Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to support content governance and compliance. As erasure requests arrive over time, models must remove new targets without undoing prior erasures. Existing methods do not cons...
Yong-Liang Wu, Haori Lu, Jin-Qi Luo et al.· 0 citations
Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-image diffusion model while preserving its ability to generate other content. Existing activation steering methods build an erasure direction mainly from the target concep...
Yong-Liang Wu, Haori Lu, Yu-Lun Wu et al.· 0 citations
Text-to-motion generation and motion-to-text captioning are two fundamental tasks in human motion modeling, both grounded in the same underlying motion-text correspondence. Existing unified approaches mostly rely on autoregressive modeling, which imposes a fixed generation order and is therefore poorly suited to the bi...
Wan-Jiang Weng, Yong-Liang Wu, Xiaofeng Tan et al.· 0 citations
Perception-Enhanced Alignment DPO (PEA-DPO), a framework for multimodal LLMs alignment, which explicitly leverages visual preference signals to overcome visual insensitivity is proposed, which demonstrates that PEA-DPO enhances sensitivity to visual context while preserving the language modeling capacity of the base mo...
Jiawei Feng, Jiancan Wu, Xingyu Zhu et al.· 1 citation
This work proposes RITA, a Robust test-tIme prompt-TAdaptation framework that shifts from sample-level estimates to distribution-level alignment, and employs optimal transport to align the distribution of augmented visual features with textual prototypes, mitigating adversarial outliers and rectifying cross-modal seman...
Xingyu Zhu, Huanshen Wu, Shuo Wang 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.
