3 citations · 3 across the 2 of their papers we have counts for
4 papers · 1 filter
RepICL: Reusable In-Context Prediction Across Heterogeneous Representation Spaces
Yu-Hsiang Liu, Kuan-Yu Chen, Chih-Sheng Chen +3
Frozen representations are widely reused for downstream classification, yet each new task typically requires fitting a new predictor. We ask whether the few-shot prediction procedu…
DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction
Kuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den +2
Financial time-series pretraining typically learns from masked observations, contrastive relations, or future outcomes---yet existing objectives struggle to simultaneously avoid fu…
Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting
Yu-Chen Den, Kuan-Yu Chen, Kendro Vincent +1
Transformer-based models have been widely adopted for time-series forecasting due to their high representational capacity and architectural flexibility. However, many Transformer v…
Trompt: Towards a Better Deep Neural Network for Tabular Data
Kuan-Yu Chen, Ping-Han Chiang, Hsin-Rung Chou +2
Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows…