Related papers: DYNAMAX: Dynamic computing for Transformers and Ma…
Transformer, a deep neural network architecture, has long dominated the field of natural language processing and beyond. Nevertheless, the recent introduction of Mamba challenges its supremacy, sparks considerable interest among…
Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level…
State Space Model (SSM) is a mathematical model used to describe and analyze the behavior of dynamic systems. This model has witnessed numerous applications in several fields, including control theory, signal processing, economics and…
Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can…
EEG-based emotion recognition holds significant potential in the field of brain-computer interfaces. A key challenge lies in extracting discriminative spatiotemporal features from electroencephalogram (EEG) signals. Existing studies often…
Transformers are the current architecture of choice for NLP, but their attention layers do not scale well to long contexts. Recent works propose to replace attention with linear recurrent layers -- this is the case for state space models,…
Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditional ML tasks (e.g., image classification), networked systems often operate in…
Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into the…
Enterprises are facing increasing risks of insider threats, while existing detection methods are unable to effectively address these challenges due to reasons such as insufficient temporal dynamic feature modeling, computational efficiency…
In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…
The growing demand for efficient long-sequence modeling on edge devices has propelled widespread adoption of State Space Models (SSMs) like Mamba, due to their superior computational efficiency and scalability. As its autoregressive…
Motion planning is a challenging task to generate safe and feasible trajectories in highly dynamic and complex environments, forming a core capability for autonomous vehicles. In this paper, we propose DRAMA, the first Mamba-based…
Irregular and asynchronous event sequences are prevalent in many domains, such as social media, finance, and healthcare. Traditional temporal point processes (TPPs), like Hawkes processes, often struggle to model mutual inhibition and…
Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based,…
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…
3D object detection is critical for autonomous driving, yet it remains fundamentally challenging to simultaneously maximize computational efficiency and capture long-range spatial dependencies. We observed that Mamba-based models, with…
Sequential modeling has demonstrated remarkable capabilities in offline reinforcement learning (RL), with Decision Transformer (DT) being one of the most notable representatives, achieving significant success. However, RL trajectories…
Recent advancements in reinforcement learning (RL) for analog circuit optimization have demonstrated significant potential for improving sample efficiency and generalization across diverse circuit topologies and target specifications.…
In the Sound Event Localization and Detection (SELD) task, Transformer-based models have demonstrated impressive capabilities. However, the quadratic complexity of the Transformer's self-attention mechanism results in computational…
In this work, we take the first exploration of the recently popular foundation model, i.e., State Space Model/Mamba, in image quality assessment (IQA), aiming at observing and excavating the perception potential in vision Mamba. A series of…