Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models

• URL: http://arxiv.org/abs/2605.25941v1
• Date: Mon, 25 May 2026 15:20:04 GMT
• Title: Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models
• Abstract summary: Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure.<n>We introduce CLEAR, a separability-driven framework for concept erasure that explicitly enforces concept-layer alignment.<n>Experiments on large-scale text-to-video models demonstrate that enforcing concept--layer alignment leads to more precise concept suppression while preserving overall generative quality.
• Score: 9.957850061310054
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-to-video diffusion transformers encode semantic information unevenly across model depth, which constrains effective concept erasure. We identify a representational bottleneck, termed concept-layer topological alignment, under which target concepts exhibit higher separability at certain representational depths. Outside these depths, concept and non-target signals remain strongly entangled, limiting the effectiveness of depth-specific erasure. This observation reframes concept erasure as the problem of identifying representational depths where concept-non-target separation naturally emerges. Motivated by this structural constraint, we introduce CLEAR, a separability-driven optimization framework for concept erasure that explicitly enforces concept-layer alignment. CLEAR operationalizes this principle by formulating layer selection as an optimization problem over concept-non-target separability, rather than relying on layer-agnostic or heuristic choices. To enable this, we introduce a separability-aware objective that favors layers exhibiting stronger concept-non-target separation. Experiments on large-scale text-to-video diffusion models demonstrate that enforcing concept--layer alignment leads to more precise concept suppression while preserving overall generative quality.

Related papers

• Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models [105.53190946111586]
  We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
  arXiv  Detail & Related papers  (2026-09-09T09:07:40Z)
• 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)
• Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning [17.479156121859827]
  We propose SAEParate, which organizes latent representations into concept-specific clusters via a concept-aware contrastive objective.<n>We also enhance the encoder with a GeLU-based nonlinear transformation to increase its expressive capacity under this separation objective.
  arXiv  Detail & Related papers  (2026-05-12T13:39:07Z)
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• ConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization [11.472088067393074]
  ConceptPrism is a novel framework that automatically disentangles the shared visual concept from image-specific residuals.<n>In experiments, ConceptPrism effectively resolves concept entanglement, achieving a significantly improved trade-off between fidelity and alignment.
  arXiv  Detail & Related papers  (2026-02-23T07:46:19Z)
• 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)
• ACE: Attentional Concept Erasure in Diffusion Models [0.0]
  Attentional Concept Erasure integrates a closed-form attention manipulation with lightweight fine-tuning.<n>We show that ACE achieves state-of-the-art concept removal efficacy and robustness.<n>Compared to prior methods, ACE better balances generality (erasing concept and related terms) and specificity (preserving unrelated content)
  arXiv  Detail & Related papers  (2025-04-16T08:16:28Z)
• Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them [21.386640828092524]
  Concept erasure has emerged as a promising technique for mitigating the risk of harmful content generation in diffusion models.<n>We propose the Adaptive Guided Erasure (AGE) method, which emphdynamically selects optimal target concepts tailored to each undesirable concept.<n>Results show that AGE significantly outperforms state-of-the-art erasure methods on preserving unrelated concepts while maintaining effective erasure performance.
  arXiv  Detail & Related papers  (2025-01-31T08:17:23Z)
• OmniPrism: Learning Disentangled Visual Concept for Image Generation [57.21097864811521]
  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes.<n>We propose OmniPrism, a visual concept disentangling approach for creative image generation.<n>Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts.
  arXiv  Detail & Related papers  (2024-12-16T18:59:52Z)
• Separable Multi-Concept Erasure from Diffusion Models [52.51972530398691]
  We propose a Separable Multi-concept Eraser (SepME) to eliminate unsafe concepts from large-scale diffusion models. The latter separates optimizable model weights, making each weight increment correspond to a specific concept erasure. Extensive experiments indicate the efficacy of our approach in eliminating concepts, preserving model performance, and offering flexibility in the erasure or recovery of various concepts.
  arXiv  Detail & Related papers  (2024-02-03T11:10:57Z)
• Implicit Concept Removal of Diffusion Models [92.55152501707995]
  Text-to-image (T2I) diffusion models often inadvertently generate unwanted concepts such as watermarks and unsafe images. We present the Geom-Erasing, a novel concept removal method based on the geometric-driven control.
  arXiv  Detail & Related papers  (2023-10-09T17:13:10Z)

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.