Search
Results
-
Clustering on multi-layer graphs via subspace analysis on Grassmann manifolds
(2013)2013 IEEE Global Conference on Signal and Information ProcessingRelationships between entities in datasets are often of multiple types, which can naturally be modeled by a multi-layer graph; a common vertex set represents the entities and the edges on different layers capture different types of relationships between the entities. In this paper, we address the problem of analyzing multi-layer graphs and propose methods for clustering the vertices by efficiently merging the information provided by the ...Conference Paper -
Adaptive thresholding for sequence-based place recognition
(2025)Robots need to know where they are in the world to operate effectively without human support. One common first step for precise robot localization is visual place recognition. It is a challenging problem, especially when the output is required in an online fashion, and the current state-of-the-art approaches that tackle it usually require either large amounts of labeled training data or rely on parameters that need to be tuned manually, ...Conference Paper -
Are Smart Planning Tools Failing Rapidly Urbanising Cities?
(2025)This special session was led by Pari Sen Biswas and Joshua Vargas, researchers at the Future Cities Laboratory (Singapore-ETH Centre). They critically examined whether smart city technologies are capable of revolutionising urban planning practice and making data- driven insights accessible to urban practitioners. In rapidly urbanising cities across the Global South, planning support tool (PST) integration attempts have failed and ...Conference Proceedings -
MPQ-DM: Mixed Precision Quantization for Extremely Low Bit Diffusion Models
(2025)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-25 Technical Tracks 16Diffusion models have received wide attention in generation tasks. However, the expensive computation cost prevents the application of diffusion models in resource-constrained scenarios. Quantization emerges as a practical solution that significantly saves storage and computation by reducing the bit-width of parameters. However, the existing quantization methods for diffusion models still cause severe degradation in performance, especially ...Conference Paper -
Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community
(2025)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-25 Technical Tracks 6Object detection, particularly open-vocabulary object detection, plays a crucial role in Earth sciences, such as environmental monitoring, natural disaster assessment, and land-use planning. However, existing open-vocabulary detectors, primarily trained on natural-world images, struggle to generalize to remote sensing images due to a significant data domain gap. Thus, this paper aims to advance the development of open-vocabulary object ...Conference Paper -
Calibrating Large Language Models with Sample Consistency
(2025)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-25 Technical Tracks 18Accurately gauging the confidence level of Large Language Models' (LLMs) predictions is pivotal for their reliable application. However, LLMs are often inherently uncalibrated and elude conventional calibration techniques due to their proprietary nature and massive scale. In this work, we derive model confidence from the distribution of multiple randomly sampled generations, using three measures of consistency. We extensively evaluate ...Conference Paper -
FIRM: Flexible Interactive Reflection ReMoval
(2025)Proceedings of the AAAI Conference on Artificial Intelligence ~ AAAI-25 Technical Tracks 2Removing reflection from a single image is challenging due to the absence of general reflection priors. Although existing methods incorporate extensive user guidance for satisfactory performance, they often lack the flexibility to adapt user guidance in different modalities, and dense user interactions further limit their practicality. To alleviate these problems, this paper presents FIRM, a novel framework for Flexible Interactive image ...Conference Paper -
Bridging the AI Gap: Evaluating the Impact of an AI Education Program for Caregivers on Parental Leave
(2025)Proceedings of the AAAI Conference on Artificial Intelligence ~ IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and DemonstrationsArtificial Intelligence (AI) literacy is increasingly important across many fields, yet caregivers remain underrepresented in AI-related fields due to a combination of systemic and individual barriers. To address this, the Caregivers and Machine Learning (C&ML) program developed and delivered an accessible AI education program to caregivers on parental leave. Two cohorts participated in this 6-week interprofessional program, featuring ...Conference Paper -
HybriDIFT: Scalable Memory-Aware Dynamic Information Flow Tracking for Hardware
(2024)ICCAD '24: Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided DesignDesigning correct and secure hardware is challenging. Dynamic information flow tracking (DIFT) enhances RTL testing flows, for example, by providing formal guarantees on detecting information leakage. However, existing DIFT solutions do not scale to large memories encountered in complex processors. A formal analysis of existing DIFT mechanisms reveals the two factors that fundamentally limit the scalability of instrumenting memories: ...Conference Paper -
SeBS 2.0: Keeping up with the Clouds
(2025)SESAME' 25: Proceedings of the 3rd Workshop on SErverless Systems, Applications and MEthodologiesThree years ago, SeBS, the serverless benchmarking suite, was introduced to address the need for an automatic, representative, and easy-to-use benchmarking framework for FaaS applications. SeBS has been widely adopted in research projects and has evolved to incorporate new features addressing the changing landscape of FaaS platforms. As serverless workflows and services continue to grow in size and complexity, there is an ongoing need to ...Conference Paper