Reinforcement-learning (RL) post-training equips multimodal large reasoning models (MLRMs) with exploratory chains of thought (CoT), substantially improving visual reasoning. However, we find that this capability introduces a distinct privacy vulnerability: even when a sensitive fact is successfully unlearned from the...
Xin-Hao Zhong, Yu Qiao, Jun-Hao Li et al.· 0 citations
Video creation spans text-to-video (T2V), image-to-video (I2V), and condition-based generation, yet video diffusion models remain costly because they repeatedly evaluate large backbones during sampling. Distribution matching distillation (DMD) reduces this cost, but its reverse Kullback--Leibler (KL) objective can prov...
Yu-Tong Wang, Xing-Tong Ge, En-Huai Liu et al.· 0 citations
This approach first reframes concept erasure as prompt-conditioned parameter amortization and trains a hypernetwork to map textual descriptions to prompt-specific LoRA updates, eliminating the need for per-prompt gradient optimization or manual LoRA merging.
Yi Sun, Xin-Hao Zhong, Zhi-Qi Zhang et al.· 0 citations
DeforM is proposed, a reasoning-guided image-to-video generation framework that directs the model's focus toward physics-critical regions, and introduces a VLM-guided physical reasoning module, DeforM-Reason, to identify target objects and generate spatial-temporal masks.
Yunyi Li, Yu Qiao, Yaohui Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
