#Transformers

Articles (3)

• 🇺🇸 KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning — 02/03/2026 [USA]

  arXiv:2602.23592v1 Announce Type: cross Abstract: Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping trac...

  Related: #Memory‑Augmented LLMs, #KV‑Cache Optimization, #Embodied Planning, #Robotics
• 🇺🇸 Understanding Transformer Optimization via Gradient Heterogeneity — 19/02/2026 [USA]

  arXiv:2502.00213v4 Announce Type: replace-cross Abstract: Transformers are difficult to optimize with stochastic gradient descent (SGD) and largely rely on adaptive optimizers such as Adam. Despite t...

  Related: #Optimization, #Gradient heterogeneity, #Adaptive optimizers, #Stochastic gradient descent
• 🇺🇸 Transformers can do Bayesian Clustering — 19/02/2026 [USA]

  arXiv:2510.24318v3 Announce Type: replace-cross Abstract: Bayesian clustering accounts for uncertainty but is computationally demanding at scale. Furthermore, real-world datasets often contain missin...

  Related: #Machine Learning, #Bayesian Methods, #Uncertainty Quantification, #Data Imputation