Enhancing Microgrid Performance Prediction with Attention-based Deep Learning Modelsby Vinod Kumar Maddineni, Naga Babu Koganti,…
FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecastingby Shusen Ma, Yu Kang, Peng Bai,…
Compact Language Models via Pruning and Knowledge Distillationby Saurav Muralidharan, Sharath Turuvekere Sreenivas, Raviraj Joshi,…
PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformerby Jiahong Ma, Mingguo He, Zhewei WeiFirst submitted…
Domain Adaptation for Industrial Time-series Forecasting via Counterfactual Inferenceby Chao Min, Guoquan Wen, Jiangru Yuan,…
An Attention-based Representation Distillation Baseline for Multi-Label Continual Learningby Martin Menabue, Emanuele Frascaroli, Matteo Boschini,…
Revisiting Attention for Multivariate Time Series Forecastingby Haixiang WuFirst submitted to arxiv on: 18 Jul…
Attention Based Simple Primitives for Open World Compositional Zero-Shot Learningby Ans Munir, Faisal Z. Qureshi,…
Hybrid Dynamic Pruning: A Pathway to Efficient Transformer Inferenceby Ghadeer Jaradat, Mohammed Tolba, Ghada Alsuhli,…
Beyond KV Caching: Shared Attention for Efficient LLMsby Bingli Liao, Danilo Vasconcellos VargasFirst submitted to…