Related papers: Enthuse: Efficient Adaptable High-throughput Strea…

Dynamic scene reconstruction with Gaussian Splatting has enabled efficient streaming for real-time rendering and free-viewpoint video. However, most pipelines rely on fixed anchor selection such as Farthest Point Sampling (FPS), typically…

Transformer models based on the Mixture of Experts (MoE) architecture have made significant progress in long-sequence modeling, but existing models still have shortcomings in computational efficiency and the ability to capture long-range…

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Several approaches to mitigating the Forwarding Information Base (FIB) overflow problem were developed and software solutions using FIB aggregation are of particular interest. One of the greatest concerns to deploy these algorithms to real…

Cloud-edge collaborative computing paradigm is a promising solution to high-resolution video analytics systems. The key lies in reducing redundant data and managing fluctuating inference workloads effectively. Previous work has focused on…

Social coordination allows users to move beyond awareness of their friends to efficiently coordinating physical activities with others. While specific forms of social coordination can be seen in tools such as Evite, Meetup and Groupon, we…

In this paper, we propose a novel method, aggregation cross-entropy (ACE), for sequence recognition from a brand new perspective. The ACE loss function exhibits competitive performance to CTC and the attention mechanism, with much quicker…

When considering a model selection or, more generally, an aggregation approach for adaptive statistical inference, it is often necessary to compute estimators over a wide range of model complexities including unnecessarily large models even…

In the graph domain, deep graph networks based on Message Passing Neural Networks (MPNNs) or Graph Transformers often cause over-smoothing of node features, limiting their expressive capacity. Many upsampling techniques involving node and…

Hypersparse matrices are a powerful enabler for a variety of network, health, finance, and social applications. Hierarchical hypersparse GraphBLAS matrices enable rapid streaming updates while preserving algebraic analytic power and…

Self-attention-based transformer models have achieved tremendous success in the domain of natural language processing. Despite their efficacy, accelerating the transformer is challenging due to its quadratic computational complexity and…

Interactive analytics increasingly involves querying for quantiles over sub-populations of high cardinality datasets. Data processing engines such as Druid and Spark use mergeable summaries to estimate quantiles, but summary merge times can…

We present SURGE, a streaming GPU encoding system deployed in production to generate embeddings for over 800 million texts across 40,000 logical partitions. Production embedding pipelines face a tension between logical data partitioning and…

The ever-increasing need for fast data processing demands new methods for efficient query execution. Just-in-time query compilation techniques have been demonstrated to improve performance in a set of analytical tasks significantly. In this…

SQL-on-Hadoop systems, query optimization, data distribution over multiple nodes and parallelization techniques are few of the areas under extreme research these days. Big names like Amazon, Google, Microsoft and many more are working on…

In this work, we detail the design and structure of a Synopses Data Engine (SDE) which combines the virtues of parallel processing and stream summarization towards delivering interactive analytics at extreme scale. Our SDE is built on top…

Retrieval-augmented generation (RAG) has achieved significant success in information retrieval to assist large language models LLMs because it builds an external knowledge database. However, it also has many problems, it consumes a lot of…

Subgraph counting aims to count the number of occurrences of a subgraph T (aka as a template) in a given graph G. The basic problem has found applications in diverse domains. The problem is known to be computationally challenging - the…

Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels. Recently, the emergence of LLMs has…

Deep Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in a wide range of applications. However, deeper CNN models, which are usually computation consuming, are widely required for complex Artificial…