5 papers · 1 filter
RepFlow: Reciprocal Supervision Improves Generation and Representation in Flow Models
Weili Zeng, Feng Tian, Shengqi Liu +1
Generative models learn visual structure through denoising, yet their internal states are entangled with both noise level and network depth, making it difficult to obtain a stable…
Spatiotemporally Decoupled Autoregressive Diffusion Model for Human Motion Generation
Chengqun Yang, Liang Xu, Yanping Li +4
Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For representation, Vector Quantizat…
Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems
Feng Tian, Yixuan Li, Weili Zeng +3
Diffusion posterior sampling solves inverse problems by combining a pretrained diffusion prior with measurement-consistency guidance. However, full-band guidance can be unreliable…
Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
Weili Zeng, Ziyuan Huang, Kaixiang Ji +1
Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution,…
Infusion: Preventing Customized Text-to-Image Diffusion from Overfitting
Weili Zeng, Yichao Yan, Qi Zhu +4
Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge…