Related papers: A.R.I.S.: Automated Recycling Identification Syste…
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous models pre-trained from distinct sources and with diverse architectures,…
Erasure coding techniques are getting integrated in networked distributed storage systems as a way to provide fault-tolerance at the cost of less storage overhead than traditional replication. Redundancy is maintained over time through…
Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products…
Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we cannot only form a decision on the spot, but also ponder,…
During the life span of large software projects, developers often apply the same code changes to different code locations in slight variations. Since the application of these changes to all locations is time-consuming and error-prone, tools…
Retrosynthesis strategically plans the synthesis of a chemical target compound from simpler, readily available precursor compounds. This process is critical for synthesizing novel inorganic materials, yet traditional methods in inorganic…
While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.…
Subset selection from massive data with noised information is increasingly popular for various applications. This problem is still highly challenging as current methods are generally slow in speed and sensitive to outliers. To address the…
Efficient spectrum utilization is critical to meeting the growing data demands of modern wireless communication networks. Automatic Modulation Classification (AMC) plays a key role in enhancing spectrum efficiency by accurately identifying…
This paper presents ARCS (Autoregressive Circuit Synthesis), a system for amortized analog circuit generation. ARCS produces complete, SPICE-simulatable designs (topology and component values) in milliseconds rather than the minutes…
The reconfigurable intelligent surface (RIS) is an emerging technology that changes how wireless networks are perceived, therefore its potential benefits and applications are currently under intense research and investigation. In this…
The increasing urbanization and the growing number of vehicles in cities have underscored the need for efficient parking management systems. Traditional smart parking solutions often rely on sensors or cameras for occupancy detection, each…
This paper tackles two key challenges: detecting small, dense, and overlapping objects (a major hurdle in computer vision) and improving the quality of noisy images, especially those encountered in industrial environments. [1, 2]. Our focus…
Deep Reinforcement Learning (DRL) solutions are becoming pervasive at the edge of the network as they enable autonomous decision-making in a dynamic environment. However, to be able to adapt to the ever-changing environment, the DRL…
In this paper, we develop a new sequential regression modeling approach for data streams. Data streams are commonly found around us, e.g in a retail enterprise sales data is continuously collected every day. A demand forecasting model is an…
In robotics, data acquisition often plays a key part in unknown environment exploration. For example, storing information about the topography of the explored terrain or the natural dangers in the environment can inform the decision-making…
Electric vehicles (EV) create an urgent need for scalable battery recycling, yet disassembly of EV battery packs remains largely manual due to high design variability. We present our Robotic Agentic Platform for Intelligent Disassembly…
Three-dimensional coronary magnetic resonance angiography (CMRA) demands reconstruction algorithms that can significantly suppress the artifacts from a heavily undersampled acquisition. While unrolling-based deep reconstruction methods have…
Evaluating the performance of autonomous vehicles (AV) and their complex subsystems to high precision under naturalistic circumstances remains a challenge, especially when failure or dangerous cases are rare. Rarity does not only require an…
Intelligent reflecting surfaces (IRSs) are emerging as promising enablers for the next generation of wireless communication systems, because of their ability to customize favorable radio propagation environments. However, with the…