Related papers: Jamba-1.5: Hybrid Transformer-Mamba Models at Scal…

Recent advancements in imitation learning have been largely fueled by the integration of sequence models, which provide a structured flow of information to effectively mimic task behaviours. Currently, Decision Transformer (DT) and…

Human engagement estimation in conversational scenarios is essential for applications such as adaptive tutoring, remote healthcare assessment, and socially aware human--computer interaction. Engagement is a dynamic, multimodal signal…

We introduce llama-embed-nemotron-8b, an open-weights text embedding model that achieves state-of-the-art performance on the Multilingual Massive Text Embedding Benchmark (MMTEB) leaderboard as of October 21, 2025. While recent models show…

In the era of large-scale pre-trained models, effectively adapting general knowledge to specific affective computing tasks remains a challenge, particularly regarding computational efficiency and multimodal heterogeneity. While…

State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL), a variant of meta-learning concerning the learned ability to solve tasks during a neural network forward pass, exploiting contextual…

Real-time speech conversation is essential for natural and efficient human-machine interactions, requiring duplex and streaming capabilities. Traditional Transformer-based conversational chatbots operate in a turn-based manner and exhibit…

The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However,…

State space models (SSMs) like Mamba have recently attracted much attention. Compared to Transformer-based large language models (LLMs), Mamba achieves linear computation complexity with the sequence length and demonstrates superior…

The topic of speech separation involves separating mixed speech with multiple overlapping speakers into several streams, with each stream containing speech from only one speaker. Many highly effective models have emerged and proliferated…

Transformer and its derivatives have achieved success in diverse tasks across computer vision, natural language processing, and speech processing. To reduce the complexity of computations within the multi-head self-attention mechanism in…

Expanding the long-context capabilities of Multi-modal Large Language Models~(MLLMs) is critical for advancing video understanding and high-resolution image analysis. Achieving this requires systematic improvements in model architecture,…

Developing high-quality large language models (LLMs) for moderately resourced languages presents unique challenges in data availability, model adaptation, and evaluation. We introduce Llama-3-Nanda-10B-Chat, or Nanda for short, a…

Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense…

State-space models (SSMs), exemplified by S4, have introduced a novel context modeling method by integrating state-space techniques into deep learning. However, they struggle with global context modeling due to their data-independent…

Dynamic graph embedding has emerged as an important technique for modeling complex time-evolving networks across diverse domains. While transformer-based models have shown promise in capturing long-range dependencies in temporal graph data,…

Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities. However, they often suffer from quadratic complexity in both GPU memory usage and…

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…

Self attention encoders such as Bidirectional Encoder Representations from Transformers(BERT) scale quadratically with sequence length, making long context modeling expensive. Linear time state space models, such as Mamba, are efficient;…

While Transformers have been the main architecture behind deep learning's success in language modeling, state-space models (SSMs) such as Mamba have recently been shown to match or outperform Transformers at small to medium scale. We show…

The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading…