相关论文: DYNAMAX: Dynamic computing for Transformers and Ma…

As one of the most representative DL techniques, Transformer architecture has empowered numerous advanced models, especially the large language models (LLMs) that comprise billions of parameters, becoming a cornerstone in deep learning.…

State Space Model (SSM)-based machine learning architectures have recently gained significant attention for processing sequential data. Mamba, a recent sequence-to-sequence SSM, offers competitive accuracy with superior computational…

Automatic modulation classification (AMC) plays a critical role in wireless communications by autonomously classifying signals transmitted over the radio spectrum. Deep learning (DL) techniques are increasingly being used for AMC due to…

Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability…

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,…

Early-Exit (EE) is a Large Language Model (LLM) architecture that accelerates inference by allowing easier tokens to be generated using only a subset of the model's layers. However, traditional batching frameworks are ill-suited for EE…

Partial Differential Equations are foundational in modeling science and natural systems such as fluid dynamics and weather forecasting. The Latent Evolution of PDEs method is designed to address the computational intensity of classical and…

While the Mamba architecture demonstrates superior inference efficiency and competitive performance on short-context natural language processing (NLP) tasks, empirical evidence suggests its capacity to comprehend long contexts is limited…

Effective reasoning is crucial to solving complex mathematical problems. Recent large language models (LLMs) have boosted performance by scaling test-time computation through long chain-of-thought reasoning. However, transformer-based…

Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including…

Transformer-based architectures have become the backbone of both uni-modal and multi-modal foundation models, largely due to their scalability via attention mechanisms, resulting in a rich ecosystem of publicly available pre-trained models…

Physics-informed machine learning (PIML) has emerged as a promising alternative to classical methods for predicting dynamical systems, offering faster and more generalizable solutions. However, existing models, including recurrent neural…

Sequential recommendation systems aim to predict users' next preferences based on their interaction histories, but existing approaches face critical limitations in efficiency and multi-scale pattern recognition. While Transformer-based…

Mamba is an emerging, complex workload with various short-range and long-range dependencies, nonlinearities, and elementwise computations that are unable to run at near-peak speeds on modern hardware. Specifically, Mamba's complex…

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as linear attention,…

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement…

Decision Transformer, a promising approach that applies Transformer architectures to reinforcement learning, relies on causal self-attention to model sequences of states, actions, and rewards. While this method has shown competitive…

Linear RNN architectures, like Mamba, can be competitive with Transformer models in language modeling while having advantageous deployment characteristics. Given the focus on training large-scale Transformer models, we consider the…

State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models grow increasingly larger, the need for Parameter-Efficient…

Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns. Over the past few years, deep learning models especially Transformers have achieved advanced performance in LTSF tasks. However, LTSF faces…