Explore projects

ATEM is a novel framework for studying topic evolution in scientific archives. It is based on dynamic topic modeling and dynamic graph embedding techniques that explore the dynamics of content and citations of documents within a scientific corpus. ATEM explores a new notion of contextual emergence for the discovery of emerging interdisciplinary research topics based on the dynamics of citation links in topic clusters. Our experiments show that ATEM can efficiently detect emerging cross-disciplinary topics within the DBLP archive of over five million computer science articles.

Code python pour les expériences de génération de graphes aléatoires

Implementing deep reinforcement learning algorithms for the ICGA competition.

Python wrapper to load and read inrimage data

Imagenet classification using sparse patch codes.

The code deposit for the "SSH Super-Resolution using high resolution SST with a Subpixel Convolutional Residual Network" article submitted at Climate informatics 2022

This is the source code of the 2021 replication for ReScience of the paper "Speedup Graph Processing by Graph Ordering" by Hao Wei, Jeffrey Xu Yu, Can Lu, and Xuemin Lin, published in Proceedings of SIGMOD 2016.

Coriolis VLSI CAD Tools

Coriolis VLSI CAD Tools

An interactive exploration platform for topic evolution graphs