The authors formalize concepts as regions in the cross-attention activation space of diffusion models and define an entanglement coefficient (\hat{\kappa}) to quantify overlap between target and neighbor concepts.
Concept entanglement forces a fundamental trade-off in diffusion model unlearning
The authors prove a geometric lower bound showing that robust erasure of a target concept inevitably damages semantically related concepts, and validate it across thirteen methods on Stable Diffusion and SDXL.
Academic
Yian Wang · Ali Ebrahimpour-Boroojeny · Hari Sundaram · Varun Chandrasekaran
University of Illinois Urbana-Champaign
Research Digest··2 min read
The paper shows that the failure of concept unlearning methods—either leaking the target under indirect prompts or degrading related concepts—is not a bug of individual algorithms but a structural consequence of overlapping concept representations in activation space.
Why this paper
From University of Illinois Urbana-Champaign
In one line
Concept unlearning in diffusion models is fundamentally limited by the geometric overlap of target and neighbor concepts in activation space.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§