Related papers: BTR: Binary Token Representations for Efficient Re…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional success in various multimodal tasks, yet their deployment is frequently limited by substantial computational demands and prolonged inference times. Given that the vision…

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach…

We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a $2$ trillion token database, our Retrieval-Enhanced Transformer (RETRO)…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Since ChatGPT released its API for public use, the number of applications built on top of commercial large language models (LLMs) increase exponentially. One popular usage of such models is leveraging its in-context learning ability and…

Retrieving and extracting knowledge from extensive research documents and large databases presents significant challenges for researchers, students, and professionals in today's information-rich era. Existing retrieval systems, which rely…

Large Language Models (LLMs) have swiftly emerged as vital resources for different applications in the biomedical and healthcare domains; however, these models encounter issues such as generating inaccurate information or hallucinations.…

Word embeddings are commonly used as a starting point in many NLP models to achieve state-of-the-art performances. However, with a large vocabulary and many dimensions, these floating-point representations are expensive both in terms of…

Pre-trained language models have shown stellar performance in various downstream tasks. But, this usually comes at the cost of high latency and computation, hindering their usage in resource-limited settings. In this work, we propose a…

Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world. Memory-based methods like LUMEN pre-compute token representations for retrieved passages to drastically speed up…

Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and inference. Meanwhile, retrieval-augmented generation (RAG)…

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer…

Augmenting a language model (LM) with $k$-nearest neighbors ($k$NN) retrieval on its training data alone can decrease its perplexity, though the underlying reasons for this remain elusive. In this work, we rule out one previously posited…

Retrieval-augmented language models (LMs) have received much attention recently. However, typically the retriever is not trained jointly as a native component of the LM, but added post-hoc to an already-pretrained LM, which limits the…

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures…

To drive progress in science and engineering, large language models (LLMs) must be able to process large amounts of numerical data and solve long calculations efficiently. This is currently only possible through the use of external tools or…

The high inference cost of Large Language Models (LLMs) poses challenges, especially for tasks requiring lengthy outputs. However, natural language often contains redundancy, which presents an opportunity for optimization. We have observed…

Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information. Notably, existing reward models only mimic human annotations by assigning…

Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) for generating more factual, accurate, and up-to-date content. Existing methods either optimize prompts to guide LLMs in leveraging retrieved…

Despite their tremendous success and versatility, Deep Neural Networks (DNNs) such as Large Language Models (LLMs) suffer from inference inefficiency and rely on advanced computational infrastructure. To address these challenges and make…