8 papers
Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
Yuan Yao, Qiushi Yang, Humen Zhong +5
Open-world referring segmentation requires grounding unconstrained language expressions to precise pixel-level regions. Existing multimodal large language models (MLLMs) exhibit st…
McSc: Motion-Corrective Preference Alignment for Video Generation with Self-Critic Hierarchical Reasoning
Qiushi Yang, Yingjie Chen, Yuan Yao +3
Text-to-video (T2V) generation has achieved remarkable progress in producing high-quality videos aligned with textual prompts. However, aligning synthesized videos with nuanced hum…
ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
Xiefan Guo, Miaomiao Cui, Liefeng Bo +1
Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering…
MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling
Yifang Men, Yuan Yao, Miaomiao Cui +1
Character video synthesis aims to produce realistic videos of animatable characters within lifelike scenes. As a fundamental problem in the computer vision and graphics community,…
MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection
Qiushi Yang, Yuan Yao, Miaomiao Cui +1
The recent Segment Anything Model 2 (SAM2) has demonstrated exceptional capabilities in interactive object segmentation for both images and videos. However, as a foundational model…
GaussianIP: Identity-Preserving Realistic 3D Human Generation via Human-Centric Diffusion Prior
Zichen Tang, Yuan Yao, Miaomiao Cui +2
Text-guided 3D human generation has advanced with the development of efficient 3D representations and 2D-lifting methods like Score Distillation Sampling (SDS). However, current me…