Related papers: Efficient Row-Level Lineage Leveraging Predicate P…

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

Coming high-cadence wide-field optical telescopes will image hundreds of thousands of sources per minute. Besides inspecting the near real-time data streams for transient and variability events, the accumulated data archive is a wealthy…

Runtime predictive analyses enhance coverage of traditional dynamic analyses based bug detection techniques by identifying a space of feasible reorderings of the observed execution and determining if any of these witnesses the violation of…

Data pre-processing pipelines are the bread and butter of any successful AI project. We introduce a novel programming model for pipelines in a data lakehouse, allowing users to interact declaratively with assets in object storage. Motivated…

Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…

Most existing pre-trained language models for source code focus on learning the static code text, typically augmented with static code structures (abstract syntax tree, dependency graphs, etc.). However, program semantics will not be fully…

Risk disclosures in SEC filings describe potential adverse events but rarely quantify their likelihood, limiting their usefulness for probabilistic analysis. A central obstacle is the absence of large-scale, risk-level supervision linking…

Parallel dataflow systems have become a standard technology for large-scale data analytics. Complex data analysis programs in areas such as machine learning and graph analytics often involve control flow, i.e., iterations and branching.…

Performance antipatterns document bad design patterns that have negative influence on system performance. In our previous work we formalized such antipatterns as logical predicates that predicate on four views: (i) the static view that…

The use of deep learning models for forecasting the resource consumption patterns of SQL queries have recently been a popular area of study. With many companies using cloud platforms to power their data lakes for large scale analytic…

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

We introduce Proceduray, an engine for real-time ray tracing of procedural geometry. Its motivation is the current lack of mid-level abstraction tools for scenes with primitives involving intersection shaders. Those scenes impose strict…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

Several decision points exist in business processes (e.g., whether a purchase order needs a manager's approval or not), and different decisions are made for different process instances based on their characteristics (e.g., a purchase order…

Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing, involves freezing the source model and training a new…

IoT and edge-based inference systems require unique solutions to overcome resource limitations and unpredictable environments. In this paper, we propose an environment-aware dynamic pruning system that handles the unpredictability of edge…

Lane detection is one of the most important functions for autonomous driving. In recent years, deep learning-based lane detection networks with RGB camera images have shown promising performance. However, camera-based methods are inherently…

Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…

The most common approach to implementing data analysis pipelines involves obtaining point estimates from the upstream modules and then treating these as known quantities when working with the downstream ones. This approach is…

We propose a novel interpretable deep neural network for text classification, called ProtoryNet, based on a new concept of prototype trajectories. Motivated by the prototype theory in modern linguistics, ProtoryNet makes a prediction by…