Neueste Zugänge 

  1. The Hidden Program State Hurts Everyone 

    Thorgeirsson, Sverrir; Graf, Oliver; Su, Zhendong (2024)
    PROCEEDINGS OF THE 2024 ACM SIGPLAN INTERNATIONAL SYMPOSIUM ON NEW IDEAS, NEW PARADIGMS, AND REFLECTIONS ON PROGRAMMING AND SOFTWARE, ONWARD! 2024
    While visual scaffolding, live programming, and direct manipulation of the program state are considered useful programming paradigms for novices, they might not always offer the same benefits to experienced software developers. In this essay, we will use chess as a proxy for exploring how these paradigms can also support those who have an intuitive understanding of the program state and its connection with textual code. We will consider ...
    Conference Paper
  2. Navigating Scaling Laws: Compute Optimality in Adaptive Model Training 

    Anagnostidis, Sotiris; Bachmann, Gregor; Schlag, Imanol; et al. (2024)
    Proceedings of Machine Learning Research ~ Proceedings of the 41st International Conference on Machine Learning
    In recent years, the state-of-the-art in deep learning has been dominated by very large models that have been pre-trained on vast amounts of data. The paradigm is very simple: investing more computational resources (optimally) leads to better performance, and even predictably so; neural scaling laws have been derived that accurately forecast the performance of a network for a desired level of compute. This leads to the notion of a ...
    Conference Paper
  3. Towards Meta-Pruning via Optimal Transport 

    Theus, Alexander; Geimer, Olin; Wicke, Friedrich; et al. (2024)
    Conference Paper
  4. TRANSFORMER FUSION WITH OPTIMAL TRANSPORT 

    Imfeld, Moritz; Graldi, Jacopo; Giordano, Marco; et al. (2024)
    Conference Paper
  5. How Susceptible are LLMs to Influence in Prompts? 

    Anagnostidis, Sotiris; Bulian, Jannis (2024)
    Conference Paper
  6. Motion Control of Autonomous Vehicle with Domain-Centralized Electronic and Electrical Architecture based on Predictive Reinforcement Learning Control Method 

    Du, Guodong; Zou, Yuan; Zhang, Xudong; et al. (2024)
    2024 35TH IEEE INTELLIGENT VEHICLES SYMPOSIUM, IEEE IV 2024
    High-level autonomous vehicles and domain-based electronic and electrical (E/E) architectures are important development directions of the intelligent automobile industry. The domain-centralized E/E architecture has become the potential upgrade to the autonomous vehicle benefitting from its powerful software updates, cabling reduction, and functional integration Aiming at the efficient motion control of the autonomous vehicle equipped with ...
    Conference Paper
  7. Progress on Event-Based Camera Characterization Techniques including Pre-Launch Measurements of the Falcon ODIN Space Experiment 

    McMahon-Crabtree, Peter N.; Kulesza, Lucas; Marcireau, Alexandre; et al. (2024)
    UNCONVENTIONAL IMAGING, SENSING, AND ADAPTIVE OPTICS 2024
    Event-based vision sensor (EVS) technology has expanded the CMOS image sensor design space of low-SWaP sensors with high-dynamic range operation and ability, under certain conditions, to efficiently capture scene information at a temporal resolution beyond that achievable by a typical sensor operating near a 1 kHz frame rate. Fundamental differences between EVS and framing sensors necessitate development of new characterization techniques ...
    Conference Paper
  8. A Language Model's Guide Through Latent Space 

    von Rütte, Dimitri; Anagnostidis, Sotiris; Bachmann, Gregor; et al. (2024)
    Proceedings of Machine Learning Research ~ Proceedings of the 41st International Conference on Machine Learning
    Concept guidance has emerged as a cheap and simple way to control the behavior of language models by probing their hidden representations for concept vectors and using them to perturb activations at inference time. While the focus of previous work has largely been on truthfulness, in this paper we extend this framework to a richer set of concepts such as appropriateness, humor, creativity and quality, and explore to what degree current ...
    Conference Paper
  9. Towards RehabCoach: Design and Preliminary Evaluation of a Conversational Agent Supporting Unsupervised Therapy After Stroke 

    Devittori, Giada; Akeddar, Mehdi; Retevoi, Alexandra; et al. (2024)
    2024 10th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob)
    Unsupervised therapy after stroke is a promising way to boost therapy dose without significantly increasing the workload on healthcare professionals. However, it raises important challenges, such as lower adherence to therapy in the absence of social interaction with therapists. We present the initial prototype of RehabCoach, a novel smartphone-based app with conversational agent to support unsupervised therapy. RehabCoach is designed to ...
    Conference Paper
  10. A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes 

    Ma, Qi; Paudel, Danda Pani; Konukoglu, Ender; et al. (2024)
    Conference Paper
  11. StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation 

