5 papers · 1 filter
L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare Data
Po-Cheng Cheng, Hung-Hsuan Chen
Healthcare institutions routinely accumulate high-dimensional computed tomography (CT) volumes, but only a fraction can be annotated by experts. We present L2GSSL, a local-to-globa…
Thinking Deeper, Not Longer: Memory-Efficient Test-Time Reasoning with Depth-Recurrent Transformers for Compositional Generalization
Hung-Hsuan Chen
Standard Transformers have a fixed computational depth, limiting their ability to generalize to tasks that require variable-depth reasoning. The usual remedy, Chain-of-Thought (CoT…
Structure-Preserving Graph Contrastive Learning for Mathematical Information Retrieval
Chun-Hsi Ku, Hung-Hsuan Chen
This paper introduces Variable Substitution as a domain-specific graph augmentation technique for graph contrastive learning (GCL) in the context of searching for mathematical form…
SCPL: Enhancing Neural Network Training Throughput with Decoupled Local Losses and Model Parallelism
Ming-Yao Ho, Cheng-Kai Wang, You-Teng Lin +1
Adopting large-scale AI models in enterprise information systems is often hindered by high training costs and long development cycles, posing a significant managerial challenge. Th…
GraphFusionSBR: Denoising Multi-Channel Graphs for Session-Based Recommendation
Jia-Xin He, Hung-Hsuan Chen
Session-based recommendation systems must capture implicit user intents from sessions. However, existing models suffer from issues such as item interaction dominance and noisy sess…