爱可可 AI 前沿推介(8.31)

文章预览

LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 1、[CL] Smaller， Weaker， Yet Better：Training LLM Reasoners via Compute-Optimal Sampling 2、[LG] Revisit Micro-batch Clipping：Adaptive Data Pruning via Gradient Manipulation 3、[CL] Physics of Language Models：Part 2.2， How to Learn From Mistakes on Grade-School Math Problems 4、[CV] SAM2Point：Segment Any 3D as Videos in Zero-shot and Promptable Manners 5、[CV] 3D Pose-Based Temporal Action Segmentation for Figure Skating：A Fine-Grained and Jump Procedure-Aware Annotation Approach 摘要：通过计算优化采样训练LLM推理器、通过梯度操纵进行自适应数据修剪、如何从小学数学问题的错误中学习、以零样本和可提示的方式将任意3D分段为视频、基于3D姿态的花样滑冰时态动作分割 1、[CL] Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling H Bansal, A Hosseini, R Agarwal, V Q. Tran, M Kazemi [Google DeepMind] 更小、更 ………………………………