DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
9 Pith papers cite this work, alongside 59 external citations. Polarity classification is still indexing.
9
Pith papers citing it
59
external citations · external index
representative citing papers
Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank them below trained models.
StressDream optimizes initial noise in diffusion video world models using VLM semantic and plausibility objectives to steer generations toward specified high-impact outcomes for improved policy evaluation.
KLIP detects and localizes distribution shifts in inverse problems via KL-divergence between diffusion prior and posterior without calibration data.
SITN performs single-sample OOD detection via goodness-of-fit testing on noise samples in the factorised latent space of continuous normalizing flows.
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
Diffusion model climate emulators provide probability density estimates that allow likelihood calculations and odds-ratio-based importance sampling for extreme events such as tropical cyclones.
PPE framework with T3+OCSVM one-class detector reaches 0.93+ borderline AUROC, cuts false positives 44-55 points versus Gaussian baselines, and runs at millisecond latency on synthetic multi-domain data.
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.
citing papers explorer
-
Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning
DOSER detects OOD actions via diffusion-model denoising error and applies selective regularization based on predicted transitions, proving gamma-contraction with performance bounds and outperforming priors on offline RL benchmarks.
-
Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics
Zero-parameter naive samplers achieve state-of-the-art generative perplexity while producing incoherent text, proving the metric is unsound; distributional divergences like MAUVE and energy distance correctly rank them below trained models.
-
StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
StressDream optimizes initial noise in diffusion video world models using VLM semantic and plausibility objectives to steer generations toward specified high-impact outcomes for improved policy evaluation.
-
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
KLIP detects and localizes distribution shifts in inverse problems via KL-divergence between diffusion prior and posterior without calibration data.
-
The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces
SITN performs single-sample OOD detection via goodness-of-fit testing on noise samples in the factorised latent space of continuous normalizing flows.
-
Scaling Pretrained Representations Enables Label-Free Out-of-Distribution Detection Without Fine-Tuning
Scaling pretrained representations improves label-free OOD detection on frozen backbones, causing performance gaps between global and local detectors to vanish across vision and language tasks.
-
Towards accurate extreme event likelihoods from diffusion model climate emulators
Diffusion model climate emulators provide probability density estimates that allow likelihood calculations and odds-ratio-based importance sampling for extreme events such as tropical cyclones.
-
Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
PPE framework with T3+OCSVM one-class detector reaches 0.93+ borderline AUROC, cuts false positives 44-55 points versus Gaussian baselines, and runs at millisecond latency on synthetic multi-domain data.
-
Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flows
Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.