Looped Transformers increase computation per token by repeatedly applying a shared backbone, offering a way to improve language modeling and downstream task performance at a fixed backbone parameter count. However, each loop depends on the preceding loop, so increasing recurrent depth also increases decoding latency. E...
Fei Song, Bo-Yi Zeng, Yi-Qing Hao et al.· 0 citations
Looped Transformers offer a parameter-efficient approach to language modeling by repeatedly applying a shared backbone. Vanilla looped Transformers use each backbone output directly as the input to the next iteration. These outputs may contain information useful several iterations later, but retaining it across the loo...
FisherEdit is proposed, a theoretically grounded method built on Fisher geometry, which replaces coarse activation-space projections with importance-aware regularization in parameter space and achieves state-of-the-art performance while better preserving model stability and downstream task accuracy.
Yi-Zhou Yang, Jia-Hong Fu, Zhi-Wu Wang et al.· 0 citations
These findings support continued benchmarking and cautious, specialist-supervised use of multimodal LLMs in retinal education and structured imaging question answering and indicate that retinal image interpretation remains a major limitation.
Xiao-Chen Gu, Yi-Zhou Yang, Xuan-Qiao Lin et al.· Frontiers in Medicine· 0 citations
Publicly available LLMs and MLLMs are evolving from report-parsing tools toward broader ophthalmic clinical assistants, but their use should follow a task-layered validation framework in which verification and human oversight increase with the clinical consequences of error.