Pietro Lio

Fast and Interpretable Protein Substructure Alignment via Optimal Transport

Sheaves Reloaded: A Direction Awakening

SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling

ContextFlow: Context-Aware Flow Matching for Trajectory Inference from Spatial Omics Data

Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding

Wasserstein Hypergraph Neural Network

Entropy-Lens: The Information Signature of Transformer Computations

An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making

Can Data-driven Machine Learning Reach Symbolic-level Logical Reasoning? -- The Limit of the Scaling Law

Toward Monosemantic Clinical Explanations for Alzheimer’s Diagnosis via Attribution and Mechanistic Interpretability

Mechanistic Interpretability of LLMs through Network Science

An algebraic approach to approximately equivariant networks

gRNAde: Geometric Deep Learning for 3D RNA inverse design

SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

EduLLM: Leveraging Large Language Models and Framelet-Based Signed Hypergraph Neural Networks for Student Performance Prediction

SPHINX: Structural Prediction using Hypergraph Inference Network

Stochastic Encodings for Active Feature Acquisition

How Particle System Theory Enhances Hypergraph Message Passing

Information Bottleneck for Active Feature Acquisition

RNA FrameFlow: Flow Matching for de novo 3D RNA Backbone Generation

NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones

G-Adaptivity: optimised graph-based mesh relocation for finite element methods

PoseCheck: Generative Models for 3D Structure-based Drug Design Produce Unrealistic Poses

Closing the Gap between Neural Networks for Approximate and Rigorous Logical Reasoning

Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification

Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts

Improving Antibody Design with Force-Guided Sampling in Diffusion Models

Bayesian Binary Search

Predicting Time-Varying Flux and Balance in Metabolic Systems using Structured Neural ODE Processes

Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates