This paper proposes a controllable method operating on the model's continuous textual representation to erase target characters during generation, and achieves state-of-the-art erasure effectiveness and image fidelity preservation, while supporting controllable erasure degree, multi-target removal, and model transferab...
Qiao Li, Xiaomeng Fu, Wangjia Yu et al.· 0 citations
Experiments on three public sequential-recommendation benchmarks show that SID Routing improves its corresponding direct-generation, and indicate that structure-grounded reasoning is most useful when prefix matching is insufficient but learnable SID-space transitions remain available, whereas long or weakly supported r...
Xiang Liu, Jingsong Su, Shuqing Zhao et al.· arXiv.org· 0 citations
This work proposes to erase concepts by directly manipulating the model's internal representations by operating exclusively on the sparse text-branch tokens and leveraging the straight sampling trajectory of rectified flow, achieving effective concept erasure with negligible overhead and without any training.
Qiao Li, Xiaomeng Fu, Yuanshu Zhao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.