17 citations · 20 across the 14 of their papers we have counts for
11 papers · 1 filter
Diagnose-to-Generate: Eliminating Structural Distortions in Flow Models via Patch-Level Grounded Alignment
Yifan Li, Lishuai Gao, Tong Zhang +8
Flow-based image generators achieve strong semantic synthesis but still produce localized structural distortions, such as malformed hands and limbs. Existing post-training methods…
Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models
Yanbing Zeng, Jia Wang, Hanghang Ma +4
Integrating image generation and understanding into a single framework has become a pivotal goal in the multimodal domain. However, how understanding can effectively assist generat…
MagicMirror: A Large-Scale Dataset and Benchmark for Fine-Grained Artifacts Assessment in Text-to-Image Generation
Jia Wang, Jie Hu, Xiaoqi Ma +3
Text-to-image (T2I) generation has achieved remarkable progress in instruction following and aesthetics. However, a persistent challenge is the prevalence of physical artifacts, su…
Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
Huijie Liu, Bingcan Wang, Jie Hu +2
Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and…
Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models
Huijie Liu, Jingyun Wang, Shuai Ma +3
Motion customization aims to adapt the diffusion model (DM) to generate videos with the motion specified by a set of video clips with the same motion concept. To realize this goal,…
RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction
Xiaoping Wu, Jie Hu, Xiaoming Wei
Diffusion Probabilistic Models (DPMs) have emerged as the de facto approach for high-fidelity image synthesis, operating diffusion processes on continuous VAE latent, which signifi…
High-Resolution Image Synthesis via Next-Token Prediction
Dengsheng Chen, Jie Hu, Tiezhu Yue +2
Recently, autoregressive models have demonstrated remarkable performance in class-conditional image generation. However, the application of next-token prediction to high-resolution…
Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input
Jiajun Liu, Yibing Wang, Hanghang Ma +6
Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a ch…
Fine-gained Zero-shot Video Sampling
Dengsheng Chen, Jie Hu, Xiaoming Wei +1
Incorporating a temporal dimension into pretrained image diffusion models for video generation is a prevalent approach. However, this method is computationally demanding and necess…
Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
Yan Zhu, Junbao Zhuo, Bin Ma +4
Zero-shot video recognition (ZSVR) is a task that aims to recognize video categories that have not been seen during the model training process. Recently, vision-language models (VL…
Large Scale Visual Food Recognition
Weiqing Min, Zhiling Wang, Yuxin Liu +5
Food recognition plays an important role in food choice and intake, which is essential to the health and well-being of humans. It is thus of importance to the computer vision commu…