Tag: Efficiency

All the articles with the tag "Efficiency".

• Single-shot prediction of parametric partial differential equations

  Published: 16 May, 2025 |  at  11:13 AM

  

  99.48 🤔

  Flexi-VAE introduces a variational autoencoder framework for single-shot forecasting of parametric PDEs, using a neural propagator to achieve efficient, accurate long-horizon predictions with significant speedups over sequential models like AE-LSTM, as validated on Burgers' and advection-diffusion equations.

• Purity Law for Generalizable Neural TSP Solvers

  Published: 15 May, 2025 |  at  11:09 AM

  

  98.11 🤔

  This paper introduces Purity Law (PuLa), a structural principle revealing sparsity bias in optimal TSP solutions, and proposes Purity Policy Optimization (PUPO), a training framework that significantly enhances the generalization of neural TSP solvers across diverse scales and distributions without inference overhead.

• Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging

  Published: 31 May, 2025 |  at  11:35 AM

  

  95.81 🤔

  本文通过模型融合方法整合快速思维和慢速推理能力，实现长到短推理，在7B模型上将响应长度压缩高达55%且保持性能，提出了一种高效解决大语言模型过度思考问题的方案。

• ASURA-FDPS-ML: Star-by-star Galaxy Simulations Accelerated by Surrogate Modeling for Supernova Feedback

  Published: 15 May, 2025 |  at  11:07 AM

  

  95.02 🤔

  This paper introduces ASURA-FDPS-ML, a framework that accelerates high-resolution galaxy simulations by using a machine learning surrogate model for supernova feedback in dense regions, achieving a fourfold speedup while maintaining comparable morphological and outflow characteristics to direct simulations, despite some discrepancies in momentum at higher altitudes.

• A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

  Published: 21 May, 2025 |  at  11:14 AM

  

  94.56 🤔

  本文提出低秩克隆（LRC）方法，通过低秩投影矩阵和激活克隆实现从大型语言模型到小型语言模型的高效知识蒸馏，仅用10-20B tokens训练即可媲美或超越训练数据量达数万亿tokens的模型，显著提升训练效率。