Sparse autoencoders inserted into VLMs and trained only for reconstruction can reliably detect adversarial attacks on images, including unseen domains and attack types.
Title resolution pending
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Diffusion posterior samplers produce biased outputs that can be expressed as an Ornstein-Uhlenbeck path expectation via a surrogate Gaussian path and Feynman-Kac representation, with STSL flattening the spatially varying bias term.
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
PG-OT builds prompt-specific Pareto frontiers and applies distribution-aware optimal transport to improve multi-reward alignment while introducing JDR and JCR metrics to measure synergy and hacking.
Introduces dual pose-image representation, cross-modal alignment, and iterative construction to improve prompt alignment and diversity in multi-person text-to-image generation.
PROWL introduces a KL-constrained adversarial curriculum and prioritized adversarial trajectory buffer to actively discover and correct rare failure modes in action-conditioned video world models.
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.