Mirage auditing reveals that VFL unlearning methods passing output-level checks still retain substantial class structure in representations across multiple datasets and baselines.
In: International conference on machine learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal video generation.
HILBERT uses joint-centric dual contrastive learning with CKA and mutual information regularizers to align long-sequence audio-text embeddings while preserving structure and balancing modalities.
citing papers explorer
-
Can Vision Models Truly Forget? Mirage: Representation-Level Certification of Visual Unlearning
Mirage auditing reveals that VFL unlearning methods passing output-level checks still retain substantial class structure in representations across multiple datasets and baselines.
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features inside a diffusion model and aligns each to its matching expert foundation model via an alignment loss plus a decoupling regularizer, yielding better visual quality and long-term consistency in multi-modal video generation.
-
Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization
HILBERT uses joint-centric dual contrastive learning with CKA and mutual information regularizers to align long-sequence audio-text embeddings while preserving structure and balancing modalities.