相关论文: AdapLeR: Speeding up Inference by Adaptive Length …

Large-scale language model pretraining is a very successful form of self-supervised learning in natural language processing, but it is increasingly expensive to perform as the models and pretraining corpora have become larger over time. We…

Despite the great success in Natural Language Processing (NLP) area, large pre-trained language models like BERT are not well-suited for resource-constrained or real-time applications owing to the large number of parameters and slow…

The vision transformer is a model that breaks down each image into a sequence of tokens with a fixed length and processes them similarly to words in natural language processing. Although increasing the number of tokens typically results in…

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Recent Vision-Language Models (VLMs) have demonstrated remarkable multimodal understanding capabilities, yet the redundant visual tokens incur prohibitive computational overhead and degrade inference efficiency. Prior studies typically…

We introduce A-ViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. A-ViT achieves this by automatically reducing the number of tokens in vision transformers that are…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Transformer-based language models such as BERT provide significant accuracy improvement for a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to…

This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple…

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Despite transformers' impressive accuracy, their computational cost is often prohibitive to use with limited computational resources. Most previous approaches to improve inference efficiency require a separate model for each possible…

The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…

Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…

End-to-end training of automated speech recognition (ASR) systems requires massive data and compute resources. We explore transfer learning based on model adaptation as an approach for training ASR models under constrained GPU memory,…

As the performance and popularity of deep neural networks has increased, so too has their computational cost. There are many effective techniques for reducing a network's computational footprint (quantisation, pruning, knowledge…

Language model pre-training, such as BERT, has significantly improved the performances of many natural language processing tasks. However, pre-trained language models are usually computationally expensive, so it is difficult to efficiently…

Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very…

Reasoning models have gained significant attention due to their strong performance, particularly when enhanced with retrieval augmentation. However, these models often incur high computational costs, as both retrieval and reasoning tokens…

Following recent successes in applying BERT to question answering, we explore simple applications to ad hoc document retrieval. This required confronting the challenge posed by documents that are typically longer than the length of input…

The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…