Related papers: TraceMem: Weaving Narrative Memory Schemata from U…
Human-agent dialogues often exhibit topic continuity-a stable thematic frame that evolves through temporally adjacent exchanges-yet most large language model (LLM) agent memory systems fail to preserve it. Existing designs follow a…
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts. Recent works like Recursive Language…
Recent advances in text-to-speech (TTS) synthesis, particularly those leveraging large language models (LLMs), have significantly improved expressiveness and naturalness. However, generating human-like, interactive dialogue speech remains…
External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…
Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions,…
Because of their superior ability to preserve sequence information over time, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network with a more complex computational unit, have obtained strong results on a variety of…
The traditional Dialogue State Tracking (DST) problem aims to track user preferences and intents in user-agent conversations. While sufficient for task-oriented dialogue systems supporting narrow domain applications, the advent of Large…
Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by feeding all the user's past memory into the prompt, which…
User simulation is essential for generating enough data to train a statistical spoken dialogue system. Previous models for user simulation suffer from several drawbacks, such as the inability to take dialogue history into account, the need…
Large language models (LLMs) can generate fluent dialogue, but prior works lack situational grounding, dynamic strategy control, and evaluation aligned with clinical standards in motivational interviewing (MI). We introduce StoryMI, a…
Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…
Comprehending extended audiovisual experiences remains challenging for computational systems, particularly temporal integration and cross-modal associations fundamental to human episodic memory. We introduce HippoMM, a computational…
Large language models show promise for embodying historical characters in dialogue systems, but existing approaches face a critical trade-off: simple retrieval-augmented generation produces shallow responses, while multi-stage reflection…
In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…
Semiparametric language models (LMs) have shown promise in continuously learning from new text data by combining a parameterized neural LM with a growable non-parametric memory for memorizing new content. However, conventional…
In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical…
Recent advances in large language models (LLMs) enable compelling story generation, but connecting narrative text to playable visual environments remains an open challenge in procedural content generation (PCG). We present a lightweight…
We introduce a comprehensive benchmark for conversational memory evaluation containing 75,336 question-answer pairs across diverse categories including user facts, assistant recall, abstention, preferences, temporal changes, and implicit…
Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or…
The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the Collaborative Memory Transformer (CoMeT), a novel…