210 citations · 1k across the 55 of their papers we have counts for
7 papers · 1 filter
Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection
Daichi Zhang, Tong Zhang, Jianmin Bao +2
With the rapid development of generative models, detecting generated fake images to prevent their malicious use has become a critical issue recently. Existing methods frame this ch…
HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animation
Wangzheng Shi, Yinglin Zheng, Yuxin Lin +3
Hair transfer is increasingly valuable across domains such as social media, gaming, advertising, and entertainment. While significant progress has been made in single-image hair tr…
Fast Autoregressive Models for Continuous Latent Generation
Tiankai Hang, Jianmin Bao, Fangyun Wei +1
Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents si…
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Microsoft, :, Abdelrahman Abouelenin +73
We introduce Phi-4-Mini and Phi-4-Multimodal, compact yet highly capable language and multimodal models. Phi-4-Mini is a 3.8-billion-parameter language model trained on high-qualit…
DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
Zhendong Wang, Jianmin Bao, Shuyang Gu +3
In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions. A primary challenge lies in…
Diffusion Models without Classifier-free Guidance
Zhicong Tang, Jianmin Bao, Dong Chen +1
This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovati…
SmartEraser: Remove Anything from Images using Masked-Region Guidance
Longtao Jiang, Zhendong Wang, Jianmin Bao +5
Object removal has so far been dominated by the mask-and-inpaint paradigm, where the masked region is excluded from the input, leaving models relying on unmasked areas to inpaint t…