udpate ICML 2024

_data/publications.yml

@@ -1,3 +1,18 @@
+- title: "Improving Molecular Modeling with Geometric GNNs: an Empirical Study"
+  authors:
+    - Ali Ramlaoui
+    - Theo Saulus 
+    - Basile Tervers
+    - Victor Schmidt
+    - David Rolnick
+    - Fragkiskos Malliaros
+    - Alexandre Duval
+  year: 2024
+  journal: ICML ML4LMS workshop. 
+  tags:
+    - tag: arXiv
+      link: https://arxiv.org/pdf/2407.08313
+
 - title: "A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems"
   authors:
     - Alexandre Duval

_data/talks.yml

@@ -1,3 +1,19 @@
+- title: "AI for materials discovery"
+  year: 2024
+  month: July
+  what: Talk and Panel session
+  where: ICML
+  city: Vienna
+  country: Austria
+
+- title: "Crystal-GFN: sampling crystals with desirable properties and constraints"
+  year: 2023
+  month: November
+  what: Paper presentation 
+  where: MOML Conference
+  city: Montreal
+  country: Canada
+
 - title: "FAENet: Frame Averaging Equivariant GNNs for Materials Modeling"
   year: 2023
   month: October

_includes/description.md

@@ -2,7 +2,7 @@
 
 I am the co-founder and Chief Science Officer (CSO) of [Entalpic](http://entalpic.ai/), a young french startup at the forefront of AI and Chemistry, working to accelerate the energy transition. Our focus is on discovering new chemicals and materials that lead to more sustainable practices in sectors where the need for change is most urgent. Specifically, we develop a modern generative AI platform to discover new catalysts that optimize targeted chemical reactions, significantly reducing CO2 emissions and thus making a substantial impact on the environment.
 
-Before this, I briefly worked at Amazon on augmenting LLMs with API-Tools and obtained my **PhD** from [CentraleSupelec](https://www.centralesupelec.fr/) and [Inria Saclay](https://www.inria.fr/fr/centre-inria-de-saclay) under the supervision of [Prof. Fragkiskos Malliaros](https://fragkiskos.me/) in April 2024. During my PhD, for two years, I have also been attached to [MILA](https://mila.quebec/) (Quebec Artificial Intelligence Insitute), under the supervision of [Prof. David Rolnick](https://davidrolnick.com/) and [Prof. Yoshua Bengio](https://yoshuabengio.org/), as part of the group "AI for Climate Change". 
+Before this, I briefly worked at Amazon on augmenting LLMs with API-Tools and obtained my **PhD** from [CentraleSupelec](https://www.centralesupelec.fr/) and [Inria Saclay](https://www.inria.fr/fr/centre-inria-de-saclay) under the supervision of [Prof. Fragkiskos Malliaros](https://fragkiskos.me/) in December 2023. During my PhD, for two years, I have also been attached to [MILA](https://mila.quebec/) (Quebec Artificial Intelligence Insitute), under the supervision of [Prof. David Rolnick](https://davidrolnick.com/) and [Prof. Yoshua Bengio](https://yoshuabengio.org/), as part of the group "AI for Climate Change". 
 
 My research originally spanned the broad field of **Graph Machine Learning** (Graph ML), i.e. an area of ML which focuses on non-euclidean data (e.g. graphs). After several projects on the explicability of Graph Neural Networks (GNN), graph pooling algorithms and graph-based text summarisation, I bifurcated towards **AI4Science** projects using Graph ML to accelerate scientific discovery. In particular, I am working on electrocatalyst design to improve the energy efficiency of hydrogen storage, cement production and other energy-intensive industrial processes. This ambitious project involves (1) constructing scalable and expressive symmetry-preserving GNN architectures for materials modelling, (2) combining them with generative methods (e.g. GFlowNets) to both propose and evaluate new catalyst materials in an end-to-end pipeline, (3) integrating the feedback of real-world lab experiments.