相关论文: RAM: Replace Attention with MLP for Efficient Mult…

Linear sequence modeling approaches, such as linear attention, provide advantages like linear-time training and constant-memory inference over sequence lengths. However, existing sequence parallelism (SP) methods are either not optimized…

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

IR-based fault localization approaches achieves promising results when locating faulty files by comparing a bug report with source code. Unfortunately, they become less effective to locate faulty methods. We conduct a preliminary study to…

Recently, random feature attentions (RFAs) are proposed to approximate the softmax attention in linear time and space complexity by linearizing the exponential kernel. In this paper, we first propose a novel perspective to understand the…

Temporal knowledge graphs (TKGs) model the temporal evolution of events and have recently attracted increasing attention. Since TKGs are intrinsically incomplete, it is necessary to reason out missing elements. Although existing TKG…

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

Large language models (LLMs) are being applied to time series forecasting. But are language models actually useful for time series? In a series of ablation studies on three recent and popular LLM-based time series forecasting methods, we…

Long-context inference in large language models is increasingly bottlenecked by the memory and compute cost of the KV-Cache. Low-rank factorization compresses KV projections by writing $W \approx A * B$, where A produces latent KV states…

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

From natural language processing to vision, Scaled Dot Product Attention (SDPA) is the backbone of most modern deep learning applications. Unfortunately, its memory and computational requirements can be prohibitive in low-resource settings.…

There has been a recent surge of interest in time series modeling using the Transformer architecture. However, forecasting multivariate time series with Transformer presents a unique challenge as it requires modeling both temporal…

Long Short-Term Memory Networks (LSTMs) have been applied to daily discharge prediction with remarkable success. Many practical scenarios, however, require predictions at more granular timescales. For instance, accurate prediction of short…

While Large Vision-Language Models (LVLMs) demonstrate exceptional multi-modal capabilities, the quadratic computational cost of processing high-resolution visual tokens remains a critical bottleneck. Though recent token reduction…

The emergence of 6th generation (6G) mobile networks brings new challenges in supporting high-mobility communications, particularly in addressing the issue of channel aging. While existing channel prediction methods offer improved accuracy…

We study the performance of transformer architectures for multivariate time-series forecasting in low-data regimes consisting of only a few years of daily observations. Using synthetically generated processes with known temporal and…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Motion planning is the soul of robot decision making. Classical planning algorithms like graph search and reaction-based algorithms face challenges in cases of dense and dynamic obstacles. Deep learning algorithms generate suboptimal…

Operations and maintenance (O&M) scheduling is a critical problem in leased manufacturing systems, with significant implications for operational efficiency, cost optimization, and machine reliability. Solving this problem involves…

Converting pretrained attention modules such as grouped-query attention (GQA) into multi-head latent attention (MLA) can improve expressivity without increasing KV-cache cost, making it attractive for efficient inference. However, many…

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…