GitHub

Simple linear attention language models balance the recall-throughput tradeoff.

Based is an efficient architecture inspired by recovering attention-like capabilities (i.e., recall). We do so by combining 2 simple ideas: Short sliding window attention (e.g., window size 64), to ...
IEEE

Refining Time-Space Traffic Diagrams: A Simple Multiple Linear Regression Model

Abstract: A time-space (TS) traffic diagram, which presents traffic states in time-space cells with color, is an important traffic analysis and visualization tool. Despite its importance for ...
GitHub

Language-Based Multimodal Trajectory Prediction

Traditional vs. Our language-based trajectory prediction, LMTraj. We provide scripts to evaluate our LMTraj-ZERO model for all datasets simultaneously. Two scripts ...
IEEE

A New Code-Block Index-Modulation-Aided DCSK System Based on Sparse Code Multiple Access

Abstract: A new code-block index-modulation-aided differential chaotic shift keying system based on sparse code multiple access, referred to as CBI-SCMA-DCSK, is proposed in this paper. With the aim ...