2 papers
cs.AI2026
DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models
Shihong Li, Juntao Xu, JinCao +3
Few-step distillation reduces the inference cost of image-to-video generation, but directly reusing LoRA adapters trained for long denoising trajectories can weaken their intended…
cs.CV2026
ReconPlusGen: Injecting Reconstruction Prior into Multi-view 3D Generation through Noise Inversion and Modulation
Jiarui Liu, Heng Li, Weiyu Li +7
Qualitative results and an illustration of our core idea. Top left: reconstruction results on benchmark images. Top right: reconstruction results on real-world images. Bottom: illu…