Related papers: Dynamic Transformers Provide a False Sense of Effi…

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…

Scaling machine learning models significantly improves their performance. However, such gains come at the cost of inference being slow and resource-intensive. Early-exit neural networks (EENNs) offer a promising solution: they accelerate…

Language Models (LMs) have demonstrated impressive capabilities with core Natural Language Processing (NLP) tasks. The effectiveness of LMs for highly specialized knowledge-intensive tasks in finance remains difficult to assess due to major…

The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between…

Transformer-based models are the state-of-the-art for Natural Language Understanding (NLU) applications. Models are getting bigger and better on various tasks. However, Transformer models remain computationally challenging since they are…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Large Language Models (LLMs) typically come with a fixed architecture, despite growing evidence that not all layers contribute equally to every downstream task. We introduce TALE (Task-Aware Layer Elimination), an inference-time method that…

Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile…

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of frames to be processed. This paper introduces the SlowFast…

Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust…

Recent innovations in Transformer-based large language models have significantly advanced the field of general-purpose neural language understanding and generation. With billions of trainable parameters, deployment of these large models…

The challenges in feature selection, particularly in balancing model accuracy, interpretability, and computational efficiency, remain a critical issue in advancing machine learning methodologies. To address these complexities, this study…

Most discussions about Large Language Model (LLM) safety have focused on single-agent settings but multi-agent LLM systems now create novel adversarial risks because their behavior depends on communication between agents and decentralized…

The large number of parameters in Pretrained Language Models enhance their performance, but also make them resource-intensive, making it challenging to deploy them on commodity hardware like a single GPU. Due to the memory and power…

As the ever-increasing token limits of large language models (LLMs) have enabled long context as input, prompting with single data samples might no longer an efficient way. A straightforward strategy improving efficiency is to batch data…

The increasing complexity of advanced machine learning models requires innovative approaches to manage computational resources effectively. One such method is the Early Exit strategy, which allows for adaptive computation by providing a…

Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yield greater efficiency. Yet, in practice, current open-source…

Diffusion models represent a powerful family of generative models widely used for image and video generation. However, the time-consuming deployment, long inference time, and requirements on large memory hinder their applications on…

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…