Related papers: MoMEMta, a modular toolkit for the Matrix Element …
This study presents a semi-nonparametric Latent Class Choice Model (LCCM) with a flexible class membership component. The proposed model formulates the latent classes using mixture models as an alternative approach to the traditional random…
With the growing complexity of computational and experimental facilities, many scientific researchers are turning to machine learning (ML) techniques to analyze large scale ensemble data. With complexities such as multi-component workflows,…
This paper proposes an approach for segmenting a task consisting of compliant motions into phases, learning a primitive for each segmented phase of the task, and reproducing the task by sequencing primitives online based on the learned…
We introduce $\texttt{mosca}$, a $\texttt{Mathematica}$ package designed to facilitate on-shell calculations in effective field theories (EFTs). This initial release focuses on the reduction of Green's bases to physical bases, as well as…
Fully Homomorphic Encryption (FHE) enables privacy preserving computation but it suffers from high latency and memory consumption. The computations are secured with special keys called rotation keys which often take up the majority of…
While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge. Training workloads impose distinct constraints,…
Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LLMs are utilizing external references to generate an answer.…
This paper introduces Patched MOA (Mixture of Agents), an inference optimization technique that significantly enhances the performance of large language models (LLMs) across diverse software development tasks. We evaluate three inference…
The rapid advancements in Large Language Models (LLMs) have significantly expanded their applications, ranging from multilingual support to domain-specific tasks and multimodal integration. In this paper, we present OmniEvalKit, a novel…
Leveraging the powerful reasoning capabilities of large language models (LLMs), recent LLM-based robot task planning methods yield promising results. However, they mainly focus on single or multiple homogeneous robots on simple tasks.…
In late fusion, each modality is processed in a separate unimodal Convolutional Neural Network (CNN) stream and the scores of each modality are fused at the end. Due to its simplicity late fusion is still the predominant approach in many…
The matrix element technique provides a superior statistical sensitivity for precision measurements of important parameters at hadron colliders, such as the mass of the top quark or the cross section for the production of Higgs bosons. The…
Video understanding is a complex challenge that requires effective modeling of spatial-temporal dynamics. With the success of image foundation models (IFMs) in image understanding, recent approaches have explored parameter-efficient…
Full automation is often not achievable or desirable in critical systems with high-stakes decisions. Instead, human-AI teams can achieve better results. To research, develop, evaluate, and validate algorithms suited for such teaming,…
Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differing in parameter scale, execution mode (forward-only or full…
This paper introduces Modular Linear Tokenization (MLT), a reversible and deterministic technique for encoding high-cardinality categorical identifiers into compact numerical vectors. Unlike traditional hashing or one-hot encodings, MLT…
Algorithm portfolio and selection approaches have achieved remarkable improvements over single solvers. However, the implementation of such systems is often highly customised and specific to the problem domain. This makes it difficult for…
Advanced detector R&D for both new and ongoing experiments in HEP requires performing computationally intensive and detailed simulations as part of the detector-design optimisation process. We propose a versatile approach to this task that…
In the first three years of running, the LHC has delivered a wealth of new data that is now being analysed. With over 20 fb$^{-1}$ of integrated luminosity, both ATLAS and CMS have performed many searches for new physics that theorists are…
Folklore is often saying "The Java memory model is broken." Therefore, several approaches have proposed repairs, only to find new programs exhibiting unexpected, unintuitive behavior or the model forbidding standard compiler optimizations.…