Related papers: PrismSSL: One Interface, Many Modalities; A Single…

Understanding the relationship between training data and model behavior during pretraining is crucial, but existing workflows make this process cumbersome, fragmented, and often inaccessible to researchers. We present TokenSmith, an…

Remote sensing data has been widely used for various Earth Observation (EO) missions such as land use and cover classification, weather forecasting, agricultural management, and environmental monitoring. Most existing remote sensing…

In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL…

Despite progress in gloss-free Sign Language Translation (SLT), traditional single modality end-to-end approaches consistently fail on two critical components of natural signing: the precise recognition of high-speed fingerspelling and the…

We present PyMoosh, a Python-based simulation library designed to provide a comprehensive set of numerical tools allowing to compute essentially all optical characteristics of multilayered structures, ranging from reflectance and…

Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar…

Computer simulation has become one of the most important tools in scientific research in many disciplines. Benefiting from the dynamical trajectories regulated by versatile interatomic interactions, various material properties can be…

We present ByzFL, an open-source Python library for developing and benchmarking robust federated learning (FL) algorithms. ByzFL provides a unified and extensible framework that includes implementations of state-of-the-art robust…

Evaluating LLMs with a single prompt has proven unreliable, with small changes leading to significant performance differences. However, generating the prompt variations needed for a more robust multi-prompt evaluation is challenging,…

After pre-training on extensive image-text pairs, Contrastive Language-Image Pre-training (CLIP) demonstrates promising performance on a wide variety of benchmarks. However, a substantial volume of multimodal interleaved documents remains…

Language Models (LLMs), such as transformer-based neural networks trained on billions of parameters, have become increasingly prevalent in software engineering (SE). These models, trained on extensive datasets that include code…

We present Qiskit Machine Learning (ML), a high-level Python library that combines elements of quantum computing with traditional machine learning. The API abstracts Qiskit's primitives to facilitate interactions with classical simulators…

Semi-supervised classification leverages both labeled and unlabeled data to improve predictive performance, but existing software support remains fragmented across methods, learning settings, and data modalities. We introduce ModSSC, an…

RSL-RL is an open-source Reinforcement Learning library tailored to the specific needs of the robotics community. Unlike broad general-purpose frameworks, its design philosophy prioritizes a compact and easily modifiable codebase, allowing…

Semi-supervised learning (SSL) has emerged as a promising paradigm for breast ultrasound (BUS) image segmentation, but it often suffers from unstable pseudo labels under extremely limited annotations, leading to inaccurate supervision and…

Confidence-based pseudo-labeling is among the dominant approaches in semi-supervised learning (SSL). It relies on including high-confidence predictions made on unlabeled data as additional targets to train the model. We propose ProtoCon, a…

Vision Language Models (VLMs) demonstrate remarkable proficiency in addressing a wide array of visual questions, which requires strong perception and reasoning faculties. Assessing these two competencies independently is crucial for model…

Self-supervised learning (SSL) has become the de facto training paradigm of large models, where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Despite demonstrating comparable performance with…

Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent work has shown that it is highly vulnerable to poisoning-based backdoor attacks operating…

We present SPDL (Scalable and Performant Data Loading), an open-source, framework-agnostic library designed for efficiently loading array data to GPU. Data loading is often a bottleneck in AI applications, and is challenging to optimize…