & ML interests
computer vision, Vision-Language Models, Multimodal Large Language Models
Recent Activity
updated a dataset 6 days ago
xiaomoguhzz/codex-ppt-temp-visual-encoder-assets published a dataset 6 days ago
xiaomoguhzz/codex-ppt-temp-visual-encoder-assets upvoted a paper 10 days ago
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware GatingOrganizations
models 8
xiaomoguhzz/VisionEncoder
Updated
xiaomoguhzz/bagelthink
Updated
xiaomoguhzz/DeCLIP2_EVA-B_DINOv2-B_csa_560_plus_sd0.3_0.1_2.0_0.3
Updated
xiaomoguhzz/DeCLIP_EVA-L_DINOv2-L_csa_0.05_2.0
Updated
xiaomoguhzz/CATSeg_DeCLIP_EVA-L_DINOv2-L_csa_0.05_2.0
Updated
xiaomoguhzz/DeCLIP_EVA-B_DINOv2-B_csa_0.05_2.0
Updated
xiaomoguhzz/CATSeg_DeCLIP_EVA-B_DINOv2-B_csa_0.05_2.0
Updated
xiaomoguhzz/DeCLIP_evab_dinov2B_csa_560_0.25_seg
Updated