Related papers: DuplexMamba: Enhancing Real-time Speech Conversati…

Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amounts of lifelong user…

We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture. Jamba is a hybrid Transformer-Mamba mixture of experts architecture, providing high throughput and low memory usage across context lengths,…

Recent advancements in the Mamba architecture, with its linear computational complexity, being a promising alternative to transformer architectures suffering from quadratic complexity. While existing works primarily focus on adapting Mamba…

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single temporal scale,…

In multivariate time-series forecasting (MTSF), extracting the temporal correlations of the input sequences is crucial. While popular Transformer-based predictive models can perform well, their quadratic computational complexity results in…

Network traffic classification is a crucial research area aiming to enhance service quality, streamline network management, and bolster cybersecurity. To address the growing complexity of transmission encryption techniques, various machine…

Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to extend a single coherent sequence and do not naturally…

MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or…

Sequential recommendation (SR), which encodes user activity to predict the next action, has emerged as a widely adopted strategy in developing commercial personalized recommendation systems. Although Transformer-based models have proven…

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances, such as Mamba, further enhance SSMs with input-dependent…

In recent years, deep learning has shown near-expert performance in segmenting complex medical tissues and tumors. However, existing models are often task-specific, with performance varying across modalities and anatomical regions.…

State space models have shown significant promise in Natural Language Processing (NLP) and, more recently, computer vision. This paper introduces a new methodology leveraging Mamba and Masked Autoencoder networks for point cloud data in…

Transformer-based text to speech (TTS) model (e.g., Transformer TTS~\cite{li2019neural}, FastSpeech~\cite{ren2019fastspeech}) has shown the advantages of training and inference efficiency over RNN-based model (e.g.,…

Transformer-based trajectory optimization methods have demonstrated exceptional performance in offline Reinforcement Learning (offline RL). Yet, it poses challenges due to substantial parameter size and limited scalability, which is…

In the information retrieval (IR) area, dense retrieval (DR) models use deep learning techniques to encode queries and passages into embedding space to compute their semantic relations. It is important for DR models to balance both…

Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end…

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in…

Recent efforts on image restoration have focused on developing "all-in-one" models that can handle different degradation types and levels within single model. However, most of mainstream Transformer-based ones confronted with dilemma…

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…

In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of original LLM capabilities, without using any carefully curated paired…