Related papers: Text2Mem: A Unified Memory Operation Language for …

Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged…

Recent progress in large models has led to significant advances in unified multimodal generation and understanding. However, the development of models that unify motion-language generation and understanding remains largely underexplored.…

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Over decades, neuroscience has accumulated a wealth of research results in the text modality that can be used to explore cognitive processes. Meta-analysis is a typical method that successfully establishes a link from text queries to brain…

Personalized and continuous interactions are critical for LLM-based conversational agents, yet finite context windows and static parametric memory hinder the modeling of long-term, cross-session user states. Existing approaches, including…

Large Language Models (LLMs) often struggle with the precise logic and schema alignment required for complex Text-to-SQL tasks. While current methods rely heavily on static prompting, they lack the ability to dynamically adapt and…

Encoder-decoder models have achieved remarkable success in speech and text tasks, yet efficiently adapting these models to diverse uni/multi-modal scenarios remains an open challenge. In this paper, we propose Whisper-UT, a unified and…

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It is determined by whether the final returned set jointly…

Large Language Models (LLMs) face significant computational and memory constraints when processing long contexts, despite growing demand for applications requiring reasoning over extensive documents, multi-session dialogues, and book length…

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning community is investing considerable effort in generating data…

We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty…

Large language models (LLMs) have achieved remarkable progress across diverse tasks, yet their internal mechanisms remain largely opaque. In this work, we investigate a fundamental question: to what extent can the original input text be…

Text embeddings from large language models (LLMs) have achieved excellent results in tasks such as information retrieval, semantic textual similarity, etc. In this work, we show an interesting finding: when feeding a text into the LLM-based…

Text-to-SQL technology has evolved rapidly, with diverse academic methods achieving impressive results. However, deploying these techniques in real-world systems remains challenging due to limited integration tools. Despite these advances,…

Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high…

Recent advances in speech-enabled language models have shown promising results in building intelligent voice assistants. However, most existing approaches rely on large-scale paired speech-text data and extensive computational resources,…

Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs…

Modern computer systems are awash in a sea of asynchronous events. There is an increasing need for a declarative language that can permit business users to specify complex event-processing rules. Such rules should be able to correlate…

Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments. To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism…