← Search

Harshul Raj Surana

1 accepted papers

2026

DETONATE – A Benchmark for Text-to-Image Alignment and Kernelized Direct Preference Optimization

AAAI 2026technical

Alignment is crucial for text-to-image (T2I) models to ensure that the generated images faithfully capture user intent while maintaining safety and fairness. Direct Preference Optimization (DPO) has emerged as a key alignment technique for large language models (LLMs), and its influence is now exten

Cited by 0SourcePDFScholar