arXiv:2605.04503v1 Announce Type: new
Abstract: Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key benchmark for fine-grained change perception, cross-moda…
arXiv:2501.03717v3 Announce Type: replace
Abstract: Achieving physically consistent image editing remains a significant challenge in computer vision. Existing image editing methods typically rely on neural networks, which struggle to accurately handle…
arXiv:2605.04524v1 Announce Type: new
Abstract: We present a single-image head mesh reconstruction framework that addresses the longstanding challenge of simultaneously preserving facial identity and producing industry-grade topology. Our framework ad…
arXiv:2605.04531v1 Announce Type: new
Abstract: Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment…
arXiv:2605.01345v2 Announce Type: replace
Abstract: Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details r…
arXiv:2605.04590v1 Announce Type: new
Abstract: Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segme…
arXiv:2605.03941v2 Announce Type: replace
Abstract: Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action…
arXiv:2604.26509v2 Announce Type: replace-cross
Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for simulation-based training and real-world deployment. While 3D generative modelin…
arXiv:2605.04447v1 Announce Type: new
Abstract: Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scenarios, it remains the in…
arXiv:2501.14171v3 Announce Type: replace-cross
Abstract: Multi-modal brain MRI provides essential complementary information for clinical diagnosis. However, acquiring all modalities in practice is often constrained by time and cost. To address this, …