10 papers
Distribution Matching Distillation Meets Reinforcement Learning
Dengyang Jiang, Dongyang Liu, Zanyi Wang +12
Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL)…
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Liuzhuozheng Li, Zhiyuan Zhan, Shuhong Liu +5
Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic method…
RefTon: Reference person shot assist virtual Try-on
Liuzhuozheng Li, Yue Gong, Shanyuan Liu +7
We introduce RefTon, a flux-based person-to-person virtual try-on framework that enhances garment realism through unpaired visual references. Unlike conventional approaches that re…
Unlocking the Potential of Grounding DINO in Videos: Parameter-Efficient Adaptation for Limited-Data Spatial-Temporal Localization
Zanyi Wang, Fan Li, Dengyang Jiang +4
Spatio-temporal video grounding (STVG) aims to localize queried objects within dynamic video segments. Prevailing fully-trained approaches are notoriously data-hungry. However, gat…
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li +6
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as R…
Deforming Videos to Masks: Flow Matching for Referring Video Segmentation
Zanyi Wang, Dengyang Jiang, Liuzhuozheng Li +6
Referring Video Object Segmentation (RVOS) requires segmenting specific objects in a video guided by a natural language description. The core challenge of RVOS is to anchor abstrac…