Related papers: MamTra: A Hybrid Mamba-Transformer Backbone for Sp…

Current end-to-end multi-modal models utilize different encoders and decoders to process input and output information. This separation hinders the joint representation learning of various modalities. To unify multi-modal processing, we…

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…

Transformers have become the backbone of modern Large Language Models (LLMs); however, their inference overhead grows linearly with the sequence length, posing challenges for modeling long sequences. In light of this, Mamba has attracted…

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT)…

We introduce MAVE (Mamba with Cross-Attention for Voice Editing and Synthesis), a novel autoregressive architecture for text-conditioned voice editing and high-fidelity text-to-speech (TTS) synthesis, built on a cross-attentive Mamba…

While Transformers underpin modern large language models (LMs), there is a growing list of alternative architectures with new capabilities, promises, and tradeoffs. This makes choosing the right LM architecture challenging. Recently…

This work presents Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that provides an alternative to state-of-the-art (SoTA) Transformer-based policies. MaIL leverages Mamba, a state-space model designed to…

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…

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…

Log parsing is a critical standard operating procedure in software systems, enabling monitoring, anomaly detection, and failure diagnosis. However, automated log parsing remains challenging due to heterogeneous log formats, distribution…

This study explores replacing Transformers in Visual Language Models (VLMs) with Mamba, a recent structured state space model (SSM) that demonstrates promising performance in sequence modeling. We test models up to 3B parameters under…

The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or…

We present a generative framework for inverse design of five-layer transmissive Huygens' metasurfaces (HMSs), addressing a longstanding challenge in achieving full-phase, high-efficiency unit cell designs with minimal full-wave simulations.…

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…

Mamba, a selective state-space model (SSM), has emerged as an efficient alternative to Transformers for speech modeling, enabling long-sequence processing with linear complexity. While effective in speech separation, existing approaches,…

This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and 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,…

Transformer structure has achieved great success in multiple applied machine learning communities, such as natural language processing (NLP), computer vision (CV) and information retrieval (IR). Transformer architecture's core mechanism\,…

In recent years, multimodal learning has become essential in robotic vision and information fusion, especially for understanding human behavior in complex environments. However, current methods struggle to fully leverage the textual…

Mamba extends earlier state space models (SSMs) by introducing input-dependent dynamics, and has demonstrated strong empirical performance across a range of domains, including language modeling, computer vision, and foundation models.…