4 citations · 4 across the 2 of their papers we have counts for
3 papers
cs.CY2026
We Should Separate Memorization from Copyright
Adi Haviv, Niva Elkin-Koren, Uri Hacohen +2
The widespread use of foundation models has introduced a new risk factor of copyright issue. This issue is leading to an active, lively and on-going debate amongst the data-science…
cs.AI2025
CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale
Shahar Sarfaty, Adi Haviv, Uri Hacohen +3
The rapid proliferation of generative components, such as LoRAs, has created a vast but unstructured ecosystem. Existing discovery methods depend on unreliable user descriptions or…
cs.CV2024★ 4 cited
Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion
Adi Haviv, Shahar Sarfaty, Uri Hacohen +3
This work addresses the challenge of quantifying originality in text-to-image (T2I) generative diffusion models, with a focus on copyright originality. We begin by evaluating T2I m…