Academic Highlights

Links: arXiv Abstract Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by …

Links: OpenReview GitHub Abstract Current methods for detecting spurious correlations rely on data splits or error patterns, leaving many harmful …

Links: arXiv GitHub Abstract Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake …

Links: arXiv GitHub Abstract Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation …

Links: arXiv Abstract Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to …

Links: arXiv Abstract Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm to improve Large Language Models on …

Links: arXiv GitHub Abstract We present ChronoGraph, a graph-structured multivariate time series forecasting dataset built from real-world production …

Links: arXiv GitHub Abstract Can models generalize attribute knowledge across semantically and perceptually dissimilar categories? While prior work …

Links: arXiv Abstract Sparse Autoencoders (SAEs) have proven valuable due to their ability to provide interpretable and steerable representations. …

Links: arXiv · GitHub Abstract Equivariant neural networks are designed to respect symmetries through their architecture, boosting generalization and …

Links: arXiv GitHub Abstract High-quality molecular representations are essential for property prediction and molecular design, yet large labeled …

Links: arXiv · GitHub Abstract Good datasets are essential for developing and benchmarking any machine learning system. Their importance is even more …

Links: arXiv · CVF Open Access Abstract Common choices of architecture give neural networks a preference for fitting data with simple functions. This …

Links: arXiv Proceedings GitHub Abstract Generative models can create entirely new images, but they can also partially modify real images in ways that …

Links: arXiv Proceedings GitHub Abstract Novelty detection seeks to identify samples deviating from a known distribution, yet data shifts in a …

Links: arXiv Abstract Datasets and pre-trained models come with intrinsic biases. Most methods rely on spotting them by analysing misclassified …

Links: arXiv GitHub Abstract In this work, we propose a simple transformer-based baseline for multimodal molecular representation learning, …

Links: arXiv GitHub Abstract It is of crucial importance to train machine learning models such that they clearly understand what defines each class in …

Links: arXiv GitHub Abstract Message-passing graph neural networks (MPNNs) have emerged as a powerful paradigm for graph-based machine learning. …