Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.09551 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917003407654912 |
|---|---|
| author | Di Nepi, Gavriel Siciliano, Federico Silvestri, Fabrizio |
| author_facet | Di Nepi, Gavriel Siciliano, Federico Silvestri, Fabrizio |
| contents | By the end of 2024, Google researchers introduced Titans: Learning at Test Time, a neural memory model achieving strong empirical results across multiple tasks. However, the lack of publicly available code and ambiguities in the original description hinder reproducibility. In this work, we present a lightweight reimplementation of Titans and conduct a comprehensive evaluation on Masked Language Modeling, Time Series Forecasting, and Recommendation tasks. Our results reveal that Titans does not always outperform established baselines due to chunking. However, its Neural Memory component consistently improves performance compared to attention-only models. These findings confirm the model's innovative potential while highlighting its practical limitations and raising questions for future research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09551 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model Di Nepi, Gavriel Siciliano, Federico Silvestri, Fabrizio Machine Learning Artificial Intelligence By the end of 2024, Google researchers introduced Titans: Learning at Test Time, a neural memory model achieving strong empirical results across multiple tasks. However, the lack of publicly available code and ambiguities in the original description hinder reproducibility. In this work, we present a lightweight reimplementation of Titans and conduct a comprehensive evaluation on Masked Language Modeling, Time Series Forecasting, and Recommendation tasks. Our results reveal that Titans does not always outperform established baselines due to chunking. However, its Neural Memory component consistently improves performance compared to attention-only models. These findings confirm the model's innovative potential while highlighting its practical limitations and raising questions for future research. |
| title | Titans Revisited: A Lightweight Reimplementation and Critical Analysis of a Test-Time Memory Model |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.09551 |