added news line

Author: dzambon

_data/news.yml

@@ -4,6 +4,12 @@
     <a href="https://arxiv.org/abs/2509.24728">Beyond Softmax: A Natural Parameterization for Categorical Random Variables</a> (Manenti and Alippi) and 
     <a href="https://arxiv.org/abs/2507.23604">Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning</a> (Marzi et al).
     Check them out!
+- date: 2025/10
+  text: >
+    We have released two new preprints about 
+    <a href="https://arxiv.org/abs/2508.03283">Online Continual Graph Learning</a> (OCGL, Donghi et al) and
+    <a href="https://arxiv.org/abs/2510.06819">The Unreasonable Effectiveness of Randomized Representations in OCGL</a> (Donghi et al). 
+    Take a look!
 - date: 2025/09
   text: 'Our papers <a href="https://arxiv.org/abs/2506.15507">Over-squashing in Spatiotemporal Graph Neural Networks</a> (Marisca et al.) and <a href="#">Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games</a> (Lu et al.) have been accepted at <strong><a href="https://neurips.cc">NeurIPS 2025</a></strong>!'
 - date: 2025/06