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

I show that a software framework intended primarily for training of neural networks, PyTorch, is easily applied to a general function minimisation problem in science. The qualities of PyTorch of ease-of-use and very high efficiency are…

Modeling the recovery of interdependent critical infrastructure is a key component of quantifying and optimizing societal resilience to disruptive events. However, simulating the recovery of large-scale interdependent systems under random…

Checkmate is a framework that allows the user to conveniently test simulated BSM physics events against current LHC data in order to derive exclusion limits. For this purpose, the data runs through a detector simulation and is then…

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform…

Attention mechanisms have revolutionized sequence learning but suffer from quadratic computational complexity. This paper introduces \model, a novel recurrent neural network (RNN) mechanism that leverages the inherent low-rank structure of…

Recently reconstruction-based deep models have been widely used for time series anomaly detection, but as their capacity and generalization capability increase, these models tend to over-generalize, often reconstructing unseen anomalies…

While Large Language Models (LLMs) possess significant capabilities in open-world agent tasks, they also face challenges in rapidly adapting to new, specialized tasks due to their reliance on static pre-trained knowledge. Traditional…

Mobile robots often have limited battery life and need to recharge periodically. This paper presents an RRT- based path-planning algorithm that addresses battery power management. A path is generated continuously from the robot's current…

We present a versatile open-source framework designed to facilitate efficient, numerically-tailored Matrix-Matrix Multiplications (MMMs). The framework offers two primary contributions: first, a fine-tuned, automated pipeline for arithmetic…

Markov decision processes (MDPs) are a well studied framework for solving sequential decision making problems under uncertainty. Exact methods for solving MDPs based on dynamic programming such as policy iteration and value iteration are…

Modern time series analysis demands frameworks that are flexible, efficient, and extensible. However, many existing Python libraries exhibit limitations in modularity and in their native support for irregular, multi-source, or sparse data.…

The last decade has witnessed growth in the computational requirements for training deep neural networks. Current approaches (e.g., data/model parallelism, pipeline parallelism) parallelize training tasks onto multiple devices. However,…

The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowledge extracted from previous data and replay them during…

This work proposes RaNNC (Rapid Neural Network Connector) as middleware for automatic hybrid parallelism. In recent deep learning research, as exemplified by T5 and GPT-3, the size of neural network models continues to grow. Since such…

The emergence of data-driven computational materials science offers unprecedented opportunities to explore complex material landscapes, complementing experimental research with the discovery of novel compounds. To enable these developments,…

Mathematical reasoning benchmarks are vital for evaluating large language models (LLMs), but many are static and repeatedly exposed through public evaluation and training pipelines, making it difficult to separate genuine reasoning from…

Articulated objects are commonly found in daily life. It is essential that robots can exhibit robust perception and manipulation skills for articulated objects in real-world robotic applications. However, existing methods for articulated…

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes…

Medical foundation models pre-trained on large-scale datasets have demonstrated powerful versatile capabilities for various tasks. However, due to the gap between pre-training tasks (or modalities) and downstream tasks (or modalities), the…