Related papers: The BaBar Mini
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy resources. This challenge discourages…
Event cameras provide a compelling alternative to traditional frame-based sensors, capturing dynamic scenes with high temporal resolution and low latency. Moving objects trigger events with precise timestamps along their trajectory,…
To reduce the source of potential exploits, binary debloating or specialization tools are used to remove unnecessary code from binaries. This paper presents a new binary debloating and specialization tool, LeanBin, that harnesses lifting…
Traditional reliability analysis has been using time to event data, degradation data, and recurrent event data, while the associated covariates tend to be simple and constant over time. Over the past years, we have witnessed the rapid…
Most pattern mining methods output a very large number of frequent patterns and isolating a small but relevant subset is a challenging problem of current interest in frequent pattern mining. In this paper we consider discovery of a small…
Transformers excel through content-addressable retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative memory at the level of probability measures, treating a context as a distribution over…
Process mining aims to comprehend and enhance business processes by analyzing event logs. Recently, object-centric process mining has gained traction by considering multiple objects interacting with each other in a process. This…
A wireless network serving multiple users in the millimeter-wave or the sub-terahertz band by a base station is considered. High-throughput multi-user hybrid-transmit beamforming is conceived by maximizing the minimum rate of the users. For…
The blooming of fake news on social networks has devastating impacts on society, economy, and public security. Although numerous studies are conducted for the automatic detection of fake news, the majority tend to utilize deep neural…
Event cameras are bio-inspired sensors that differ from conventional frame cameras: Instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes, and output a stream of events that encode the time,…
Monitoring the status of large computing systems is essential to identify unexpected behavior and improve their performance and uptime. However, due to the large-scale and distributed design of such computing systems as well as a large…
Embedded devices collect and process significant amounts of data in a variety of applications including environmental monitoring, industrial automation and control, and other Internet of Things (IoT) applications. Storing data efficiently…
Large language models are limited in deployment by GPU memory and inference latency. We present Minima, a production compression pipeline that learns where and how to structurally compress a Transformer and turns that compression into real…
We present BIEBER (Byte-IdEntical Binary parsER), the first system to model and regenerate a full working parser from instrumented program executions. To achieve this, BIEBER exploits the regularity (e.g., header fields and array-like data…
The execution of processes leaves traces of event data in information systems. These event data can be analyzed through process mining techniques. For traditional process mining techniques, one has to associate each event with exactly one…
Dynamic Vision Sensors (DVS) exhibit exceptional dynamic range and low power consumption, making them ideal for edge applications in the Internet of Video Things (IoVT). However, their output is often degraded by spurious Background…
A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably…
Large-scale embedding-based retrieval (EBR) is the cornerstone of search-related industrial applications. Given a user query, the system of EBR aims to identify relevant information from a large corpus of documents that may be tens or…
We present Jamba-1.5, new instruction-tuned large language models based on our Jamba architecture. Jamba is a hybrid Transformer-Mamba mixture of experts architecture, providing high throughput and low memory usage across context lengths,…
In this technical report, we present the Ring-linear model series, specifically including Ring-mini-linear-2.0 and Ring-flash-linear-2.0. Ring-mini-linear-2.0 comprises 16B parameters and 957M activations, while Ring-flash-linear-2.0…