arXiv:2509.19504v1 Announce Type: new Abstract: Counterfactual explanation (CE) is a widely used post-hoc method that provides individuals with actionable changes to alter an unfavorable prediction from a machine learning model. Plausible CE methods improve realism by considering data distribution characteristics,…
arXiv:2508.15690v2 Announce Type: replace-cross Abstract: GRAFT is a structured multimodal benchmark for evaluating models on instruction-following, visual reasoning, and visual-textual alignment tasks. It features programmatically generated charts and synthetically rendered tables, created with Python visualization libraries to ensure control over…
arXiv:2509.19506v1 Announce Type: new Abstract: Recent methods for molecular generation face a trade-off: they either enforce strict equivariance with costly architectures or relax it to gain scalability and flexibility. We propose a frame-based diffusion paradigm that achieves deterministic E(3)-equivariance while…
arXiv:2509.19707v1 Announce Type: cross Abstract: Copulas are a fundamental tool for modelling multivariate dependencies in data, forming the method of choice in diverse fields and applications. However, the adoption of existing models for multimodal and high-dimensional dependencies is hindered by…
arXiv:2509.19526v1 Announce Type: new Abstract: Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure…
arXiv:2509.19997v1 Announce Type: cross Abstract: In this work, we leverage informative embeddings from foundational models for unsupervised anomaly detection in medical imaging. For small datasets, a memory-bank of normative features can directly be used for anomaly detection which has been…
arXiv:2509.19538v1 Announce Type: new Abstract: Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforcement learning (RL). However, many existing methods do not directly generate actions alongside states and rewards, limiting their compatibility with standard…
arXiv:2509.20134v1 Announce Type: cross Abstract: The “No Free Lunch” theorem dictates that no single recommender algorithm is optimal for all users, creating a significant Algorithm Selection Problem. Standard meta-learning approaches aim to solve this by selecting an algorithm based on…
arXiv:2509.19554v1 Announce Type: new Abstract: This thesis explores how deep learning models learn over time, using ideas inspired by force analysis. Specifically, we zoom in on the model’s training procedure to see how one training example affects another during learning,…
arXiv:2509.20239v1 Announce Type: cross Abstract: This paper investigates theoretical and methodological foundations for stochastic optimal control (SOC) in discrete time. We start formulating the control problem in a general dynamic programming framework, introducing the mathematical structure needed for a detailed…
