2024/04/14 by Dongseong Hwang, Weiran Wang, Hwang, Dongseong +7 · 1 voice · 2 citations
Computer Science · #Advanced Neural Network Applications #Generative Adversarial Networks and Image Synthesis #Topic Modeling #cs.AI #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2404.09173
openalex publication_date 2024/04/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
While Transformers have revolutionized deep learning, their quadratic attention complexity hinders their ability to process infinitely long inputs. We propose Feedback Attention Memory (FAM), a novel Transformer architecture that leverages a feedback loop to enable the network to attend to its own latent representations. This design fosters the emergence of working memory within the Transformer, allowing it to process indefinitely long sequences. TransformerFAM requires no additional weights, enabling seamless integration with pre-trained models. Our experiments show that TransformerFAM significantly improves Transformer performance on long-context tasks across various model sizes (1B, 8B, and 24B). These results showcase the potential to empower Large Language Models (LLMs) to process sequences of unlimited length.