Related papers: AssoMem: Scalable Memory QA with Multi-Signal Asso…
Large language models (LLMs) are increasingly deployed in multi-turn dialogue settings, yet their behavior remains bottlenecked by naive history management strategies. Replaying the full conversation at every turn is simple but costly,…
Audio Question Answering (AQA) constitutes a pivotal task in which machines analyze both audio signals and natural language questions to produce precise natural language answers. The significance of possessing high-quality, diverse, and…
Transformative innovations in model architectures have introduced hierarchical embedding augmentation as a means to redefine the representation of tokens through multi-level semantic structures, offering enhanced adaptability to complex…
AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based…
Several recent works have suggested to represent semantic relations with questions and answers, decomposing textual information into separate interrogative natural language statements. In this paper, we consider three QA-based semantic…
Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recall. In realistic interactions, appropriate responses often…
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external storage require complex management and incur storage overhead,…
We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect…
Navigating complex environments requires robots to effectively store observations as memories and leverage them to answer human queries about spatial locations, which is a critical yet underexplored research challenge. While prior work has…
AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events. A concession during a client negotiation encodes as a…
Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction. Related queries therefore repeat similar multi-hop…
Given the similarity between facial expression categories, the presence of compound facial expressions, and the subjectivity of annotators, facial expression recognition (FER) datasets often suffer from ambiguity and noisy labels. Ambiguous…
Attention mechanism has been proven effective on natural language processing. This paper proposes an attention boosted natural language inference model named aESIM by adding word attention and adaptive direction-oriented attention…
Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics…
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…
Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…
Long-term memory is essential for natural, realistic dialogue. However, current large language model (LLM) memory systems rely on either brute-force context expansion or static retrieval pipelines that fail on edge-constrained devices. We…
Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…
Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training. The core…
The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we explore a novel mechanism to improve model generalization via…