相关论文: ALPINE: An adaptive language-agnostic pruning meth…

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Recent work targeting large language models (LLMs) for code generation demonstrated that increasing the amount of training data through synthetic code generation often leads to exceptional performance. In this paper we explore data pruning…

Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial model size, which presents significant challenges in both the…

Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to continual adaptation. To simultaneously address both issues,…

NLP(natural language processsing) has achieved great success through the transformer model.However, the model has hundreds of millions or billions parameters,which is huge burden for its deployment on personal computer or small scale of…

Streamliner constraints reduce the search space of combinatorial problems by ruling out portions of the solution space. We adapt the StreamLLM approach, which uses Large Language Models (LLMs) to generate streamliners for Constraint…

While convolutional neural networks (CNN) have achieved impressive performance on various classification/recognition tasks, they typically consist of a massive number of parameters. This results in significant memory requirement as well as…

The rapid growth in machine learning models, especially in natural language processing and computer vision, has led to challenges when running these models on hardware with limited resources. This paper introduces Superpipeline, a new…

Small language models (SLMs) have attracted considerable attention from both academia and industry due to their broad range of applications in edge devices. To obtain SLMs with strong performance, conventional approaches either pre-train…

How can we accelerate large language models(LLMs) without sacrificing accuracy? The slow inference speed of LLMs hinders us to benefit from their remarkable performance in diverse applications. This is mainly because numerous sublayers are…

While Large Language Models (LLMs) have significantly advanced code generation efficiency, they face inherent challenges in balancing performance and inference costs across diverse programming tasks. Dynamically selecting the optimal LLM…

Detectability of failures of linear programming (LP) decoding and the potential for improvement by adding new constraints motivate the use of an adaptive approach in selecting the constraints for the underlying LP problem. In this paper, we…

When programmers retrieve a code method and want to reuse it, they need to understand the usage patterns of the retrieved method. However, it is difficult to obtain usage information of the retrieved method since this method may only have a…

Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields models that cannot…

Existing image reflection removal methods struggle to handle complex reflections. Accurate language descriptions can help the model understand the image content to remove complex reflections. However, due to blurred and distorted…

Linguine is a natural-language-inspired programming language that enables users to write programs in a fluent, controlled subset of English while preserving formal semantics. The language introduces anaphoric constructs, such as pronoun…

IoT and edge-based inference systems require unique solutions to overcome resource limitations and unpredictable environments. In this paper, we propose an environment-aware dynamic pruning system that handles the unpredictability of edge…

Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present…

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…

LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as…