Related papers: The BaBar Mini
We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-quality web and synthetic data, significantly outperforming recent…
Previous industrial anomaly detection methods often struggle to handle the extensive diversity in training sets, particularly when they contain stylistically diverse and feature-rich samples, which we categorize as feature-rich anomaly…
Narrow bit-width data formats are key to reducing the computational and storage costs of modern deep learning applications. This paper evaluates Microscaling (MX) data formats that combine a per-block scaling factor with narrow…
Event cameras encode visual information with high temporal precision, low data-rate, and high-dynamic range. Thanks to these characteristics, event cameras are particularly suited for scenarios with high motion, challenging lighting…
Event cameras have higher temporal resolution, and require less storage and bandwidth compared to traditional RGB cameras. However, due to relatively lagging performance of event-based approaches, event cameras have not yet replace…
Event cameras are novel sensors that report brightness changes in the form of asynchronous "events" instead of intensity frames. They have significant advantages over conventional cameras: high temporal resolution, high dynamic range, and…
This paper presents a novel event-based eye-tracking system deployed on a resource-constrained microcontroller, addressing the challenges of real-time, low-latency, and low-power performance in embedded systems. The system leverages a…
The event camera's low power consumption and ability to capture microsecond brightness changes make it attractive for various computer vision tasks. Existing event representation methods typically convert events into frames, voxel grids, or…
Fully supervised change detection methods have achieved significant advancements in performance, yet they depend severely on acquiring costly pixel-level labels. Considering that the patch-level annotations also contain abundant information…
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming. Thus,…
Manufacturing-viable neuromorphic chips require novel computer architectures to achieve the massively parallel and efficient information processing the brain supports so effortlessly. Emerging event-based architectures are making this dream…
We introduce a new technique for the efficient management of large sequences of multidimensional data, which takes advantage of regularities that arise in real-world datasets and supports different types of aggregation queries. More…
Raw data sizes are growing and proliferating in scientific research, driven by the success of data-hungry computational methods, such as machine learning. The preponderance of proprietary and shoehorned data formats make computations slower…
An evolved real-time data processing strategy is proposed for high-energy physics experiments, and its implementation at the LHCb experiment is presented. The reduced event model allows not only the signal candidate firing the trigger to be…
Transformers have achieved promising results on a variety of tasks. However, the quadratic complexity in self-attention computation has limited the applications, especially in low-resource settings and mobile or edge devices. Existing works…
Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal…
This paper presents a storage-efficient learning model titled Recursive Binary Neural Networks for sensing devices having a limited amount of on-chip data storage such as < 100's kilo-Bytes. The main idea of the proposed model is to…
Recurrent neural networks are now the state-of-the-art in natural language processing because they can build rich contextual representations and process texts of arbitrary length. However, recent developments on attention mechanisms have…
Object-centric process mining is emerging as a promising paradigm across diverse industries, drawing substantial academic attention. To support its data requirements, existing object-centric data formats primarily facilitate the exchange of…
Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased…