Genre
Going Beyond Heuristics by Imposing Policy Improvement as a Constraint Chi-Chang Lee
As such, we prevent policies from merely exploiting heuristic rewards without improving the task reward.
Divergences between Language Models and Human Brains
Do machines and humans process language in similar ways?
LearningtoReasonIterativelyandParallellyfor ComplexVisualReasoningScenarios
Meanwhile, its"parallel" computation allowsforthesimultaneous explorationofdifferent reasoning paths andbenefits more robust and efficient execution of operations that are mutually independent (e.g. when counting individual colors for the query:"determine the maximum occurring color amongst all t-shirts"). We design IPRM as a lightweight and fully-differentiable neural module thatcanbeconveniently applied toboth transformer and non-transformer vision-language backbones.
Learning the Infinitesimal Generator of Stochastic Diffusion Processes Vladimir R. Kostic CSML, Istituto Italiano di Tecnologia University of Novi Sad
We address data-driven learning of the infinitesimal generator of stochastic diffusion processes, essential for understanding numerical simulations of natural and physical systems.
Partial Transportability for Domain Generalization Kasra Jalaldoust Alexis Bellot
Our results are corroborated with experiments.
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
We introduce a novel score-based diffusion framework named Twigs that incorporates multiple co-evolving flows for enriching conditional generation tasks. Specifically, a central or trunk diffusion process is associated with a primary variable (e.g., graph structure), and additional offshoot or stem processes are dedicated
Graph Classification via Reference Distribution Learning: Theory and Practice
This work introduces Graph Reference Distribution Learning (GRDL), an efficient and accurate graph classification method. GRDL treats each graph's latent node embeddings given by GNN layers as a