🏢 POSTECH

Certified selective generation controls language model hallucinations by leveraging textual entailment and a novel semi-supervised algorithm, guaranteeing a controlled false discovery rate.

Pessimistic Backward Policy for GFlowNets (PBP-GFN) tackles GFlowNets’ tendency to under-exploit high-reward objects by maximizing observed backward flow, enhancing high-reward object discovery and ov…

This paper introduces a novel object-centric learning (OCL) framework that enhances slot attention with a self-modulating top-down pathway, significantly improving object representation and achieving …