Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Modelsby Yihong Dong, Xue…
DetoxLLM: A Framework for Detoxification with Explanationsby Md Tawkat Islam Khondaker, Muhammad Abdul-Mageed, Laks V.…
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learningby Anthony Liang, Guy Tennenholtz, Chih-wei Hsu,…
On the dynamics of three-layer neural networks: initial condensationby Zheng-An Chen, Tao LuoFirst submitted to…
Shaving Weights with Occam’s Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihoodby Rayen…
Hierarchical energy signatures using machine learning for operational visibility and diagnostics in automotive manufacturingby Ankur…
Structural Knowledge-Driven Meta-Learning for Task Offloading in Vehicular Networks with Integrated Communications, Sensing and Computingby…
CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous modelsby Abhishek Singh, Gauri…
A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural…
Model Compression Method for S4 with Diagonal State Space Layers using Balanced Truncationby Haruka Ezoe,…