12 citations · 14 across the 5 of their papers we have counts for
5 papers
Long-Context Modeling via GSS-Transformer Hybrid Architecture with Learnable Mixing
Kuzey Torlak, Hüseyin Arda Arslan, Anıl Dervişoğlu +2
Modeling long-range dependencies remains a central challenge in natural language processing. Transformer architectures achieve strong performance via self-attention but scale quadr…
Conditional Latent Space Molecular Scaffold Optimization for Accelerated Molecular Design
Onur Boyar, Hiroyuki Hanada, Ichiro Takeuchi
The rapid discovery of new chemical compounds is essential for advancing global health and developing treatments. While generative models show promise in creating novel molecules,…
Crystal-LSBO: Automated Design of De Novo Crystals with Latent Space Bayesian Optimization
Onur Boyar, Yanheng Gu, Yuji Tanaka +3
Generative modeling of crystal structures is significantly challenged by the complexity of input data, which constrains the ability of these models to explore and discover novel cr…
Latent Space Bayesian Optimization with Latent Data Augmentation for Enhanced Exploration
Onur Boyar, Ichiro Takeuchi
Latent Space Bayesian Optimization (LSBO) combines generative models, typically Variational Autoencoders (VAE), with Bayesian Optimization (BO) to generate de-novo objects of inter…
Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation
Enes Sadi Uysal, M. Şafak Bilici, B. Selin Zaza +2
Retinal Vessel Segmentation is important for the diagnosis of various diseases. The research on retinal vessel segmentation focuses mainly on the improvement of the segmentation mo…