Explore projects

ATEM is a novel framework for studying topic evolution in scientific archives. ATEM 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. paper: https://arxiv.org/abs/2306.02221

Short abstract

Implementing deep reinforcement learning algorithms for the ICGA competition.

RankMerging version in C++ as coded by Dan Timsit in 2024.

The BoolEAN POLynomial Evaluation library

Porting of Skip-Thoughts pretrained models from Theano to Torch7 (Retwitted by Yann LeCun :D)

Bibliography related to the post-doc of Marek Felšöci

Cross domain dynamic