Related papers: An LSM-based Tuple Compaction Framework for Apache…

Data-intensive applications fueled the evolution of log structured merge (LSM) based key-value engines that employ the out-of-place paradigm to support high ingestion rates with low read/write interference. These benefits, however, come at…

Large language models (LLMs) have been increasingly used to analyze text. However, they are often plagued with contextual reasoning limitations when analyzing long documents. When long documents are processed sequentially, early or dominant…

The growing volume of graph data may exhaust the main memory. It is crucial to design a disk-based graph storage system to ingest updates and analyze graphs efficiently. However, existing dynamic graph storage systems suffer from read or…

In enterprise datasets, documents are rarely pure. They are not just text, nor just numbers; they are a complex amalgam of narrative and structure. Current Retrieval-Augmented Generation (RAG) systems have attempted to address this…

Document layout understanding remains data-intensive despite advances in semi-supervised learning. We present a framework that enhances semi-supervised detection by fusing visual predictions with structural priors from text-pretrained LLMs…

Automatic process discovery from textual process documentations is highly desirable to reduce time and cost of Business Process Management (BPM) implementation in organizations. However, existing automatic process discovery approaches…

We introduce Microsoft Machine Learning for Apache Spark (MMLSpark), an ecosystem of enhancements that expand the Apache Spark distributed computing library to tackle problems in Deep Learning, Micro-Service Orchestration, Gradient…

Retrieval-augmented generation (RAG) systems face significant challenges in multi-hop question answering (MHQA), where complex queries require synthesizing information across multiple document chunks. Existing approaches typically rely on…

Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…

Efficient long-context LLM deployment is stalled by a dichotomy between amortized compression, which struggles with out-of-distribution generalization, and Test-Time Training, which incurs prohibitive synthetic data costs and requires…

Contemporary large language model (LLM) training pipelines require the assembly of internet-scale databases full of text data from a variety of sources (e.g., web, academic, and publishers). Preprocessing these datasets via deduplication --…

Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices. More critically, the computational speed on these devices is…

Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic attention complexity. In this paper, we introduce…

JSON Lines (JSONL) is widely used for managing large collections of semi-structured data, ranging from large language model (LLM) prompts to chemical compound records and geospatial datasets. A key operation is substructure search, which…

Data warehouses are overwhelmingly built through a bottom-up process, which starts with the identification of sources, continues with the extraction and transformation of data from these sources, and then loads the data into a set of data…

To reduce the computation cost and the energy consumption in large language models (LLM), skimming-based acceleration dynamically drops unimportant tokens of the input sequence progressively along layers of the LLM while preserving the…

Long-context LLM agents often struggle with growing token, memory, and latency costs, making efficient context compression essential for practical deployment. Existing LLM-as-a-compressor methods remain noticeably inferior to using the full…

The heterogeneity of data poses a great challenge when data from different sources is to be merged for one application. Solutions for this are offered, for example, by ontology-based data management (OBDM). A challenge of OBDM is the…

Applications in science and engineering often require huge computational resources for solving problems within a reasonable time frame. Parallel supercomputers provide the computational infrastructure for solving such problems. A…

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on…