2 papers
cs.CL2024
Equipping Transformer with Random-Access Reading for Long-Context Understanding
Chenghao Yang, Zi Yang, Nan Hua
Long-context modeling presents a significant challenge for transformer-based large language models (LLMs) due to the quadratic complexity of the self-attention mechanism and issues…
cs.CL2024
Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing
Zi Yang, Nan Hua
As LLMs have become capable of processing more complex types of inputs, researchers have recently studied how to efficiently and affordably process possibly arbitrarily long sequen…