Predictable Scale (Part II) --- Farseer: A Refined Scaling Law in LLMs

NeurIPSSpotlight2025

Authors: Houyi Li, Wenzhen Zheng, Qiufeng Wang, Zhenyu Ding, Haoying Wang, Zili Wang, Shijie Xuyang, Ning Ding, Shuigeng Zhou, Xiangyu Zhang, Daxin Jiang
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Training Large Language Models (LLMs) is prohibitively expensive, creating a critical scaling gap where insights from small-scale experiments often fail to transfer to resource-intensive production sy…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

large language model language model scaling law llm

← All NeurIPS 2025 Spotlight papers · Browse the whole archive