Related papers: DynamicLogLog: Faster, Smaller, and More Accurate …

To address the computational and storage challenges posed by large-scale datasets in deep learning, dataset distillation has been proposed to synthesize a compact dataset that replaces the original while maintaining comparable model…

Diffusion large language models (dLLMs) have recently drawn considerable attention within the research community as a promising alternative to autoregressive generation, offering parallel token prediction and lower inference latency. Yet,…

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…

Previous approaches to learned cardinality estimation have focused on improving average estimation error, but not all estimates matter equally. Since learned models inevitably make mistakes, the goal should be to improve the estimates that…

Persistent spread measurement is to count the number of distinct elements that persist in each network flow for predefined time periods. It has many practical applications, including detecting long-term stealthy network activities in the…

System log anomaly detection is critical for maintaining the reliability of large-scale software systems, yet traditional methods struggle with the heterogeneous and evolving nature of modern log data. Recent advances in Large Language…

With the increasing prevalence of scalable file systems in the context of High Performance Computing (HPC), the importance of accurate anomaly detection on runtime logs is increasing. But as it currently stands, many state-of-the-art…

Effective log anomaly detection is critical to sustaining reliability in large-scale IT infrastructures. Transformer-based models require substantial resources and labeled data, exacerbating the cold-start problem in target domains where…

Due to the outstanding capability of capturing underlying data distributions, deep learning techniques have been recently utilized for a series of traditional database problems. In this paper, we investigate the possibilities of utilizing…

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) significantly reduces model size, its direct…

Diffusion large language models (dLLMs) offer capabilities beyond those of autoregressive (AR) LLMs, such as parallel decoding and random-order generation. However, realizing these benefits in practice is non-trivial, as dLLMs inherently…

Stochastic Computing (SC) is a computing paradigm that allows for the low-cost and low-power computation of various arithmetic operations using stochastic bit streams and digital logic. In contrast to conventional representation schemes…

Online monitoring user cardinalities (or degrees) in graph streams is fundamental for many applications. For example in a bipartite graph representing user-website visiting activities, user cardinalities (the number of distinct visited…

Binary quantization represents the most extreme form of compression, reducing weights to +/-1 for maximal memory and computational efficiency. While recent sparsity-aware binarization achieves sub-1-bit compression via weight pruning, it…

In this paper, we present BitNet Distillation (BitDistill), a lightweight pipeline that fine-tunes off-the-shelf full-precision LLMs (e.g., Qwen) into 1.58-bit precision (i.e., ternary weights {-1, 0, 1}) for specific downstream tasks,…

Traditional benchmarks for large language models (LLMs) typically rely on static evaluations through storytelling or opinion expression, which fail to capture the dynamic requirements of real-time information processing in contemporary…

Most cloud services and distributed applications rely on hashing algorithms that allow dynamic scaling of a robust and efficient hash table. Examples include AWS, Google Cloud and BitTorrent. Consistent and rendezvous hashing are algorithms…

Field-Programmable Gate Arrays (FPGAs) play an indispensable role in Electronic Design Automation (EDA), translating Register-Transfer Level (RTL) designs into gate-level netlists. The correctness and reliability of FPGA logic synthesis…

We present FlexLLM, a composable High-Level Synthesis (HLS) library for rapid development of domain-specific LLM accelerators. FlexLLM exposes key architectural degrees of freedom for stage-customized inference, enabling hybrid designs that…

Super point is a special kind of host whose cardinality, the number of contacting hosts in a certain period, is bigger than a threshold. Super point cardinality estimation plays important roles in network field. This paper proposes a super…