Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMsby Ben Athiwaratkun, Sujan Kumar…
Implicit Regularization of Gradient Flow on One-Layer Softmax Attentionby Heejune Sheen, Siyu Chen, Tianhao Wang,…
Scattered Mixture-of-Experts Implementationby Shawn Tan, Yikang Shen, Rameswar Panda, Aaron CourvilleFirst submitted to arxiv on:…
Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognitionby Wenjing Zhu, Sining Sun, Changhao Shan, Peng…
CHAI: Clustered Head Attention for Efficient LLM Inferenceby Saurabh Agarwal, Bilge Acun, Basil Hosmer, Mostafa…
FWin transformer for dengue prediction under climate and ocean influenceby Nhat Thanh Tran, Jack Xin,…
An Efficient Learning-based Solver Comparable to Metaheuristics for the Capacitated Arc Routing Problemby Runze Guo,…
Responsible Artificial Intelligence: A Structured Literature Reviewby Sabrina Goellner, Marina Tropmann-Frick, Bostjan BrumenFirst submitted to…
Advancing Graph Neural Networks with HL-HGAT: A Hodge-Laplacian and Attention Mechanism Approach for Heterogeneous Graph-Structured…
TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generationby Jian Qu, Xiaobo…