Google（谷歌）

Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model

训练混合：将小规模支架式预训练运行重组为更大的语言模型

Mohammed Sabry, Sean Augenstein, Keith Rush, Lucio Dery

机构 * Google（谷歌公司） ； School of Computing, Dublin City University（都柏林城市大学计算机学院） 纠错

AI总结 本研究提出训练混合（MoT）框架，将Transformer划分为层块在冻结对齐器内独立训练后重组，在13亿参数Gemma模型上验证其可重组为可用语言模型，可复用对齐器实现计算优势，用于研究可复用训练单元。

Comments Accepted at the Workshop on Methods and Opportunities at Small Scale (MOSS), COLM 2026

EvDiff: Event-Based Video Reconstruction using One-Step Diffusion Models

EvDiff：高质视频与事件相机

Weilun Li, Lei Sun, Ruixi Gao, Qi Jiang, Yuqin Ma, Kaiwei Wang, Ming-Hsuan Yang, Luc Van Gool, Danda Pani Paudel

机构 * Zhejiang University（浙江大学） ； INSAIT ； UC Merced（加州大学默塞德分校） ； Google DeepMind（谷歌DeepMind） 纠错

AI总结 EvDiff通过基于事件的扩散模型和替代训练框架，从单色事件流生成高质量彩色视频，提升视频生成的保真度和现实感。

Comments Replacement note: This manuscript has been transferred from the CVPR format to the ECCV 2026 format, with the corresponding title and template updated accordingly. The technical content remains largely unchanged from the previous version. (Current version: 21 pages, 6 figures, and 3 tables.) Accepted by ECCV 2026