2 papers
cs.LG2026
Transformers with Selective Access to Early Representations
Skye Gunasekaran, Téa Wright, Rui-Jie Zhu +1
Several recent Transformer architectures expose later layers to representations computed in the earliest layers, motivated by the observation that low-level features can become har…
cs.LG2025
A Predictive Approach To Enhance Time-Series Forecasting
Skye Gunasekaran, Assel Kembay, Hugo Ladret +4
Accurate time-series forecasting is crucial in various scientific and industrial domains, yet deep learning models often struggle to capture long-term dependencies and adapt to dat…