As an extension of traditional visual single object tracking (SOT) task [2, 3, 4], VLT can harness the complementary advantages of multiple modalities. Therefore, vision-language trackers (VLTs) have the potential to achieve more promising tracking performance, which has recently attracted widespreadattention[5,6,7,8].

However, most existing vision-language trackers still overly rely on initial fixed multimodal prompts, which struggle to provide effective guidance for dynamically changing targets.

Memory extraction is crucial for maintaining coherent ultra-long dialogues in human-robot role-playing scenarios. However, existing methods often exhibit uncontrolled memory growth. To address this, we propose MOOM, the first dual-branch memory plugin that leverages literary theory by modeling plot development and character portrayal as core storytelling elements. Specifically, one branch summarizes plot conflicts across multiple time scales, while the other extracts the user's character profile. MOOM further integrates a forgetting mechanism, inspired by the ``competition-inhibition'' memory theory, to constrain memory capacity and mitigate uncontrolled growth. Furthermore, we present ZH-4O, a Chinese ultra-long dialogue dataset specifically designed for role-playing, featuring dialogues that average 600 turns and include manually annotated memory information. Experimental results demonstrate that MOOM outperforms all state-of-the-art memory extraction methods, requiring fewer large language model invocations while maintaining a controllable memory capacity.

Multimodal large language models (MLLMs) are attracting growing attention in the development of Graphical User Interface (GUI) agents. Existing approaches often rely on historical screenshots or actions to implicitly represent the task state. This reliance poses challenges for GUI agents in accurately understanding task states and underscores the absence of effective mechanisms to store critical information in complex and lengthy cross-app tasks. To address these challenges, we propose Chain-of-Memory (CoM), a novel approach for explicitly modeling short-term and long-term memory in GUI agents. CoM achieves this by capturing action descriptions, integrating task-relevant screen information, and maintaining a dedicated memory module to store and manage this information. By leveraging explicit memory representations, CoM enables GUI agents to better understand task states and retain critical historical information persistently. To equip GUI agents with memory management capabilities and evaluate the effectiveness of CoM, we developed the GUI Odyssey-CoM, a dataset comprising 111k screen-action pairs annotated with Chain-of-Memory. Experimental results demonstrate that CoM significantly improves GUI agents' performance in cross-application tasks. Additionally, GUI Odyssey-CoM enables 7B models to achieve memory management capabilities comparable to 72B models. The dataset and code will be open-sourced.

This study is the first to clearly identify the functions required to construct artificial entities capable of behaving autonomously like humans, and organizes them into a three-layer functional hierarchy. Specifically, it defines three levels: Core Functions, which enable interaction with the external world; the Integrative Evaluation Function, which selects actions based on perception and memory; and the Self Modification Function, which dynamically reconfigures behavioral principles and internal components. Based on this structure, the study proposes a stepwise model of autonomy comprising reactive, weak autonomous, and strong autonomous levels, and discusses its underlying design principles and developmental aspects. It also explores the relationship between these functions and existing artificial intelligence design methods, addressing their potential as a foundation for general intelligence and considering future applications and ethical implications. By offering a theoretical framework that is independent of specific technical methods, this work contributes to a deeper understanding of autonomy and provides a foundation for designing future artificial entities with strong autonomy.

Researchers working in The N.1 Institute for Health at the National University Of Singapore (NUS), led by Assistant Professor Camilo Libedinsky from NUS Psychology, and Senior Lecturer Shih-Cheng Yen from the Innovation and Design Programme at NUS Engineering, have discovered that a population of neurons in the brain's frontal lobe contain stable short-term memory information within dynamically-changing neural activity. This discovery may have far-reaching consequences in understanding how organisms have the ability to perform multiple mental operations simultaneously, such as remembering, paying attention and making a decision, using a brain of limited size. The results of this study were published in the journal Nature Communications on 1 November 2019. In the human brain, the frontal lobe plays an important role in processing short-term memories. Short-term memory has a low capacity to retain information.

Researchers working in The N.1 Institute for Health at NUS, led by Assistant Professor Camilo Libedinsky from NUS Psychology, and Senior Lecturer Shih-Cheng Yen from the Innovation and Design Programme at NUS Engineering, have discovered that a population of neurons in the brain's frontal lobe contain stable short-term memory information within dynamically-changing neural activity. This discovery may have far-reaching consequences in understanding how organisms have the ability to perform multiple mental operations simultaneously, such as remembering, paying attention and making a decision, using a brain of limited size. The results of this study were published in the journal Nature Communications on 1 November 2019. In the human brain, the frontal lobe plays an important role in processing short-term memories. Short-term memory has a low capacity to retain information.