🧑🔬 Mehran Kazemi — papers of 20242 papers · all years of Mehran KazemiGenerative Verifiers: Reward Modeling as Next-Token PredictionLunjun Zhang, Arian Hosseini, Hritik Bansal, et al.arXiv:2408.15240 · 143 citationsSmaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal SamplingHritik Bansal, Arian Hosseini, Rishabh Agarwal, et al.arXiv:2408.16737 · 26 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/mehran-kazemi/year/2024/