Related papers: FuseFlow: A Fusion-Centric Compilation Framework f…
Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an…
Neuro-Symbolic AI (NSAI) is an emerging paradigm that integrates neural networks with symbolic reasoning to enhance the transparency, reasoning capabilities, and data efficiency of AI systems. Recent NSAI systems have gained traction due to…
We propose an unsupervised image fusion architecture for multiple application scenarios based on the combination of multi-scale discrete wavelet transform through regional energy and deep learning. To our best knowledge, this is the first…
Linear algebra operations, which are ubiquitous in machine learning, form major performance bottlenecks. The High-Performance Computing community invests significant effort in the development of architecture-specific optimized kernels, such…
The integration of artificial intelligence capabilities into modern software systems is increasingly being simplified through the use of cloud-based machine learning services and representational state transfer architecture design. However,…
Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. During model selection and debugging, data scientists need to…
Digital Compute-in-Memory (CIM) architectures have shown great promise in Deep Neural Network (DNN) acceleration by effectively addressing the "memory wall" bottleneck. However, the development and optimization of digital CIM accelerators…
This paper describes a novel approach of packing sparse convolutional neural networks for their efficient systolic array implementations. By combining subsets of columns in the original filter matrix associated with a convolutional layer,…
Generative modeling has recently shown remarkable promise for visuomotor policy learning, enabling flexible and expressive control across diverse embodied AI tasks. However, existing generative policies often struggle with data…
Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark datasets, through a fine-grained sample-level inspection, we…
Dataflow visualization systems enable flexible visual data exploration by allowing the user to construct a dataflow diagram that composes query and visualization modules to specify system functionality. However learning dataflow diagram…
We present Piecewise Rectified Flow (PeRFlow), a flow-based method for accelerating diffusion models. PeRFlow divides the sampling process of generative flows into several time windows and straightens the trajectories in each interval via…
Event-based vision represents a paradigm shift in how vision information is captured and processed. By only responding to dynamic intensity changes in the scene, event-based sensing produces far less data than conventional frame-based…
Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the…
Reinforcement learning (RL) has become the pivotal post-training technique for large language model (LLM). Effectively scaling reinforcement learning is now the key to unlocking advanced reasoning capabilities and ensuring safe,…
Distributed training frameworks, like TensorFlow, have been proposed as a means to reduce the training time of deep learning models by using a cluster of GPU servers. While such speedups are often desirable---e.g., for rapidly evaluating…
We consider the problem of scheduling non preemptively a set of jobs on parallel identical machines with prior setup operations on a single shared server, where the objective is to minimise the makespan. We develop an arc-flow formulation…
FPGAs are well-suited for dataflow architectures that process data in a streaming or pipelined manner, thus satisfying the high computational and communication demands of emerging applications. However, manually implementing an efficient…
Software packages like TensorFlow and PyTorch are designed to support linear algebra operations, and their speed and usability determine their success. However, by prioritising speed, they often neglect memory requirements. As a…
Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, failing to produce diverse trajectory proposals. Meanwhile,…