Related papers: CELI: Controller-Embedded Language Model Interacti…

A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner. Rather than merely reacting to commands, it would continuously listen, reason, and respond…

Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder to the input of the large language model (LLM). This static architecture…

Assistant AI agents should be capable of rapidly acquiring novel skills and adapting to new user preferences. Traditional frameworks like imitation learning and reinforcement learning do not facilitate this capability because they support…

While large-scale language models (LLMs) have demonstrated remarkable capabilities in specific natural language processing (NLP) tasks, they may still lack proficiency compared to specialized models in certain domains, such as grammatical…

The applications of large language models (LLMs) have been widely spread across all domains. However, the basic abilities such as the controllability of LLMs are still limited. To address this, we propose "Self-controller", a novel agentic…

Multi-modal Large Language Models (MLLMs) have recently exhibited impressive general-purpose capabilities by leveraging vision foundation models to encode the core concepts of images into representations. These are then combined with…

The growing diversity of large language models (LLMs) means users often need to compare and combine outputs from different models to obtain higher-quality or more comprehensive responses. However, switching between separate interfaces and…

Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at test time without model fine-tuning. Despite its success,…

Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…

We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model…

By integrating tools from external APIs, Large Language Models (LLMs) have expanded their promising capabilities in a diverse spectrum of complex real-world tasks. However, testing, evaluation, and analysis of LLM tool use remain in their…

We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM…

Large language models (LLMs) have advanced the field of artificial intelligence (AI) and are a powerful enabler for interactive systems. However, they still face challenges in long-term interactions that require adaptation towards the user…

Event-driven reactive functionalities are an urgent need in nowadays distributed service-oriented applications and (Semantic) Web-based environments. An important problem to be addressed is how to correctly and efficiently capture and…

Machine learning (ML) models have significantly impacted various domains in our everyday lives. While large language models (LLMs) offer intuitive interfaces and versatility, task-specific ML models remain valuable for their efficiency and…

The rapid emergence of new entities -- driven by cultural shifts, evolving trends, and personalized user data -- poses a significant challenge for existing Speech Large Language Models (Speech LLMs). While these models excel at general…

Large language models (LLMs) excel at explicit reasoning, but their implicit computational strategies remain underexplored. Decades of psychophysics research show that humans intuitively process and integrate noisy signals using…

Speech synthesis has significantly advanced from statistical methods to deep neural network architectures, leading to various text-to-speech (TTS) models that closely mimic human speech patterns. However, capturing nuances such as emotion…

The rapid progress of Multimodal Large Language Models(MLLMs) has transformed the AI landscape. These models combine pre-trained LLMs with various modality encoders. This integration requires a systematic understanding of how different…

Generating clinical reports that summarize abnormal patterns, diagnostic findings, and clinical interpretations from long-term EEG recordings remains labor-intensive. We present CELM, the first clinical EEG-to-Language foundation model…