MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning
We present our submission to Task 3 of the Gen$μ$ 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 s
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%microsoft/semantic-kernel →
“Fuzzy title match (0.73): “MapRoute++: Surrogate-Guided Semantic Routing for Visual Con” ≈ “microsoft/semantic-kernel””
- LinkedLinked via arxiv author · 85%Ashok Urlana →
“MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning”
- LinkedLinked via arxiv author · 85%L. D. M. S. Sai Teja →
“MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning”
- LinkedLinked via arxiv author · 85%Vivek Hruday Kavuri →
“MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning”
- LinkedLinked via arxiv author · 85%Ponnurangam Kumaraguru →
“MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning”