视频大模型缩放规律新发现：稳定曲线下藏着不稳定的样本差异，读懂这项研究才能避开评估陷阱。
arXiv:2608.07014v1 Announce Type: new Abstract: Aggregate scaling curves suggest that Video LLMs improve smoothly or saturate as visual budgets grow. …
字节跳动开源EdgeBench，揭示AI在真实世界环境中的学习缩放规律，值得研究者关注。
Article URL: https://github.com/ByteDance-Seed/EdgeBench Comments URL: https://news.ycombinator.com/item?id=48801308 Points: 1 # Comments: 0
视觉语言模型在测试时也能通过缩放计算量提升性能，这篇论文揭示了新的缩放规律。
arXiv:2606.28864v1 Announce Type: new Abstract: Test-time scaling is a paradigm where large models use additional compute at inference to achieve bett…
LLM继续预训练中，超参数配置可预测的缩放规律，告别启发式搜索与高昂成本
arXiv:2606.05610v1 Announce Type: new Abstract: The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter con…
数据稀缺时如何扩展稀疏语言模型？这篇ICML 2026论文提出重复训练方法，有望突破数据瓶颈。
arXiv:2606.01155v1 Announce Type: new Abstract: Scaling laws for dense LLMs under infinite data are well explored, but how sparsity interacts with lim…