6 accepted papers
Reinforcement learning (RL) has emerged as a powerful post-training paradigm for large language models (LLMs), yet its effectiveness varies significantly across base models. While incorporating a pre-RL supervised fine-tuning (SFT) phase can enhance RL training, key questions remain: how long should…
Direct Preference Optimization (DPO) has emerged as a promising framework for aligning Large Language Models (LLMs) with human preferences by directly optimizing the log-likelihood difference between chosen and rejected responses. However, existing methods assign equal importance to all tokens in th…
Self-play fine-tuning has demonstrated promising abilities in adapting large language models (LLMs) to downstream tasks with limited real-world data. The basic principle is to iteratively refine the model with real samples and synthetic ones generated from itself. However, the existing methods prima…
Recently, self-play fine-tuning (SPIN) has been proposed to adapt large language models to downstream applications with scarce expert-annotated data, by iteratively generating synthetic responses from the model itself. However, SPIN is designed to optimize the current reward advantages of annotated…
Temporal graphs offer more accurate modeling of many real-world scenarios than static graphs. However, neighbor aggregation, a critical building block of graph networks, for temporal graphs, is currently straightforwardly extended from that of static graphs. It can be computationally expensive when…
Recently, the online matching problem has attracted much attention due to its wide application on real-world decision-making scenarios. In stationary environments, by adopting the stochastic user arrival model, existing methods are proposed to learn dual optimal prices and are shown to achieve a fas…