    Wu, Sidi; Chen, Yizi; Mermet, Samuel; et al. (2024)
    2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains. However, this assumption does not always hold in real-world scenarios due to divergent distributions, different class sets, and asymmet- rical information representation. As conventional GANs attempt to generate images that match the distribution of the target domain, they may hallucinate ...
    Conference Paper
  12. Comparison of 16 national methods in the life cycle assessment of carbon storage in wood products in a reference building 

    Ouellet-Plamondon, Claudiane M.; Balouktsi, M; Delem, L; et al. (2024)
    IOP Conference Series: Earth and Environmental Science
    Wood and bio-based construction products are perceived as a way to use renewable resources, to save energy and to mitigate greenhouse gas (GHG)-emissions during production and to store carbon during the entire service life of the building. This article compares the carbon footprint per kilogram of wood products (softwood beams, plywood, oriented strand board panel, and fibre board) from the perspective of the life cycle assessment methodology ...
    Conference Paper
  13. Data-Driven Railway Vehicle Parameter Tuning using Markov-Chain Monte Carlo Bayesian updating 

    Hoelzl, Cyprien; Keller, Lisa; Simpson, Thomas; et al. (2024)
    Journal of Physics: Conference Series
    Conference Paper
  14. Identification of Railway Bridge Modal Properties via Acceleration Data from Traversing Trains 

    Stoura, Charikleia D.; Dertimanis, Vasilis K.; Chatzi, Eleni N. (2024)
    Conference Proceedings of the Society for Experimental Mechanics Series
    Conference Paper
  15. Shadow Health-Related Data: Definition, Categorization, and User Perspectives 

    El Zein, Yamane; Salehzadeh Niksirat, Kavous; Zufferey, Noé; et al. (2024)
    EuroUSEC '24: Proceedings of the 2024 European Symposium on Usable Security
    Health-related data (HRD) about individuals are increasingly generated and processed. The sources and volume of such data have grown larger over the past years, they include wearable devices, health-related mobile apps, and electronic health records. HRD are sensitive, have important privacy implications, hence hold a special status under existing privacy laws and regulations. In this work, we focus on shadow HRD: these HRD are generated ...
    Conference Paper
  16. MUSES: The Multi-sensor Semantic Perception Dataset for Driving Under Uncertainty 

    Brödermann, Tim; Bruggemann, David; Sakaridis, Christos; et al. (2025)
    Lecture Notes in Computer Science ~ Computer Vision - ECCV 2024
    Achieving level-5 driving automation in autonomous vehicles necessitates a robust semantic visual perception system capable of parsing data from different sensors across diverse conditions. However, existing semantic perception datasets often lack important non-camera modalities typically used in autonomous vehicles, or they do not exploit such modalities to aid and improve semantic annotations in challenging conditions. To address this, ...
    Conference Paper
  17. Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation? 

    Cekmeceli, Kerem; Himmetoglu, Meva; Tombak, Guney I.; et al. (2024)
    Neural networks achieve state-of-the-art performance in many supervised learning tasks when the training data distribution matches the test data distribution. However, their performance drops significantly under domain (covariate) shift, a prevalent issue in medical image segmentation due to varying acquisition settings across different scanner models and protocols. Recently, foundational models (FMs) trained on large datasets have gained ...
    Conference Paper
  18. Convergence guarantees for adaptive model predictive control with kinky inference 

    Zuliani, Riccardo; Soloperto, Raffaele; Lygeros, John (2024)
    Proceedings of Machine Learning Research
    We analyze the convergence properties of a robust adaptive model predictive control algorithm used to control an unknown nonlinear system. We show that by employing a standard quadratic stabilizing cost function, and by recursively updating the nominal model through kinky inference, the resulting controller ensures convergence of the true system to the origin, despite the presence of model uncertainty. We illustrate our theoretical findings ...
    Conference Paper
  19. Exploring Tokenized Product Passports for Circular Construction Supply Chains 

    Byers, Brandon; Hunhevicz, Jens Juri; Honic-Eser, Meliha; et al. (2024)
    Computing in Construction ~ Proceedings of the 2024 European Conference on Computing in Construction
    A token is a cryptoeconomic entity on a blockchain that can be used to digitally secure, represent, and trade assets. Existing research does not sufficiently explore the use of tokenization as digital representations of physical construction assets within the context of circular supply chains. Thus, this research explores why tokenization for circular construction may be helpful by employing a mixed methods approach via quantitative and ...
    Conference Paper
  20. Deep Equilibrium Diffusion Restoration with Parallel Sampling 

    Cao, Jiezhang; Shi, Yue; Zhang, Kai; et al. (2024)
    2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
    Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images achieving promising performance. Due to the inherent property of diffusion models most existing methods need long serial sampling chains to restore HQ images step-by-step resulting in expensive sampling time and high computation costs. Moreover, such long sampling chains hinder understanding the relationship ...
    Conference Paper

Mehr anzeigen