Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attentionby Rengan Xu, Junjie…
An Efficient Recommendation Model Based on Knowledge Graph Attention-Assisted Network (KGATAX)by Zhizhong WuFirst submitted to…
Block-Attention for Efficient RAGby East Sun, Yan Wang, Lan TianFirst submitted to arxiv on: 14…
Efficiently Dispatching Flash Attention For Partially Filled Attention Masksby Agniv Sharma, Jonas GeipingFirst submitted to…
EDSNet: Efficient-DSNet for Video Summarizationby Ashish Prasad, Pranav Jeevan, Amit SethiFirst submitted to arxiv on:…
TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Mapsby Arjun Raj, Lei Wang, Tom…
EchoAtt: Attend, Copy, then Adjust for More Efficient Large Language Modelsby Hossein Rajabzadeh, Aref Jafari,…
ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuningby Jimeng Shi, Azam…
Sparse Low-Ranked Self-Attention Transformer for Remaining Useful Lifetime Prediction of Optical Fiber Amplifiersby Dominic Schneider,…
Analysis of Gene Regulatory Networks from Gene Expression Using Graph Neural Networksby Hakan T. Otal,…