Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Trainingby Zhiyuan Wang, Bokui Chen,…
Attention Mechanisms Don’t Learn Additive Models: Rethinking Feature Importance for Transformersby Tobias Leemann, Alina Fastowski,…
Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series Forecastingby Peiwang Tang, Weitai…
Dynamic Context Adaptation and Information Flow Control in Transformers: Introducing the Evaluator Adjuster Unit and…
System Safety Monitoring of Learned Components Using Temporal Metric Forecastingby Sepehr Sharifi, Andrea Stocco, Lionel…
Reducing Transformer Key-Value Cache Size with Cross-Layer Attentionby William Brandon, Mayank Mishra, Aniruddha Nrusimha, Rameswar…
Transformer in Touch: A Surveyby Jing Gao, Ning Cheng, Bin Fang, Wenjuan HanFirst submitted to…
A Masked Semi-Supervised Learning Approach for Otago Micro Labels Recognitionby Meng Shang, Lenore Dedeyne, Jolan…
Enhancing Transformer-based models for Long Sequence Time Series Forecasting via Structured Matrixby Zhicheng Zhang, Yong…
Your Transformer is Secretly Linearby Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Nikolai Gerasimenko, Ivan Oseledets,…