Ehsan Abbasnejad

Influence propagation can dramatically enhance link prediction accuracy in multi-relational graphs, as demonstrated by the IGNP framework's superior performance over traditional methods.

Unseen single-cell perturbation effects can be predicted more accurately by explicitly modeling the latent, dynamic causal processes that drive cellular response.

By tracking how LLM activations *move* through layers, this new method reveals the hidden geometry of reasoning, outperforming standard probing techniques that treat activations as static snapshots.