TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Compu- tational Linguistics: Human Language Technologies (Volume 1: Long Papers)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
On a simulated dataset of 180 patients, an interaction-aware logistic model using medication adherence as a contextual modifier raised recall of high-risk financial events during vulnerability windows from 0.7442 to 0.9070 while the financial-only baseline retained the highest overall F1.
citing papers explorer
-
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
-
Medication-Aware Financial Exploitation Detection for Alzheimer's Patients Using Edge-Aware Interaction Risk Modeling
On a simulated dataset of 180 patients, an interaction-aware logistic model using medication adherence as a contextual modifier raised recall of high-risk financial events during vulnerability windows from 0.7442 to 0.9070 while the financial-only baseline retained the highest overall F1.