Related papers: Blockbuster, Part 1: Block-level AI Operator Fusio…

Ensembles of Deep Neural Networks (DNNs) have achieved qualitative predictions but they are computing and memory intensive. Therefore, the demand is growing to make them answer a heavy workload of requests with available computational…

In this paper, we present an Adaptive Ensemble Learning framework that aims to boost the performance of deep neural networks by intelligently fusing features through ensemble learning techniques. The proposed framework integrates ensemble…

In artificial neural networks, understanding the contributions of input features on the prediction fosters model explainability and delivers relevant information about the dataset. While typical setups for feature importance ranking assess…

Effective attention modules have played a crucial role in the success of Transformer-based large language models (LLMs), but the quadratic time and memory complexities of these attention modules also pose a challenge when processing long…

Clustering is an essential data mining tool for analyzing and grouping similar objects. In big data applications, however, many clustering algorithms are infeasible due to their high memory requirements and/or unfavorable runtime…

The human visual system contains a hierarchical sequence of modules that take part in visual perception at superordinate, basic, and subordinate categorization levels. During the last decades, various computational models have been proposed…

Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…

Dempster-Shafer Theory (DST) as an effective and robust framework for handling uncertain information is applied in decision-making and pattern classification. Unfortunately, its real-time application is limited by the exponential…

As AI systems become increasingly capable and ubiquitous, ensuring the safety of these systems is critical. However, existing safety tools often target different aspects of model safety and cannot provide full assurance in isolation,…

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

Large language model (LLM) decoding is latency-sensitive and often bottlenecked by fragmented operator execution and repeated off-chip materialization of intermediate tensors. Prior work expands fusion scope by leveraging thread-block…

Detector simulation and reconstruction are a significant computational bottleneck in particle physics. We develop Particle-flow Neural Assisted Simulations (Parnassus) to address this challenge. Our deep learning model takes as input a…

Convolution neural network (CNN) has been widely used in Single Image Super Resolution (SISR) so that SISR has been a great success recently. As the network deepens, the learning ability of network becomes more and more powerful. However,…

AI deployment increasingly resembles a pipeline of data transformation, fine-tuning, and agent interactions rather than a monolithic LLM job; recent examples include RLHF/RLAIF training and agentic workflows. To cope with this shift, we…

Real-world problems are often dependent on multiple data modalities, making multimodal fusion essential for leveraging diverse information sources. In high-stakes domains, such as in healthcare, understanding how each modality contributes…

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal…

This paper proposes an integrated approach combining computer networks and artificial neural networks to construct an intelligent network operator, functioning as an AI model. State information from computer networks is transformed into…

Sequence alignment is a memory bound computation whose performance in modern systems is limited by the memory bandwidth bottleneck. Processing-in-memory architectures alleviate this bottleneck by providing the memory with computing…

We propose a new class of models for variable clustering called Asymptotic Independent block (AI-block) models, which defines population-level clusters based on the independence of the maxima of a multivariate stationary mixing random…

Today's AI models learn primarily through mimicry and refining, so it is not surprising that they struggle to solve problems beyond the limits set by existing data. To solve novel problems, agents should acquire skills for exploring and…