arXiv AI
Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 15
Local Diagnostics of Continuous Normalizing Flow for Out-of-Distribution Detection
arXiv:2606.00684v3 Announce Type: replace-cross Abstract: We address the problem of out-of-distribution (OOD) detection for target observations embedded in a subspace of the high dimensional data spa...
arXiv Machine Learning
Jun 5
Zero-Flow Encoders
arXiv:2602. 00797v2 Announce Type: replace-cross Abstract: Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions.
arXiv Machine Learning
Oct 2
From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
The paper introduces entropy-ordered flows (EOFlows), a normalizing flow framework that adds an orthogonality regularizer on the decoder Jacobian to promote geometric disentanglement. EOFlows produce near‑orthogonal curvilinear coordinates whose features can be ranked by explained manifold entropy, providing a nonlinear analogue to PCA. The method yields an order‑of‑magnitude more stable features than existing approaches, categorizing them into global, local, and generic types, and can be trimmed to form an autoencoder with competitive rate‑distortion performance.
arXiv AI
Jul 17
Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions
arXiv:2607. 14306v1 Announce Type: new Abstract: In this paper, we study the connection between an LLM's output distribution and the data used to train it.
arXiv Machine Learning
Jun 30
High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.
arXiv Machine Learning
Sep 17
Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows
The paper introduces Contrastive Noise Alignment (CNA), a training-time method for generative flow models that dynamically aligns Gaussian noise with data samples using a cross-modal InfoNCE objective. By modeling noise as an interacting particle system and regularizing with angular entropy and radial norm penalties, CNA reduces arbitrary data-noise couplings and flow curvature. Empirical results show that CNA improves generation quality, lowering FID by over 50% for few-step pixel-space generation compared to standard rectified flow and outperforming optimal transport baselines by at least 24%.