相关论文: Exploring the Capability of Mamba in Speech Applic…

Recent advances in sequence modeling have introduced selective SSMs as promising alternatives to Transformer architectures, offering theoretical computational efficiency and sequence processing advantages. A comprehensive understanding of…

We present SAM, a State-space Audio-language Model that integrates an audio encoder with a Mamba-2 backbone. SAM-2.7B achieves 21.1 mAP on AudioSet and 17.6 SPICE on AudioCaps, matching or surpassing larger 7B transformer-based models with…

The Interspeech 2025 URGENT Challenge aimed to advance universal, robust, and generalizable speech enhancement by unifying speech enhancement tasks across a wide variety of conditions, including seven different distortion types and five…

Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks. Recently, researchers introduced Mamba, an…

Large pre-trained models have achieved outstanding results in sequence modeling. The Transformer block and its attention mechanism have been the main drivers of the success of these models. Recently, alternative architectures, such as…

Token-free language models learn directly from raw bytes and remove the inductive bias of subword tokenization. Operating on bytes, however, results in significantly longer sequences. In this setting, standard autoregressive Transformers…

We introduce Llamba, a family of efficient recurrent language models distilled from Llama-3.x into the Mamba architecture. The series includes Llamba-1B, Llamba-3B, and Llamba-8B, which achieve higher inference throughput and handle…

Modern large language models are built on sequence modeling via next-token prediction. While the Transformer remains the dominant architecture for sequence modeling, its quadratic decoding complexity in sequence length poses a major…

Transformers have become increasingly popular for image super-resolution (SR) tasks due to their strong global context modeling capabilities. However, their quadratic computational complexity necessitates the use of window-based attention…

Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global…

State-space models (SSMs), particularly Mamba, emerge as an efficient Transformer alternative with linear complexity for long-sequence modeling. Recent empirical works demonstrate Mamba's in-context learning (ICL) capabilities competitive…

State-space models (SSMs), particularly Mamba, have become powerful architectures for sequence modeling, yet their internal dynamics remain poorly understood compared to attention-based models. We introduce and validate the Influence Score,…

Probabilistic State Space Models (SSMs) are essential for Reinforcement Learning (RL) from high-dimensional, partial information as they provide concise representations for control. Yet, they lack the computational efficiency of their…

Audio super-resolution aims to enhance low-resolution signals by creating high-frequency content. In this work, we modify the architecture of AERO (a state-of-the-art system for this task) for music super-resolution. SPecifically, we…

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity…

The rapid growth of statutory corpora and judicial decisions requires scalable legal AI systems capable of classification and retrieval over extremely long contexts. Transformer-based architectures (e.g., Longformer, DeBERTa) dominate…

Recent advancements in imitation learning, particularly with the integration of LLM techniques, are set to significantly improve robots' dexterity and adaptability. This paper proposes using Mamba, a state-of-the-art architecture with…

Speech intelligibility prediction (SIP) models have been used as objective metrics to assess intelligibility for hearing-impaired (HI) listeners. In the Clarity Prediction Challenge 2 (CPC2), non-intrusive binaural SIP models based on…

Mamba has emerged as a powerful model for efficiently addressing tasks involving temporal and spatial data. Regarding the escalating heterogeneity and dynamics in wireless networks, Mamba holds the potential to revolutionize wireless…

End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recognizers dominate current research, their quadratic complexity…