相关论文: Rockmate: an Efficient, Fast, Automatic and Generi…

Large model training often uses recomputation to alleviate memory pressure and pipelines to exploit the parallelism of data, tensors, and devices. However, existing recomputation approaches may incur high overhead when training real-world…

The high probability of hardware failures prevents many advanced robots (e.g., legged robots) from being confidently deployed in real-world situations (e.g., post-disaster rescue). Instead of attempting to diagnose the failures, robots…

adaptNMT is an open-source application that offers a streamlined approach to the development and deployment of Recurrent Neural Networks and Transformer models. This application is built upon the widely-adopted OpenNMT ecosystem, and is…

We introduce the IBM Analog Hardware Acceleration Kit, a new and first of a kind open source toolkit to simulate analog crossbar arrays in a convenient fashion from within PyTorch (freely available at https://github.com/IBM/aihwkit). The…

The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks typically demand full-fledged code repositories rather than…

Random Matrix Theory (RMT) is applied to analyze weight matrices of Deep Neural Networks (DNNs), including both production quality, pre-trained models such as AlexNet and Inception, and smaller models trained from scratch, such as LeNet5…

YAMLE: Yet Another Machine Learning Environment is an open-source framework that facilitates rapid prototyping and experimentation with machine learning (ML) models and methods. The key motivation is to reduce repetitive work when…

Access to vast amounts of data along with affordable computational power stimulated the reincarnation of neural networks. The progress could not be achieved without adequate software tools, lowering the entry bar for the next generations of…

We introduce Dynamic Dropout, a novel regularization technique designed to enhance the training efficiency of Transformer models by dynamically adjusting the dropout rate based on training epochs or validation loss improvements. This…

Metamaterials are artificial materials that are designed to meet unseen properties in nature, such as ultra-stiffness and negative materials indices. In mechanical metamaterial design, three key modalities are typically involved, i.e., 3D…

Batteryless IoT systems face energy constraints exacerbated by checkpointing overhead. Approximate computing offers solutions but demands manual expertise, limiting scalability. This paper presents CheckMate, an automated framework…

Mathematical models allow us to gain a deeper understanding of real-world dynamical systems. One of the most powerful mathematical frameworks for modeling real-world phenomena are systems of differential equations. In the majority of fields…

Running complex sets of machine learning experiments is challenging and time-consuming due to the lack of a unified framework. This leaves researchers forced to spend time implementing necessary features such as parallelization, caching,…

To make machine learning (ML) sustainable and apt to run on the diverse devices where relevant data is, it is essential to compress ML models as needed, while still meeting the required learning quality and time performance. However, how…

Nowadays, this is very popular to use the deep architectures in machine learning. Deep Belief Networks (DBNs) are deep architectures that use stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training…

As deep learning models continue to increase in size, the memory requirements for training have surged. While high-level techniques like offloading, recomputation, and compression can alleviate memory pressure, they also introduce…

When Requirements Engineering(RE) models are unreasonably complex, they cannot support efficient decision making. SHORT is a tool to simplify that reasoning by exploiting the "key" decisions within RE models. These "keys" have the property…

We propose a cooperative training framework for deep neural network architectures that enables the runtime network depths to change to satisfy dynamic computing resource requirements. In our framework, the number of layers participating in…

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

We present a generalised architecture for reactive mobile manipulation while a robot's base is in motion toward the next objective in a high-level task. By performing tasks on-the-move, overall cycle time is reduced compared to methods…