5 papers
Sortblock: Similarity-Aware Feature Reuse for Diffusion Model
Hanqi Chen, Xu Zhang, Xiaoliu Guan +4
Diffusion Transformers (DiTs) have demonstrated remarkable generative capabilities, particularly benefiting from Transformer architectures that enhance visual and artistic fidelity…
Forecasting When to Forecast: Accelerating Diffusion Models with Confidence-Gated Taylor
Xiaoliu Guan, Lielin Jiang, Hanqi Chen +6
Diffusion Transformers (DiTs) have demonstrated remarkable performance in visual generation tasks. However, their low inference speed limits their deployment in low-resource applic…
SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
Jixiang Hong, Yiran Zhang, Guanzhong Wang +3
Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still strugg…
PP-DocBee2: Improved Baselines with Efficient Data for Multimodal Document Understanding
Kui Huang, Xinrong Chen, Wenyu Lv +3
This report introduces PP-DocBee2, an advanced version of the PP-DocBee, designed to enhance multimodal document understanding. Built on a large multimodal model architecture, PP-D…
Enabling Versatile Controls for Video Diffusion Models
Xu Zhang, Hao Zhou, Haoming Qin +5
Despite substantial progress in text-to-video generation, achieving precise and flexible control over fine-grained spatiotemporal attributes remains a significant unresolved challe…