Related papers: LiteMat: a scalable, cost-efficient inference enco…

Scaling laws with respect to the amount of training data and the number of parameters allow us to predict the cost-benefit trade-offs of pretraining language models (LMs) in different configurations. In this paper, we consider another…

This paper introduces RankMap, a platform-aware end-to-end framework for efficient execution of a broad class of iterative learning algorithms for massive and dense datasets. Our framework exploits data structure to factorize it into an…

We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds.…

The optimization of query execution plans is known to be crucial for reducing the query execution time. In particular, query optimization has been studied thoroughly for relational databases over the past decades. Recently, the Resource…

Deep discrete structured models have seen considerable progress recently, but traditional inference using dynamic programming (DP) typically works with a small number of states (less than hundreds), which severely limits model capacity. At…

Large language model (LLM) inference at the network edge is a promising serving paradigm that leverages distributed edge resources to run inference near users and enhance privacy. Existing edge-based LLM inference systems typically adopt…

Cloud systems generate large, heterogeneous log data containing critical infrastructure, application, and security information. Transforming these logs into RDF triples enables their integration into knowledge graphs, improving…

Teaching large language models (LLMs) to use tools for solving complex problems can grant them human-like reasoning abilities. ReAct and its variants are popular frameworks for tool use in both single-agent and multi-agent systems. To…

Linked Data Fragments (LDFs) refer to Web interfaces that allow for accessing and querying Knowledge Graphs on the Web. These interfaces, such as SPARQL endpoints or Triple Pattern Fragment servers, differ in the SPARQL expressions they can…

Semantic web is a web of future. The Resource Description Framework (RDF) is a language to represent resources in the World Wide Web. When these resources are queried the problem of duplicate query results occurs. The present techniques…

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-sized models and infrequent requests. While existing serverless solutions follow exclusive GPU allocation, we take a step back to explore…

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

Massive RDF data sets are becoming commonplace. RDF data is typically generated in social semantic domains (such as personal information management) wherein a fixed schema is often not available a priori. We propose a simple Three-way…

Current approaches for knowledge graph construction with RML focus on full RDF graph materialization without considering user queries. As a result, mapping engines are inefficient in dynamic query environments, materializing large graphs…

Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks. However, their deployment in resource-constrained environments and concerns over…

To improve deep-learning performance in low-resource settings, many researchers have redesigned model architectures or applied additional data (e.g., external resources, unlabeled samples). However, there have been relatively few…

We present a versatile open-source framework designed to facilitate efficient, numerically-tailored Matrix-Matrix Multiplications (MMMs). The framework offers two primary contributions: first, a fine-tuned, automated pipeline for arithmetic…

Increasing amounts of scientific and social data are published in the Resource Description Framework (RDF). Although the RDF data can be queried using the SPARQL language, even the SPARQL-based operation has a limitation in implementing…

Large Reasoning Models (LRMs) achieve remarkable inference-time improvements through parallel thinking. However, existing methods rely on redundant sampling of reasoning trajectories, failing to effectively explore the reasoning space to…

Network embedding has been widely used in social recommendation and network analysis, such as recommendation systems and anomaly detection with graphs. However, most of previous approaches cannot handle large graphs efficiently, due to that…