Related papers: UniMC: A Unified Framework for Long-Term Memory Co…

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our…

Large Language Models (LLMs) have made significant progress in dialogue, yet redundant memory contexts severely limit their effectiveness in long-term dialogue agents. External memory systems have been proposed to improve memory…

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model with various neural…

As large language models (LLMs) evolve into autonomous agents, persistent memory at the API layer is essential for enabling context-aware behavior across LLMs and multi-session interactions. Existing approaches force vendor lock-in and rely…

Building an end-to-end conversational agent for multi-domain task-oriented dialogues has been an open challenge for two main reasons. First, tracking dialogue states of multiple domains is non-trivial as the dialogue agent must obtain…

Reference Expression Generation (REG) and Comprehension (REC) are two highly correlated tasks. Modeling REG and REC simultaneously for utilizing the relation between them is a promising way to improve both. However, the problem of distinct…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

Existing retrieval-based methods have made significant strides in maintaining long-term conversations. However, these approaches face challenges in memory database management and accurate memory retrieval, hindering their efficacy in…

Representation learning is a widely adopted framework for learning in data-scarce environments, aiming to extract common features from related tasks. While centralized approaches have been extensively studied, decentralized methods remain…

As the use of interactive machines grow, the task of Emotion Recognition in Conversation (ERC) became more important. If the machine-generated sentences reflect emotion, more human-like sympathetic conversations are possible. Since emotion…

Associative learning--forming links between co-occurring items--is fundamental to human cognition, reshaping internal representations in complex ways. Testing hypotheses on how representational changes occur in biological systems is…

While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. In this paper, we introduce an…

Conventional approaches to relation extraction usually require a fixed set of pre-defined relations. Such requirement is hard to meet in many real applications, especially when new data and relations are emerging incessantly and it is…

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

Processing long contexts presents a significant challenge for large language models (LLMs). While recent advancements allow LLMs to handle much longer contexts than before (e.g., 32K or 128K tokens), it is computationally expensive and can…

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In…

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Many advances in Natural Language Processing have been based upon more expressive models for how inputs interact with the context in which they occur. Recurrent networks, which have enjoyed a modicum of success, still lack the…