Related papers: On Memory Construction and Retrieval for Personali…
Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack…
Embedding-based retrieval models have made significant strides in retrieval-augmented generation (RAG) techniques for text and multimodal large language models (LLMs) applications. However, when it comes to speech larage language models…
Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability…
Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…
Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has…
Recent research has focused on applying speech large language model (SLLM) to improve speech emotion recognition (SER). However, the inherently high frame rate in speech modality severely limits the signal processing and understanding…
Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…
Using a sequence-to-sequence framework, many neural conversation models for chit-chat succeed in naturalness of the response. Nevertheless, the neural conversation models tend to give generic responses which are not specific to given…
Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existing memory systems often store…
Long-term memory plays a critical role in personal interaction, considering long-term memory can better leverage world knowledge, historical information, and preferences in dialogues. Our research introduces PerLTQA, an innovative QA…
Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems represent conversation history as unstructured embedding…
Most of the semantic segmentation approaches have been developed for single image segmentation, and hence, video sequences are currently segmented by processing each frame of the video sequence separately. The disadvantage of this is that…
This paper addresses the limitations of large language models in understanding long-term context. It proposes a model architecture equipped with a long-term memory mechanism to improve the retention and retrieval of semantic information…
Prompt compression reduces inference cost and context length in large language models, but prior evaluations focus primarily on autoregressive architectures. This study investigates whether prompt compression transfers effectively to…
Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time.…
Existing agent memory systems universally follow what we term a Memory-as-Tool paradigm where a single query triggers one-shot retrieval of flat passage lists, suffering from passive invocation, reasoning-retrieval decoupling, and…
Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the…
The future of conversational agents will provide users with personalized information responses. However, a significant challenge in developing models is the lack of large-scale dialogue datasets that span multiple sessions and reflect…
Persistent conversational AI systems face a choice between passing full conversation histories to a long-context large language model (LLM) and maintaining a dedicated memory system that extracts and retrieves structured facts. We compare a…
Dialogue topic segmentation supports summarization, retrieval, memory management, and conversational continuity. Despite decades of work, evaluation practice remains dominated by strict boundary matching and F1-based metrics. Modern large…