Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Autoregressive Direct Preference Optimization
Masanari Oi, Mahiro Ukai, Masahiro Kaneko +2
Direct preference optimization (DPO) has emerged as a promising approach for aligning large language models (LLMs) with human preferences. However, the widespread reliance on the r…
cs.AI2024
AdaCoder: Adaptive Prompt Compression for Programmatic Visual Question Answering
Mahiro Ukai, Shuhei Kurita, Atsushi Hashimoto +2
Visual question answering aims to provide responses to natural language questions given visual input. Recently, visual programmatic models (VPMs), which generate executable program…