paper-with-me

Papers

Enhancing Long-Term Memory using Hierarchical Aggregate Tree for Retrieval Augmented Generation

2024-06-10 · Aadharsh Aadhithya A, Sachin Kumar S, Soman K. P

Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through conditional tree traversals. HAT encapsulates information from children nodes, enabling broad coverage with depth control. We formulate finding best context as optimal tree traversal. Experiments show HAT improves dialog coherence and summary quality over baseline contexts, demonstrating the techniques effectiveness for multi turn reasoning without exponential parameter growth. This memory augmentation enables more consistent, grounded longform conversations from LLMs

📄 PDF Abstract BibTeX arXiv:2406.06124

Code (0)

등록된 구현이 없습니다.

Tasks

RetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

MELODI: Exploring Memory Compression for Long Contexts

2024-10-04 · Yinpeng Chen, DeLesley Hutchins, Aren Jansen, Andrey Zhmoginov 외

We present MELODI, a novel memory architecture designed to efficiently process long documents using short context windows. The key principle behind MELODI is to represent short-term and long-term memory as a hierarchical…

HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking

2025-07-10 · Ruixiang Chen, Guolei Sun, Yawei Li, Jie Qin 외

This paper presents enhancements to the SAM2 framework for video object tracking task, addressing challenges such as occlusions, background clutter, and target reappearance. We introduce a hierarchical motion estimation …

Motion EstimationObject TrackingVideo Object Tracking

Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management

2025-12-25 · Changzhi Sun, Xiangyu Chen, Jixiang Luo, Dell Zhang 외 arxiv

External memory is a key component of modern large language model (LLM) systems, enabling long-term interaction and personalization. Despite its importance, memory management is still largely driven by hand-designed heur…

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

2024-10-17 · Alireza Rezazadeh, Zichao Li, Wei Wei, Yujia Bao

Recent advancements in large language models have significantly improved their context windows, yet challenges in effective long-term memory management remain. We introduce MemTree, an algorithm that leverages a dynamic,…

Dialogue UnderstandingManagementQuestion AnsweringRetrieval

Enhancing Long Video Understanding via Hierarchical Event-Based Memory

2024-09-10 · Dingxin Cheng, Mingda Li, Jingyu Liu, Yongxin Guo 외

Recently, integrating visual foundation models into large language models (LLMs) to form video understanding systems has attracted widespread attention. Most of the existing models compress diverse semantic information w…

Video Understanding