Source author record

Ivona Brandić

Ivona Brandić appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Distributed, Parallel, and Cluster Computing Machine Learning Computer Vision quant-ph

Catalog footprint

What is connected

3works

4topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference

Edge deployment of Vision-Language Models (VLMs) faces a tradeoff between latency and accuracy: cloud execution provides high-quality predictions but incurs communication delay and energy cost, while edge-only execution is faster but less accurate due to limited model capacity. This trade-off is further complicated by heterogeneity in image quality and reasoning complexity, making static placement suboptimal. We present INAR-VL, a lightweight edge-cloud routing system for multimodal inference in a two-tier deployment. INAR-VL maintains complementary VLMs across edge and cloud and uses lightweight image and text complexity signals to guide routing and model selection, executing simple queries locally while offloading complex ones when beneficial. Evaluation on visual question answering shows that INAR-VL executes 36% of requests on the edge, reduces latency by 24%, lowers energy by 26%, and preserves 97% of cloud-level accuracy.

preprint2025arXiv

Limits of quantum generative models with classical sampling hardness

Sampling tasks have been successful in establishing quantum advantages both in theory and experiments. This has fueled the use of quantum computers for generative modeling to create samples following the probability distribution underlying a given dataset. In particular, the potential to build generative models on classically hard distributions would immediately preclude classical simulability, due to theoretical separations. In this work, we study quantum generative models from the perspective of output distributions, showing that models that anticoncentrate are not trainable on average, including those exhibiting quantum advantage. In contrast, models outputting data from sparse distributions can be trained. We consider special cases to enhance trainability, and observe that this opens the path for classical algorithms for surrogate sampling. This observed trade-off is linked to verification of quantum processes. We conclude that quantum advantage can still be found in generative models, although its source must be distinct from anticoncentration.

preprint2013arXiv

Take a break: cloud scheduling optimized for real-time electricity pricing

Cloud computing revolutionised the industry with its elastic, on-demand approach to computational resources, but has lead to a tremendous impact on the environment. Data centers constitute 1.1-1.5% of total electricity usage in the world. Taking a more informed view of the electrical grid by analysing real-time electricity prices, we set the foundations of a grid-conscious cloud. We propose a scheduling algorithm that predicts electricity price peaks and throttles energy consumption by pausing virtual machines. We evaluate the approach on the OpenStack cloud manager through an empirical approach and show reductions in energy consumption and costs. Finally, we define green instances in which cloud providers can offer such services to their customers under better pricing options.