Conceptio › Archive › Scholar Commons
Scholar Commonsmetadata only

YinYang-Align: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment

Das, Amitava et al.
Scholar Commons · Papers
Open Source ↗
alignmentartificial-intelligence-and-roboticsgenerative-ailarge-language-modelsmulti-objective-optimizationresponsible-ai
text-to-image, alignment, generative ai, large language models, responsible ai, direct preference optimization, multi-objective optimization, artificial intelligence and robotics
This document is indexed with metadata only — full text is not available in the archive for this record. Open the official source ↗
Record · ID 680673
Retrieved via Conceptio — every document is proof-bundled with source, license, and retrieval metadata.