Tag: Data Augmentation

All the articles with the tag "Data Augmentation".

• Deep Learning for On-Street Parking Violation Prediction

  Published: 14 May, 2025 |  at  11:08 AM

  

  89.01 🤔

  This paper develops a Deep Learning model with a novel data smoothing technique to predict fine-grained on-street parking violation rates in Thessaloniki, Greece, using indirect features like weather and time, achieving improved accuracy (MAE of 0.146) over baseline methods.

• More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives

  Published: 2 Jun, 2025 |  at  01:15 PM

  

  87.51 🤔

  本文提出DrICL方法，通过差异化学习和基于优势的重新加权优化大型语言模型在many-shot上下文学习中的性能，并在自建的ICL-50数据集上验证了其在多种任务中的稳定性和有效性。

• Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures

  Published: 2 Jun, 2025 |  at  01:14 PM

  

  87.28 🤔

  本文提出 CoLM 方法，通过构建小批量核心集匹配大批量梯度，在内存需求减少 2 倍的情况下，使 LLM 微调性能优于 4 倍批大小的常规训练，同时提升收敛速度。

• PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery

  Published: 2 Jun, 2025 |  at  11:32 AM

  

  87.10 🤔

  PASER提出了一种针对剪枝后大语言模型能力恢复的后训练数据选择方法，通过语义聚类、能力退化感知选择和负面效应缓解，在有限数据预算下显著提升恢复性能并降低计算成本。

• Behavior Injection: Preparing Language Models for Reinforcement Learning

  Published: 1 Jun, 2025 |  at  11:45 AM

  

  86.57 🤔

  本文提出BRIDGE方法，通过在SFT阶段注入探索和利用行为增强大型语言模型的RL准备度，并在数学与逻辑推理任务上显著提升RFT性能。