IEEE

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

Abstract: Visual program synthesis is a promising approach to ex-ploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-shot ...
InfoQ

Java Explores Carrier Classes to Extend Data-Oriented Programming beyond Records

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...
National Bureau of Economic Research

Creating High-Opportunity Neighborhoods: Evidence from the HOPE VI Program

We study whether low-economic-mobility neighborhoods can be transformed into high-mobility areas by analyzing the HOPE VI program, which invested $17 billion to revitalize 262 distressed public ...
IEEE

Visual Programming for Zero-Shot Open-Vocabulary 3D Visual Grounding

Abstract: 3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predefined ...