Pierre-André Noël — accepted AI-conference papers

2026

DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone

Vaibhav Singh, Oleksiy Ostapenko, Pierre-André Noël, Eugene Belilovsky, Torsten Scholak

ICML 2026poster

Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention or KV-cache overhead. We introduce DiffuMamba, a masked diffusion language model built on a b…

Cited by 0 Source ↗Scholar ↗

2023

Flaky Performances When Pretraining on Relational Databases (Student Abstract)

Shengchao Liu, David Vazquez, Jian Tang, Pierre-André Noël

AAAI 2023technical

We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extracted from relational databases (RDBs). Intuitively, this joint use of SSL and GNNs should allow to leverage more of the available data, which could translate to…

Cited by 2 Source ↗PDF ↗Scholar ↗