Related papers: Samyama: A Unified Graph-Vector Database with In-D…

Here we study the problem of matched record clustering in unsupervised entity resolution. We build upon a state-of-the-art probabilistic framework named the Data Washing Machine (DWM). We introduce a graph-based hierarchical 2-step record…

Modern LLM service providers increasingly rely on autoscaling and parallelism reconfiguration to respond to rapidly changing workloads, but cold-start latency remains a major bottleneck. While recent systems have reduced model weight…

A fundamental building block in any graph algorithm is a graph container - a data structure used to represent the graph. Ideally, a graph container enables efficient access to the underlying graph, has low space usage, and supports updating…

Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires…

As the amount of data produced in society continues to grow at an exponential rate, modern applications are incurring significant performance and energy penalties due to high data movement between the CPU and memory/storage. While…

Logistics optimization nowadays is becoming one of the hottest areas in the AI community. In the past year, significant advancements in the domain were achieved by representing the problem in a form of graph. Another promising area of…

The era of foundation models has revolutionized AI research, yet Graph Foundation Models (GFMs) remain constrained by the scarcity of large-scale graph corpora. Traditional graph data synthesis techniques primarily focus on simplistic…

Graph Neural Networks (GNNs) are vital for learning from graph-structured data, enabling applications in network analysis, recommendation systems, and speech analytics. Deploying them on edge devices like client PCs and laptops enhances…

Modern computing systems face security threats, including memory corruption attacks, speculative execution vulnerabilities, and control-flow hijacking. Although existing solutions address these threats individually, they frequently…

Simple graph algorithms such as PageRank have been the target of numerous hardware accelerators. Yet, there also exist much more complex graph mining algorithms for problems such as clustering or maximal clique listing. These algorithms are…

Relational databases store much of the world's structured information, and they are essential for driving complex predictive applications. However, deep learning progress on relational data remains limited, as conventional approaches…

Graphics Processing Units (GPUs) have become the standard in accelerating scientific applications on heterogeneous systems. However, as GPUs are getting faster, one potential performance bottleneck with GPU-accelerated applications is the…

Graph pattern mining applications try to find all embeddings that match specific patterns. Compared to the traditional graph computation, graph mining applications are computation-intensive. The state-of-the-art method, pattern enumeration,…

Many models have been proposed for vision and language tasks, especially the image-text retrieval task. All state-of-the-art (SOTA) models in this challenge contained hundreds of millions of parameters. They also were pretrained on a large…

Language agents powered by large language models (LLMs) have demonstrated remarkable capabilities in understanding, reasoning, and executing complex tasks. However, developing robust agents presents significant challenges: substantial…

Graph neural networks (GNNs) realize great success in graph learning but suffer from performance loss when meeting heterophily, i.e. neighboring nodes are dissimilar, due to their local and uniform aggregation. Existing attempts of…

Retrieval-Augmented Generation (RAG) systems have become the standard architecture for grounding large language models in organizational knowledge. Yet production deployments consistently expose a gap between clean prototype performance and…

Long-sequence state-space models (SSMs) such as Hyena and Mamba replace the quadratic complexity of self-attention with more efficient FFT and scan operations. However, modern accelerators like GPUs are poorly suited to these non-GEMM…

Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses this by integrating external corpora, its effectiveness…

The explosive growth of multimodal data - spanning text, image, video, spatial, and relational modalities, coupled with the need for real-time semantic search and retrieval over these data - has outpaced the capabilities of existing…