Related papers: Hierarchical Learning for Generation with Long Sou…

Large language models have limited context capacity, hindering reasoning over long conversations. We propose the Hierarchical Aggregate Tree memory structure to recursively aggregate relevant dialogue context through conditional tree…

Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse…

The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal downsampling, combining level-specific score matrices through learned convex weights. The…

Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…

Hierarchical neural architectures are often used to capture long-distance dependencies and have been applied to many document-level tasks such as summarization, document segmentation, and sentiment analysis. However, effective usage of such…

We present a Three-level Hierarchical Transformer Network (3-level-HTN) for modeling long-term dependencies across clinical notes for the purpose of patient-level prediction. The network is equipped with three levels of Transformer-based…

The attention mechanisms are playing a boosting role in advancements in sequence-to-sequence problems. Transformer architecture achieved new state of the art results in machine translation, and it's variants are since being introduced in…

Extractive summarization for long documents is challenging due to the extended structured input context. The long-distance sentence dependency hinders cross-sentence relations modeling, the critical step of extractive summarization. This…

Prompt learning has become a prevalent strategy for adapting vision-language foundation models to downstream tasks. As large language models (LLMs) have emerged, recent studies have explored the use of category-related descriptions as input…

Relations between words are governed by hierarchical structure rather than linear ordering. Sequence-to-sequence (seq2seq) models, despite their success in downstream NLP applications, often fail to generalize in a hierarchy-sensitive…

Scientific document summarization has been a challenging task due to the long structure of the input text. The long input hinders the simultaneous effective modeling of both global high-order relations between sentences and local…

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…

Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods. Training the hierarchical encoder…

Previous approaches for video summarization mainly concentrate on finding the most diverse and representative visual contents as video summary without considering the user's preference. This paper addresses the task of query-focused video…

Despite advancements in multimodal large language models (MLLMs), current approaches struggle in medium-to-long video understanding due to frame and context length limitations. As a result, these models often depend on frame sampling, which…

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical…

We describe a neural transducer that maintains the flexibility of standard sequence-to-sequence (seq2seq) models while incorporating hierarchical phrases as a source of inductive bias during training and as explicit constraints during…

Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This highlights the difficulty of enabling hierarchical reasoning…

The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation. In this work, we propose and compare several modifications of HAN in which the…