Related papers: Return of the Encoder: Maximizing Parameter Effici…

Deploying large language models (LLMs) on mobile devices increasingly relies on heterogeneous execution, yet no prior study has systematically characterized NPU effectiveness at the operator and pipeline level. We present the first…

The widespread adoption of Language Models (LMs) across industries is driving interest in deploying these services across the computing continuum, from the cloud to the network edge. This shift aims to reduce costs, lower latency, and…

Scaling large language models (LLMs) has shown great potential for improving retrieval model performance; however, previous studies have mainly focused on dense retrieval trained with contrastive loss (CL), neglecting the scaling behavior…

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Language models (LMs) are being scaled and becoming powerful. Improving their efficiency is one of the core research topics in neural information processing systems. Tay et al. (2022) provided a comprehensive overview of efficient…

The prevalence of Large Language Models (LLMs) for generating multilingual text and source code has only increased the imperative for machine-generated content detectors to be accurate and efficient across domains. Current detectors,…

Low-latency decoding for large language models (LLMs) is crucial for applications like chatbots and code assistants, yet generating long outputs remains slow in single-query settings. Prior work on speculative decoding (which combines a…

Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…

Contextual representation models have achieved great success in improving various downstream tasks. However, these language-model-based encoders are difficult to train due to the large parameter sizes and high computational complexity. By…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs). In response, we introduce SpreadsheetLLM,…

Tensor computations, with matrix multiplication being the primary operation, serve as the fundamental basis for data analysis, physics, machine learning, and deep learning. As the scale and complexity of data continue to grow rapidly, the…

Large language models (LLMs) exhibit strong general intelligence, yet their multilingual performance remains highly imbalanced. Although LLMs encode substantial cross-lingual knowledge in a unified semantic space, they often struggle to…

Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

Semantic role labeling (SRL) is a crucial task of natural language processing (NLP). Although generative decoder-based large language models (LLMs) have achieved remarkable success across various NLP tasks, they still lag behind…

Emerging intelligent service scenarios in 6G communication impose stringent requirements for low latency, high reliability, and privacy preservation. Generative large language models (LLMs) are gradually becoming key enablers for the…

Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…