Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers

• URL: http://arxiv.org/abs/2603.25074v1
• Date: Thu, 26 Mar 2026 06:24:28 GMT
• Title: Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
• Abstract summary: Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models.<n>Z-Erase is the first concept erasure method tailored for single-stream T2I models.
• Score: 28.8135497087758
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures (e.g., Flux), this task remains under-explored in the recent emerging paradigm of single-stream diffusion transformers (e.g., Z-Image). In this new paradigm, text and image tokens are processed as a single unified sequence via shared parameters. Consequently, directly applying prior erasure methods typically leads to generation collapse. To bridge this gap, we introduce Z-Erase, the first concept erasure method tailored for single-stream T2I models. To guarantee stable image generation, Z-Erase first proposes a Stream Disentangled Concept Erasure Framework that decouples updates and enables existing methods on single-stream models. Subsequently, within this framework, we introduce Lagrangian-Guided Adaptive Erasure Modulation, a constrained algorithm that further balances the sensitive erasure-preservation trade-off. Moreover, we provide a rigorous convergence analysis proving that Z-Erase can converge to a Pareto stationary point. Experiments demonstrate that Z-Erase successfully overcomes the generation collapse issue, achieving state-of-the-art performance across a wide range of tasks.

Related papers

• EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse Autoencoders [103.46709005379591]
  Concept erasure offers a principled remedy by removing unwanted semantics from pretrained models.<n>Existing approaches typically operate at a coarse quality, misaligned with the finegrained, distributed nature of concept representations.<n>We propose EraseSAE, a novel framework that leverages sparse autoencoders to achieve surgical concept erasure.
  arXiv  Detail & Related papers  (2026-09-03T10:23:37Z)
• SACE: Concept Erasure at the Semantic Singularity in Visual Autoregressive Models [10.865745057624833]
  We introduce the first scale-aware concept erasure framework (SACE) for visual autoregressive ( VAR) models.<n>By strictly confining interventions to the first scale, our approach couples an Entropy-Regularized Erasure Objective to prevent high-entropy sampling degeneration.
  arXiv  Detail & Related papers  (2026-06-14T13:39:00Z)
• FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models [47.80885954469943]
  Flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks.<n>We propose emphFlowErase-RL, the first GRPO-based framework for concept erasure in flow matching models.<n>We show that our method achieves state-of-the-art erasure performance while maintaining strong image quality and semantic alignment.
  arXiv  Detail & Related papers  (2026-05-19T12:10:09Z)
• Closed-Form Concept Erasure via Double Projections [8.357438653110973]
  Concept erasure is a process of removing unwanted concepts from generative models.<n>We present a linear transformation framework that achieves concept erasure analytically, without any training.<n>Our design yields a deterministic and geometrically interpretable procedure for safe, efficient, and theory-grounded concept removal.
  arXiv  Detail & Related papers  (2026-04-11T05:06:15Z)
• UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation [51.41441081823758]
  Unified models capable of interleaved generation have emerged as a promising paradigm.<n>We propose a unified reinforcement learning framework tailored for interleaved generation.<n>Our experiments demonstrate that this unified training recipe significantly enhances image generation quality through reasoning.
  arXiv  Detail & Related papers  (2026-03-24T17:59:17Z)
• EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization [18.80236205171204]
  EraseAnything++ is a unified framework for concept erasure in both image and video diffusion models.<n>Our method anchors erasure on key visual representations and propagates it consistently across spatial and temporal dimensions.<n>In the video setting, we further enhance consistency through an anchor-and-propagate mechanism that initializes erasure on reference frames and enforces it throughout subsequent transformer layers.
  arXiv  Detail & Related papers  (2026-03-01T08:13:05Z)
• Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models [49.10620605347065]
  We propose Differential Vector Erasure (DVE), a training-free concept erasure method specifically designed for flow matching models.<n>Our key insight is that semantic concepts are implicitly encoded in the directional structure of the velocity field governing the generative flow.<n>During inference, DVE selectively removes concept-specific components by projecting the velocity field onto the differential direction, enabling precise concept suppression without affecting irrelevant semantics.
  arXiv  Detail & Related papers  (2026-02-01T08:05:45Z)
• Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration [39.5698877093219]
  We propose an Uncertainty-Aware Diffusion Bridge Model (UDBM) for image restoration.<n>UDBM reformulates AiOIR as a transport problem steered by pixel-wise uncertainty.<n>It achieves state-of-the-art performance across diverse restoration tasks within a single inference step.
  arXiv  Detail & Related papers  (2026-01-29T12:02:42Z)
• Score Distillation of Flow Matching Models [67.86066177182046]
  We extend Score identity Distillation (SiD) to pretrained text-to-image flow-matching models.<n>SiD works out of the box across these models, in both data-free and data-aided settings.<n>This provides the first systematic evidence that score distillation applies broadly to text-to-image flow matching models.
  arXiv  Detail & Related papers  (2025-09-29T17:45:48Z)
• TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models [0.0]
  Concept erasure aims to remove or suppress specific concept information in a generative model.<n>Trajectory-Constrained Attentional Concept Erasure (TRACE) is a novel method to erase targeted concepts from diffusion models.<n>TRACE achieves state-of-the-art performance, outperforming recent methods such as ANT, EraseAnything, and MACE in terms of removal efficacy and output quality.
  arXiv  Detail & Related papers  (2025-05-29T10:15:22Z)
• Few-Step Diffusion via Score identity Distillation [67.07985339442703]
  Diffusion distillation has emerged as a promising strategy for accelerating text-to-image (T2I) diffusion models.<n>Existing methods rely on real or teacher-synthesized images to perform well when distilling high-resolution T2I diffusion models.<n>We propose two new guidance strategies: Zero-CFG, which disables CFG in the teacher and removes text conditioning in the fake score network, and Anti-CFG, which applies negative CFG in the fake score network.
  arXiv  Detail & Related papers  (2025-05-19T03:45:16Z)
• EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers [33.195628798316754]
  EraseAnything is the first method specifically developed to address concept erasure within the latest flow-based T2I framework.<n>We formulate concept erasure as a bi-level optimization problem, employing LoRA-based parameter tuning and an attention map regularizer.<n>We propose a self-contrastive learning strategy to ensure that removing unwanted concepts does not inadvertently harm performance on unrelated ones.
  arXiv  Detail & Related papers  (2024-12-29T09:42:53Z)
• Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models [76.39651111467832]
  We introduce Reliable and Efficient Concept Erasure (RECE), a novel approach that modifies the model in 3 seconds without necessitating additional fine-tuning. To mitigate inappropriate content potentially represented by derived embeddings, RECE aligns them with harmless concepts in cross-attention layers. The derivation and erasure of new representation embeddings are conducted iteratively to achieve a thorough erasure of inappropriate concepts.
  arXiv  Detail & Related papers  (2024-07-17T08:04:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.