pith. sign in

Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Closed-Form Concept Erasure via Double Projections

cs.LG · 2026-04-11 · unverdicted · novelty 6.0

A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.

citing papers explorer

Showing 2 of 2 citing papers.

  • Closed-Form Concept Erasure via Double Projections cs.LG · 2026-04-11 · unverdicted · none · ref 53

    A training-free double-projection linear transformation erases target concepts from generative models by computing a proxy projection then applying a constrained update in the left null space of known directions.

  • Intrinsic Concept Extraction Based on Compositional Interpretability cs.CV · 2026-03-12 · unverdicted · none · ref 37

    HyperExpress extracts composable intrinsic concepts from single images via hyperbolic concept learning and concept-wise optimization in diffusion-based models.