Authors

Yanlin Qi

Publications 2

Preprint Open access

EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding

Gujie Shao, Zixun Xie, Xuechun Xing et al. · 2026

Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging remain insufficiently characterized. Existing ophthalmic datasets are typically designed for individual diseases or specialized tasks, making it difficult to systematically evaluat …

Preprint Open access

MassAlloc Attention: Let Attention Allocate Its Own Compute

Jingze Shi, Zhangyang Peng, Xianduo Li et al. · 2026

FullAttn often assigns negligible normalized mass to much of the causal score space, yet dense kernels execute the complete post-score path after forming each QK tile. We introduce MALA, a fused attention primitive that preserves score access to every legal causal interaction and uses normalized contribution to allocat …

Co-authors