Related papers: On Memory Construction and Retrieval for Personali…

Large Language Models (LLMs) face significant challenges in long-context processing, including quadratic computational costs, information forgetting, and the context fragmentation inherent in retrieval-augmented generation (RAG). We propose…

Memory systems have been designed to leverage past experiences in Large Language Model (LLM) agents. However, many deployed memory systems primarily optimize compression and storage, with comparatively less emphasis on explicit, closed-loop…

Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations.…

Temporal reasoning in multi-session dialogues presents a significant challenge which has been under-studied in previous temporal reasoning benchmarks. To bridge this gap, we propose a new evaluation task for temporal reasoning in…

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose \textit{Sequential…

This paper proposes a novel Sequence-to-Sequence (Seq2Seq) model integrating the structure of Hidden Semi-Markov Models (HSMMs) into its attention mechanism. In speech synthesis, it has been shown that methods based on Seq2Seq models using…

While large language models (LLMs) have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanism offers a flexible solution for managing long contexts, utilizing…

Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…

Users try to articulate their complex information needs during search sessions by reformulating their queries. To make this process more effective, search engines provide related queries to help users in specifying the information need in…

Semantic communication (SemCom) has emerged as a promising technique for the next-generation communication systems, in which the generation at the receiver side is allowed with semantic features' recovery. However, the majority of existing…

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…

Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each…

Effective memory management is essential for large language model (LLM) agents handling long-term interactions. Current memory frameworks typically treat agents as passive "recorders" and retrieve information without understanding its…

We leverage the modern advancements in talking head generation to propose an end-to-end system for talking head video compression. Our algorithm transmits pivot frames intermittently while the rest of the talking head video is generated by…

The rapid development of multimodal AI and Large Language Models (LLMs) has greatly enhanced real-time interaction, decision-making, and collaborative tasks. However, in wireless multi-agent scenarios, limited bandwidth poses significant…

Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over…

Large language model assistants are increasingly expected to retain and reason over information accumulated across many sessions. We introduce EngramaBench, a benchmark for long-term conversational memory built around five personas, one…

Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (SLM) to serve as an…

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

Multimodal large language models (MLLMs) have made remarkable strides, largely driven by their ability to process increasingly long and complex contexts, such as high-resolution images, extended video sequences, and lengthy audio input.…