When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models.
Haoran YouYichao FuZheng WangAmir YazdanbakhshYingyan LinPublished in: CoRR (2024)
Keyphrases
- language model
- autoregressive
- language modeling
- n gram
- probabilistic model
- query expansion
- speech recognition
- information retrieval
- language modelling
- test collection
- document retrieval
- retrieval model
- relevance model
- moving average
- context sensitive
- language models for information retrieval
- non stationary
- statistical language models
- gaussian markov random field
- gray level
- image compression
- active learning
- computer vision
- machine learning