Related papers: MemOS: A Memory OS for AI System

Real-world multimodal applications often require any-to-any capabilities, enabling both understanding and generation across modalities including text, image, audio, and video. However, integrating the strengths of autoregressive language…

Operating system (OS) kernel tuning is a critical yet challenging problem for performance optimization, due to the large configuration space, complex interdependencies among configuration options, and the rapid evolution of kernel versions.…

Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low…

A critical challenge remains unresolved as generative AI systems are quickly implemented in various organizational settings. Despite significant advances in memory components such as RAG, vector stores, and LLM agents, these systems still…

Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments and changing goals. This capacity, known as working memory, is fundamental to human reasoning and intelligence. Despite…

As Large Language Models (LLMs) evolve from static dialogue interfaces to autonomous general agents, effective memory is paramount to ensuring long-term consistency. However, existing benchmarks primarily focus on casual conversation or…

Large Language Models (LLMs) have emerged as transformative tools for natural language understanding and user intent resolution, enabling tasks such as translation, summarization, and, increasingly, the orchestration of complex workflows.…

The field of Artificial Intelligence (AI) continues to drive transformative innovations, with significant progress in conversational interfaces, autonomous vehicles, and intelligent content creation. Since the launch of ChatGPT in late…

Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…

Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time. The primary culprits are the activations, whose memory footprints scale linearly with sequence length. We…

Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over time. However, existing benchmarks either evaluate…

Large Language Models (LLMs) face fundamental limitations in context management despite recent advances extending context windows to millions of tokens. We propose Cognitive Workspace, a novel paradigm that transcends traditional…

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Large language model (LLM) agents increasingly operate in settings where a single context window is far too small to capture what has happened, what was learned, and what should not be repeated. Memory -- the ability to persist, organize,…

Knowing that the generative capabilities of large language models (LLM) are sometimes hampered by tendencies to hallucinate or create non-factual responses, researchers have increasingly focused on methods to ground generated outputs in…

Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that require specialized processing or up-to-date data. While…

Large language model (LLM) agents increasingly rely on external memory systems to remain consistent across long-horizon interactions, but little empirical work has been done to understand the specific failure modes and design choices that…

Knowledge-intensive conversations supported by large language models (LLMs) have become one of the most popular and helpful applications that can assist people in different aspects. Many current knowledge-intensive applications are centered…

Although Transformers with fully connected self-attentions are powerful to model long-term dependencies, they are struggling to scale to long texts with thousands of words in language modeling. One of the solutions is to equip the model…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…