mlsanityData to 14 Oct 2026

MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning

arXiv 2608.13478 ↗First posted 13 Aug 2026cs.CVcited by 0

On the map: LLM safety and security → Vision-language and text-to-image safety

Abstract (arXiv)

We present our submission to Task 3 of the Genμ 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training objectives, richer concept representations, and semantic routing for concept-specific mapper selection. Our approach improves robust concept removal while preserving unrelated and semantically adjacent concepts. On the official benchmark, evaluated using the Erasing-Retention-Robustness (ERR) metric on Stable Diffusion v1.4, our method outperforms the state-of-the-art baseline by 12.1% on average across the five concept categories, achieving substantial gains.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security. Builds on 20 of its 23 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

20 of 23 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Models25 Mar
  2. 2025Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them31 Jan
  3. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models30 Mar
  4. 2022Red-Teaming the Stable Diffusion Safety Filter3 Oct

Other references · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  6. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  7. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 648
  8. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  9. 2023Erasing Concepts from Diffusion Modelscited by 539
  10. 2022Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Modelscited by 513
  11. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  12. 2023LEACE: Perfect linear concept erasure in closed formcited by 267
4 more
  1. 2023One-Dimensional Adapter to Rule Them All: Concepts, Diffusion Models and Erasing Applicationscited by 169
  2. 2023Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Eraserscited by 120
  3. 2024Robust Concept Erasure Using Task Vectorscited by 27
  4. 2025CRCE: Coreference-Retention Concept Erasure in Text-to-Image Diffusion Modelscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
  2. 2026Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
  3. 2026Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
  4. 2026A Concept is More Than a Word: Diversified Unlearning in Text-to-Image Diffusion Models
  5. 2026Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
  6. 2026You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning
  7. 2026EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimization
  8. 2026Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models