local LLMs, small LLMs, mixture of experts
From SHAP to Rules: Distilling Expert Knowledge from Post-hoc Model Explanations in Time Series Classification
arxiv.org·15h
Filtering with Self-Attention and Storing with MLP: One-Layer Transformers Can Provably Acquire and Extract Knowledge
arxiv.org·15h
Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
arxiv.org·15h
What Is Your AI Agent Buying? Evaluation, Implications and Emerging Questions for Agentic E-Commerce
arxiv.org·15h
TriP-LLM: A Tri-Branch Patch-wise Large Language Model Framework for Time-Series Anomaly Detection
arxiv.org·1d
Loading...Loading more...