3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Transformer-based large language models often suffer from inter-layer parameter redundancy, where functional transformations are redundantly learned across network depths. We propose CS-MoE, a novel Transformer architecture featuring cross-layer expert sharing to address this inefficiency. Deviating from the widely use...
This paper proposes ViCo, a training framework for visual-oriented coding that employs iterative reflections to align generated chart images progressively with the reference and proposes an automatic, multifaceted evaluation framework that assesses charts'style, layout, and semantic consistency via a hierarchical heter...
A novel pipeline framework, PiPMRE, developed on language models to enhance MRE performance, which surpasses the previous state-of-the-art by an average of 5.6 recall points and 4.4 accuracy points and is demonstrated in few-shot settings.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
