Abstract: The Direct Preference Optimization (DPO) method and its various variants have recently been shown to perform well on general instruction tuning tasks. These methods focus on optimizing ...
Abstract: To improve the operational efficiency of compressor units and reduce waste, a Multi-Strategy Improved Beluga Whale Optimization (MSI-BWO) algorithm is proposed for the collaborative ...
TournO (Tournament Optimization) combines pointwise and pairwise LLM judges to produce reward signals in RL for LLMs, using tournament-style comparisons (round-robin, ELO) to derive scalar rewards ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results