65 citations · 69 across the 12 of their papers we have counts for
12 papers
EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation
Yuhan Liu, Zongwei Hong, Jinglun Li +3
Diffusion-based visual generative models deliver strong image and video synthesis quality but incur high inference costs because sequential samplers repeatedly evaluate large netwo…
SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching
Zong-Wei Hong, Jinglun Li, Shen Zhang +3
Denoising diffusion transformers achieve strong generation quality but converge slowly during training. Regularizing their internal representations has emerged as an effective acce…
The Velocity Deficit: Initial Energy Injection for Flow Matching
Linze Li, Zong-Wei Hong, Shen Zhang +4
While Flow Matching theoretically guarantees constant-velocity trajectories, we identify a critical breakdown in high-dimensional practice: the Velocity Deficit. We show that the M…
VeCoR -- Velocity Contrastive Regularization for Flow Matching
Zong-Wei Hong, Jing-lun Li, Lin-Ze Li +2
Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target directio…
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
Shen Zhang, Siyuan Liang, Yaning Tan +9
Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings(PE),…
Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers
Zhaodong Bing, Linze Li, Jiajun Liang
Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either…
MegActor-: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer
Shurong Yang, Huadong Li, Juhao Wu +6
Diffusion models have demonstrated superior performance in the field of portrait animation. However, current approaches relied on either visual or audio modality to control charact…
Efficient Single Image Super-Resolution with Entropy Attention and Receptive Field Augmentation
Xiaole Zhao, Linze Li, Chengxing Xie +5
Transformer-based deep models for single image super-resolution (SISR) have greatly improved the performance of lightweight SISR tasks in recent years. However, they often suffer f…
Large Kernel Distillation Network for Efficient Single Image Super-Resolution
Chengxing Xie, Xiaoming Zhang, Linze Li +4
Efficient and lightweight single-image super-resolution (SISR) has achieved remarkable performance in recent years. One effective approach is the use of large kernel designs, which…
MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
Shurong Yang, Huadong Li, Juhao Wu +5
Despite raw driving videos contain richer information on facial expressions than intermediate representations such as landmarks in the field of portrait animation, they are seldom…
FAAC: Facial Animation Generation with Anchor Frame and Conditional Control for Superior Fidelity and Editability
Linze Li, Sunqi Fan, Hengjun Pu +6
Over recent years, diffusion models have facilitated significant advancements in video generation. Yet, the creation of face-related videos still confronts issues such as low facia…
Efficient One Pass Self-distillation with Zipf's Label Smoothing
Jiajun Liang, Linze Li, Zhaodong Bing +4
Self-distillation exploits non-uniform soft supervision from itself during training and improves performance without any runtime cost. However, the overhead during training is ofte…