9 papers
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
Feihong Yan, Shaoyu Liu, Haixuan Wang +4
Visual Autoregressive (VAR) models have emerged as a strong alternative to diffusion for image synthesis, yet their fixed training resolution prevents direct generation at higher r…
Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge
Shuai Lu, Meng Wang, Jia Guo +6
Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis. However, their clinical deployment is severely hindered by lacking domain-specific k…
Native Intelligence Emerges from Large-Scale Clinical Practice: A Retinal Foundation Model with Deployment Efficiency
Jia Guo, Jiawei Du, Shengzhu Yang +21
Current retinal foundation models remain constrained by curated research datasets that lack authentic clinical context, and require extensive task-specific optimization for each ap…
One Dinomaly2 Detect Them All: A Unified Framework for Full-Spectrum Unsupervised Anomaly Detection
Jia Guo, Shuai Lu, Lei Fan +9
Unsupervised anomaly detection (UAD) has evolved from building specialized single-class models to unified multi-class models, yet existing multi-class models significantly underper…
CLIPin: A Non-contrastive Plug-in to CLIP for Multimodal Semantic Alignment
Shengzhu Yang, Jiawei Du, Shuai Lu +3
Large-scale natural image-text datasets, especially those automatically collected from the web, often suffer from loose semantic alignment due to weak supervision, while medical da…
MDSAM:Memory-Driven Sparse Attention Matrix for LVLMs Hallucination Mitigation
Shuaiye Lu, Linjiang Zhou, Xiaochuan Shi
Hallucinations in large vision-language models (LVLMs) often stem from the model's sensitivity to image tokens during decoding, as evidenced by attention peaks observed when genera…