We present Adaptive Memory Networks (AMN) that processes input-question pairs to dynamically construct a network architecture optimized for lower inference times for Question Answering (QA) tasks. AMN processes the input story to extract entities and stores them in memory banks. Starting from a single bank, as the number of input entities increases, AMN learns to create new banks as the entropy in a single bank becomes too high. Hence, after processing an input-question(s) pair, the resulting network represents a hierarchical structure where entities are stored in different banks, distanced by question relevance. At inference, one or few banks are used, creating a tradeoff between accuracy and performance. AMN is enabled by dynamic networks that allow input dependent network creation and efficiency in dynamic mini-batching as well as our novel bank controller that allows learning discrete decision making with high accuracy. In our results, we demonstrate that AMN learns to create variable depth networks depending on task complexity and reduces inference times for QA tasks.
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
College of Design and Innovation, Tongji University（同济大学设计创意学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海自主智能无人系统科学中心）
Adaptive Memory and Reflection Multi-Agent System for Medical Question Answering
School of Computing and Mathematics, Manchester Metropolitan University（曼彻斯特城市大学计算与数学学院）；Electrical and Computer Engineering, Technion – Israel Institute of Technology（以色列理工学院电气与计算机工程系）；School of Science and Technology, Hong Kong Metropolitan University（香港都会大学科学与科技学院）
Choosing How to Remember: Adaptive Memory Structures for LLM Agents
University of Technology Sydney（悉尼大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California, Los Angeles（加州大学洛杉矶分校）；The University of Melbourne（墨尔本大学）
HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Bristol（布里斯托大学）；The Hong Kong University of Science and Technology（香港科技大学）
Rosetta Memory: Adaptive Memory for Cross-LLM Agents
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Weixin, Tencent（腾讯微信）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）
Reasoning with Memory: A Temporal Granularity-Adaptive Framework for Training-Free Long Video Understanding
National University of Singapore（新加坡国立大学）；Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR)（高性能计算研究所，科学、技术与研究机构（A*STAR））；Nanyang Technological University（南洋理工大学）；University of Science and Technology of China（中国科学技术大学）；Jilin University（吉林大学）
AMA: Adaptive Memory via Multi-Agent Collaboration
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Shandong University（山东大学）；Nanyang Technological University（南洋理工大学）；Southern University of Science and Technology（南方科技大学）
In Self-Supervised Learning (SSL), it is known that frequent occurrences of the collision in which target data and its negative samples share the same class can decrease performance. Especially in real-world data such as crawled data or robot-gathered observations, collisions may occur more often due to the duplicates in the data. To deal with this problem, we claim that sampling negative samples from the adaptively debiased distribution in the memory makes the model more stable than sampling from a biased dataset directly. In this paper, we introduce a novel SSL framework with adaptive Duplic…
The BioRobotics Institute（生物机器人研究所）；Scuola Superiore Sant’Anna（圣安娜高等研究院）
This work presents an adaptive architecture that performs online learning and faces catastrophic forgetting issues by means of episodic memories and prediction-error driven memory consolidation. In line with evidences from the cognitive science and neuroscience, memories are retained depending on their congruency with the prior knowledge stored in the system. This is estimated in terms of prediction error resulting from a generative model. Moreover, this AI system is transferred onto an innovative application in the horticulture industry: the learning and transfer of greenhouse models. This wo…
ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization
Department of Mathematics and Computer Science（数学与计算机科学系）；Sri Sathya Sai Institute of Higher Learning（Sri Sathya Sai高等研究院）；Department of Computer Science and Engineering（计算机科学与工程系）；Indian Institute of Technology Ropar（印度理工学院罗帕尔分校）；AI Performance Engineer（AI性能工程师）；Red Hat（红帽公司）
Adaptive Path-Memory Network for Temporal Knowledge Graph Reasoning
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences（中国科学院大学）；University of Macau（澳门大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Central Florida（中佛罗里达大学）
SWE-MeM: Learning Adaptive Memory Management for Long-Horizon Coding Agents
The Chinese University of Hong Kong, China（香港中文大学）；Shanghai Jiao Tong University, China（上海交通大学）；Tsinghua University, China（清华大学）；ByteDance, China（字节跳动）
FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding
Institute of Trustworthy Embodied AI（可信具身人工智能研究所）；Fudan University（复旦大学）；Shanghai Innovation Institute（上海创新研究院）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）；University of Maryland, College Park（马里兰大学 College Park 分校）
SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
University of Science and Technology of China（中国科学技术大学）；Fudan University（复旦大学）；Georgia Institute of Technology（佐治亚理工学院）；Shanghai Jiao Tong University（上海交通大学）
Google Brain（谷歌大脑）；University of California, Berkeley（加利福尼亚大学伯克利分校）
In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter second-moment estimators requires memory equal to the number of parameters. For the case of neural network weight matrices, we propose maintaining only the per-row and per-column sums of these moving averages, and estimating the per-parameter second moments based on these sums. We demonstrate empirically that this method produces similar results to the basel…
Imperial College London（帝国理工学院）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；Austrian Academy of Sciences（奥地利科学院）
Central to the success of adaptive systems is their ability to interpret signals from their environment and respond accordingly -- they act as agents interacting with their surroundings. Such agents typically perform better when able to execute increasingly complex strategies. This comes with a cost: the more information the agent must recall from its past experiences, the more memory it will need. Here we investigate the power of agents capable of quantum information processing. We uncover the most general form a quantum agent need adopt to maximise memory compression advantages, and provide …
