Related papers: DynamicLogLog: Faster, Smaller, and More Accurate …
The performance gains obtained by large language models (LLMs) are closely linked to their substantial computational and memory requirements. Quantized LLMs offer significant advantages with extremely quantized models, motivating the…
On-device continual learning (CL) is critical for edge AI systems operating on non-stationary data streams, but most existing methods rely on backpropagation or exemplar-heavy classifiers, incurring substantial compute, memory, and latency…
Large language models (LLMs) have become increasingly popular in various areas, traditional business gradually shifting from rule-based systems to LLM-based solutions. However, the inference of LLMs is resource-intensive or…
In 2020 Blasiok (ACM Trans. Algorithms 16(2) 3:1-3:28) constructed an optimal space streaming algorithm for the cardinality estimation problem with the space complexity of $\mathcal O(\varepsilon^{-2} \ln(\delta^{-1}) + \ln n)$ where…
Dataset distillation (DD) aims to construct compact synthetic datasets that allow models to achieve comparable performance to full-data training while substantially reducing storage and computation. Despite rapid empirical progress, its…
Diffusion language models (dLLMs) generate text by iteratively denoising multiple token positions in parallel, offering an attractive alternative to strictly autoregressive decoding. In practice, however, block-wise dLLM inference exposes a…
The reliability of cloud platforms is of significant relevance because society increasingly relies on complex software systems running on the cloud. To improve it, cloud providers are automating various maintenance tasks, with failure…
Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually…
Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…
Deep learning and signal processing are closely correlated in many IoT scenarios such as anomaly detection to empower intelligence of things. Many IoT processors utilize digital signal processors (DSPs) for signal processing and build deep…
Current AI systems at the tactical edge lack the computational resources to support in-situ training and inference for situational awareness, and it is not always practical to leverage backhaul resources due to security, bandwidth, and…
Cardinality estimation algorithms receive a stream of elements whose order might be arbitrary, with possible repetitions, and return the number of distinct elements. Such algorithms usually seek to minimize the required storage and…
We study differentially-private statistics in the fully dynamic continual observation model, where many updates can arrive at each time step and updates to a stream can involve both insertions and deletions of an item. Earlier work (e.g.,…
We introduce HBLLM, a wavelet-enhanced high-fidelity $1$-bit post-training quantization method for Large Language Models (LLMs). By leveraging Haar wavelet transforms to enhance expressive capacity through frequency decomposition, HBLLM…
Modern model hubs, such as Hugging Face, store tens of petabytes of LLMs, with fine-tuned variants vastly outnumbering base models and dominating storage consumption. Existing storage reduction techniques -- such as deduplication and…
Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for…
Despite recent advancements in large language models (LLMs), their performance on complex reasoning problems requiring multi-step thinking and combining various skills is still limited. To address this, we propose a novel framework HDFlow…
6G networks are composed of subnetworks expected to meet ultra-reliable low-latency communication (URLLC) requirements for mission-critical applications such as industrial control and automation. An often-ignored aspect in URLLC is…
The circllhist histogram is a fast and memory efficient data structure for summarizing large numbers of latency measurements. It is particularly suited for applications in IT infrastructure monitoring, and provides nano-second data…
In the domain of chip design, Hardware Description Languages (HDLs) play a pivotal role. However, due to the complex syntax of HDLs and the limited availability of online resources, debugging HDL codes remains a difficult and time-intensive…