Related papers: AttenMfg: An Attention Network Based Optimization …
As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and…
Traffic forecasting requires modeling complex temporal dynamics and long-range spatial dependencies over large sensor networks. Existing methods typically face a trade-off between expressiveness and efficiency: Transformer-based models…
Multi-Agent Task Assignment and Planning (MATP) has attracted growing attention but remains challenging in terms of scalability, spatial reasoning, and adaptability in obstacle-rich environments. To address these challenges, we propose OATH…
The Main Control Room of the Fermilab accelerator complex continuously gathers extensive time-series data from thousands of sensors monitoring the beam. However, unplanned events such as trips or voltage fluctuations often result in beam…
Motion prediction (MP) of multiple agents is a crucial task in arbitrarily complex environments, from social robots to self-driving cars. Current approaches tackle this problem using end-to-end networks, where the input data is usually a…
Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer…
This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by…
We present an active learning framework for efficiently generating training data for machine-learned interatomic potentials (MLIPs). The method combines local entropy-driven molecular dynamics with global dataset-aware filtering: a…
This chapter presents an innovative framework for the application of machine learning and data analytics for the identification of alloys or composites exhibiting certain desired properties of interest. The main focus is on alloys and…
Time series forecasting presents a significant challenge, particularly when its accuracy relies on external data sources rather than solely on historical values. This issue is prevalent in the financial sector, where the future behavior of…
This letter explores intelligent scheduling of sensor-to-controller communication in networked control systems, particularly when data transmission incurs a cost. While the optimal controller in a standard linear quadratic Gaussian (LQG)…
Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…
In this research, an effort is made to address microgrid systems' operational challenges, characterized by power oscillations that eventually contribute to grid instability. An integrated strategy is proposed, leveraging the strengths of…
Multi-headed Attention's (MHA) quadratic compute and linearly growing KV-cache make long-context transformers expensive to train and serve. Prior works such as Grouped Query Attention (GQA) and Multi-Latent Attention (MLA) shrink the cache,…
A practical large language model (LLM) service may involve a long system prompt, which specifies the instructions, examples, and knowledge documents of the task and is reused across requests. However, the long system prompt causes…
Transformers excel at sequence modeling but face quadratic complexity, while linear attention offers improved efficiency but often compromises recall accuracy over long contexts. In this work, we introduce Native Hybrid Attention (NHA), a…
Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention…
There has been a proliferation of artificial intelligence applications, where model training is key to promising high-quality services for these applications. However, the model training process is both time-intensive and energy-intensive,…
Predicting the motion of multiple traffic participants has always been one of the most challenging tasks in autonomous driving. The recently proposed occupancy flow field prediction method has shown to be a more effective and scalable…
Accurate day-ahead electricity price forecasting (DAEPF) is critical for the efficient operation of power systems, but extreme condition and market anomalies pose significant challenges to existing forecasting methods. To overcome these…