7 papers
Shortest-Path Flow Matching with Mixture-Conditioned Bases for OOD Generalization to Unseen Conditions
Andrea Rubbi, Amir Akbarnejad, Mohammad Vali Sanian +10
Robust generalization under distribution shift remains a key challenge for conditional generative modeling: conditional flow-based methods often fit the training conditions well bu…
An Empirical Investigation of Neural ODEs and Symbolic Regression for Dynamical Systems
Panayiotis Ioannou, Pietro Liò, Pietro Cicuta
Accurately modelling the dynamics of complex systems and discovering their governing differential equations are critical tasks for accelerating scientific discovery. Using noisy, s…
DisentangleFormer: Spatial-Channel Decoupling for Multi-Channel Vision
Jiashu Liao, Pietro Liò, Marc de Kamps +1
Vision Transformers face a fundamental limitation: standard self-attention jointly processes spatial and channel dimensions, leading to entangled representations that prevent indep…
Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification
Cristina Cornelio, Flavio Petruzzellis, Pietro Lio
Large Language Models (LLMs) have shown promise as robotic planners but often struggle with long-horizon and complex tasks, especially in specialized environments requiring externa…
GenRec: Generative Sequential Recommendation with Large Language Models
Panfeng Cao, Pietro Lio
Sequential recommendation is a task to capture hidden user preferences from historical user item interaction data and recommend next items for the user. Significant progress has be…
A physics-informed search for metric solutions to Ricci flow, their embeddings, and visualisation
Aarjav Jain, Challenger Mishra, Pietro Liò
Neural networks with PDEs embedded in their loss functions (physics-informed neural networks) are employed as a function approximators to find solutions to the Ricci flow (a curvat…
A Multiscale Graph Convolutional Network Using Hierarchical Clustering
Alex Lipov, Pietro Liò
The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised. A novel architecture is explored which exploits this information through…