相关论文: Enhancing RWKV-based Language Models for Long-Sequ…

Currently, most multimodal studies are based on large language models (LLMs) with quadratic-complexity Transformer architectures. While linear models like RNNs enjoy low inference costs, their application has been largely limited to the…

As is known, hybrid quadratic and subquadratic attention models in multi-head architectures have surpassed both Transformer and Linear RNN models , with these works primarily focusing on reducing KV complexity and improving efficiency. For…

Long-horizon conversational agents rely on memory systems with increasingly sophisticated retrieval mechanisms. However, retrieved fragments are typically fed to the language model as unstructured text, lacking the relational, temporal, and…

Human-AI interaction thrives on intuitive and efficient interfaces, among which voice stands out as a particularly natural and accessible modality. Recent advancements in transformer-based text-to-speech (TTS) systems, such as Fish-Speech,…

Large language models (LLMs) increasingly require mechanisms for continual adaptation without full retraining. However, sequential updates can lead to catastrophic forgetting, where new edits degrade previously acquired knowledge. This work…

Modern Recurrent Neural Networks (RNNs), such as RWKV, are distinguished by their powerful short-range modeling capabilities and efficient fixed-size states, which constitute a core advantage over standard Transformers. However, there is a…

Maintaining semantic consistency over extended text sequences remains a fundamental challenge in long-form text generation, where conventional training methodologies often struggle to prevent contextual drift and coherence degradation. A…

Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information…

Textbook question answering (TQA) is a challenging task in artificial intelligence due to the complex nature of context needed to answer complex questions. Although previous research has improved the task, there are still some limitations…

Constructing responses in task-oriented dialogue systems typically relies on information sources such the current dialogue state or external databases. This paper presents a novel approach to knowledge-grounded response generation that…

Recurrent neural networks (RNNs) are powerful dynamical models for data with complex temporal structure. However, training RNNs has traditionally proved challenging due to exploding or vanishing of gradients. RNN models such as LSTMs and…

Recently, Transformers (e.g., Audio Spectrogram Transformers, AST) and state-space models (e.g., Audio Mamba, AuM) have achieved remarkable progress in audio modeling. However, the O(L^2) computational complexity of the Transformer…

Standard transformer-based language models, while powerful for general text, often struggle with the fine-grained syntax and entity relationships in complex technical, engineering documents. To address this, we propose the Contextual Graph…

Retrieval-augmented generation (RAG) systems have been widely adopted in contemporary large language models (LLMs) due to their ability to improve generation quality while reducing the required input context length. In this work, we focus…

Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields. However, substantial computational complexity poses limitations for their application in long-context tasks, such as high-resolution…

Grounding dialogue system with external knowledge is a promising way to improve the quality of responses. Most existing works adopt knowledge graphs (KGs) as the external resources, paying attention to the contribution of entities in the…

A latent-variable model is introduced for text matching, inferring sentence representations by jointly optimizing generative and discriminative objectives. To alleviate typical optimization challenges in latent-variable models for text, we…

One of the strengths of traditional convolutional neural networks (CNNs) is their inherent translational invariance. However, for the task of speech enhancement in the time-frequency domain, this property cannot be fully exploited due to a…

Semantic communication is a promising technology to improve communication efficiency by transmitting only the semantic information of the source data. However, traditional semantic communication methods primarily focus on data…

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…