Related papers: Hyperloop -- The ALICE analysis train system for R…
We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among the small and intricate parts. For…
The Large Hadron Collider (LHC) at the European Organization for Nuclear Research (CERN) is the world's largest and most powerful particle accelerator colliding beams of protons and lead ions at energies up to 7 ZTeV, Z is the atomic…
The ALICE High Level Trigger has to process data online, in order to select interesting (sub)events, or to compress data efficiently by modeling techniques. Focusing on the main data source, the Time Projection Chamber (TPC), we present two…
While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-context examples under audio conditioning remains unstudied. To address this gap,…
Recent research has shown that LLM performance on reasoning tasks can be enhanced by scaling test-time compute. One promising approach, particularly with decomposable problems, involves arranging intermediate solutions as a graph on which…
The Inner Tracking System (ITS) is the key ALICE detector for the study of heavy flavour production at LHC. Heavy flavor can be studied via the identification of short-lived hadrons containing heavy quarks which have a mean proper decay…
Supervised machine learning and deep learning require a large amount of labeled data, which data scientists obtain in a manual, and time-consuming annotation process. To mitigate this challenge, Active Learning (AL) proposes promising data…
To support operations and passenger-facing services, transit agencies need reliable passenger load trajectories. Currently, load estimates are typically inferred from imperfect sensing systems rather than fully observed, and the accuracy of…
ALICE (A Large Ion Collider Experiment) aims at studying the behaviour of nuclear matter at high energy densities and the transition to the Quark Gluon Plasma (QGP), expected to occur in ultra-relativistic heavy ion collisions. Quarkonia…
In ultra-relativistic heavy-ion collisions at $\sqrt{s_{NN}}$ = 5.5 TeV at the ALICE experiment at the LHC, interactions between the high-$p_{T}$ partons and the hot, dense medium produced in the collisions, are expected to lead to jet…
Simulation is a fundamental tool in developing autonomous vehicles, enabling rigorous testing without the logistical and safety challenges associated with real-world trials. As autonomous vehicle technologies evolve and public safety…
In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foster fair evaluation…
This study presents the development of the PsyCogMetrics AI Lab (psycogmetrics.ai), an integrated, cloud-based platform that operationalizes psychometric and cognitive-science methodologies for Large Language Model (LLM) evaluation. Framed…
With the widespread installation of location-enabled devices on public transportation, public vehicles are generating massive amounts of trajectory data in real time. However, using these trajectory data for meaningful analysis requires…
Railway operations require control systems to ensure safety and efficiency, and to coordinate infrastructure elements such as switches, signals and train protection. To compete with the traditional approaches to these systems, a…
Grounded theory offers deep insights from qualitative data, but its reliance on expert-intensive manual coding presents a major scalability bottleneck. Existing computational tools either fail on full automation or lack flexible schema…
The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…
The ATLAS Trigger system is a key component of the ATLAS experiment at the CERN Large Hadron Collider (LHC), designed to reduce the event rate from the 40 MHz proton-proton bunch crossing frequency to an output suitable for offline storage…
Reasoning-based end-to-end (E2E) autonomous driving has recently emerged as a promising approach to improving the interpretability of driving decisions as it can generate human-readable reasoning together with predicted trajectories. Such…
Tool-using agent systems powered by large language models (LLMs) are increasingly deployed across web, app, operating-system, and transactional environments. Yet existing safety benchmarks still emphasize explicit risks, potentially…