Related papers: The Tiny Time-series Transformer: Low-latency High…

The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. Prior research has mostly focused on improving the accuracy and efficiency of classifiers,…

Many real-world time series exhibit strong periodic structures arising from physical laws, human routines, or seasonal cycles. However, modern deep forecasting models often fail to capture these recurring patterns due to spectral bias and a…

Training and deploying deepfake detection models on edge devices offers the advantage of maintaining data privacy and confidentiality by processing it close to its source. However, this approach is constrained by the limited computational…

At present time Robotic observatory making is of current importance. Having a large field of view and being able to point at anywhere, Robotic astronomical systems are indispensable when they looking for transients like grb, supernovae…

Time series account for a large proportion of the data stored in financial, medical and scientific databases. The efficient storage of time series is important in practical applications. In this paper, we propose a novel compression scheme…

Accurate thermospheric density prediction is crucial for reliable satellite operations in Low Earth Orbits, especially at high solar and geomagnetic activity. Physics-based models such as TIE-GCM offer high fidelity but are computationally…

Next-generation wireless networks are expected to leverage multi-modal data sources to execute various wireless communication tasks such as beamforming and blockage prediction with situational-awareness. To do so, multi-modal transformers…

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

We present the Deep-learning Transient Astronomical Object (Deep-TAO), a dataset of 1,249,079 annotated images from the Catalina Real-time Transient Survey, including 3,807 transient and 12,500 non-transient sequences. Deep-TAO has been…

Inference-time scaling trades efficiency for increased reasoning accuracy by generating longer or more parallel sequences. However, in Transformer LLMs, generation cost is bottlenecked by the size of the key-value (KV) cache, rather than…

The nature of scientific and technological data collection is evolving rapidly: data volumes and rates grow exponentially, with increasing complexity and information content, and there has been a transition from static data sets to data…

Nowadays a diverse range of physiological data can be captured continuously for various applications in particular wellbeing and healthcare. Such data require efficient methods for classification and analysis. Deep learning algorithms have…

Gravitational wave astronomy has set in motion a scientific revolution. To further enhance the science reach of this emergent field, there is a pressing need to increase the depth and speed of the gravitational wave algorithms that have…

Modern time-domain astronomical surveys produce high throughput data streams which require tools for processing and analysis. This will be critical for programs making full use of the alert stream from the Vera Rubin Observatory (VRO),…

The Zwicky Transient Facility (ZTF), a public-private enterprise, is a new time domain survey employing a dedicated camera on the Palomar 48-inch Schmidt telescope with a 47 deg$^2$ field of view and 8 second readout time. It is well…

The exponential growth of astronomical data from large-scale surveys has created both opportunities and challenges for the astrophysics community. This paper explores the possibilities offered by transfer learning techniques in addressing…

One of the most compelling goals of observational cosmology is the characterisation of the properties of the dark energy component thought to be responsible for the recent acceleration of the universe, including its possible dynamics. In…

Modern astronomical surveys detect asteroids by linking together their appearances across multiple images taken over time. This approach faces limitations in detecting faint asteroids and handling the computational complexity of trajectory…

Current time domain facilities are finding several hundreds of transient astronomical events a year. The discovery rate is expected to increase in the future as soon as new surveys such as the Zwicky Transient Facility (ZTF) and the Large…

Time-domain astronomy is entering an era of unprecedented discovery driven by wide-field, high-cadence surveys such as LSST, Roman, Euclid, SKA, and PLATO. While some of these facilities will generate enormous photometric alert streams, the…