Related papers: ZeroSim: Zero-Shot Analog Circuit Evaluation with …

Learning code representations has been the core prerequisite of many software engineering tasks such as code clone detection and code generation. State-of-the-art program representation techniques mainly utilize pre-trained language models…

Zero-shot learning (ZSL) enables solving a task without the need to see its examples. In this paper, we propose two ZSL frameworks that learn to synthesize parameters for novel unseen classes. First, we propose to cast the problem of ZSL as…

Recent progress of voice conversion~(VC) has achieved a new milestone in speaker cloning and linguistic preservation. But the field remains fragmented, relying on specialized models for linguistic-preserving, expressive, and singing…

The goal of coreset selection is to identify representative subsets of datasets for efficient model training. Yet, existing approaches paradoxically require expensive training-based signals, e.g., gradients, decision boundary estimates or…

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…

Telerobotic technologies are becoming increasingly essential in fields such as remote surgery, nuclear decommissioning, and space exploration. Reliable datasets and testbeds are essential for evaluating telerobotic system performance prior…

Sparse matrix-matrix multiplication (SpGEMM) is a critical kernel widely employed in machine learning and graph algorithms. However, real-world matrices' high sparsity makes SpGEMM memory-intensive. In-situ computing offers the potential to…

In the early stages of semiconductor equipment development, obtaining large quantities of raw optical images poses a significant challenge. This data scarcity hinder the advancement of AI-powered solutions in semiconductor manufacturing. To…

Tremendous progress has been made in deep stereo matching to excel on benchmark datasets through per-domain fine-tuning. However, achieving strong zero-shot generalization - a hallmark of foundation models in other computer vision tasks -…

Zero-shot learning aims at recognizing unseen classes (no training example) with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space shared by both seen and unseen classes, i.e.,…

Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…

Zero-shot learning (ZSL) aims to recognize the novel object categories using the semantic representation of categories, and the key idea is to explore the knowledge of how the novel class is semantically related to the familiar classes.…

Domain specialization under energy constraints in deeply-scaled CMOS has been driving the need for agile development of Systems on a Chip (SoCs). While digital subsystems have design flows that are conducive to rapid iterations from…

As deep neural networks require tremendous amount of computation and memory, analog computing with emerging memory devices is a promising alternative to digital computing for edge devices. However, because of the increasing simulation time…

Accurate and efficient characterization of nanoparticle morphology in Scanning Electron Microscopy (SEM) images is critical for ensuring product quality in nanomaterial synthesis and accelerating development. However, conventional deep…

Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, like multimodal translation, often require a combination of…

Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learningbased segmentation techniques require extensive annotated datasets,…

Semantic segmentation is a fundamental task in medical image analysis and autonomous driving and has a problem with the high cost of annotating the labels required in training. To address this problem, semantic segmentation methods based on…

The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes.…

Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling…