3 papers
cs.LG2026
Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation
Lin Guan, Jia-Qi Yang, Zhishan Zhao +12
Short-video recommenders such as Douyin must exploit extremely long user behavior histories without breaking latency or cost budgets. We present an end-to-end industrial recommende…
cs.CV2026
Disciplined Diffusion: Text-to-Image Diffusion Model against NSFW Generation
Chi Zhang, Changjia Zhu, Xiaowen Li +2
Text-to-image (T2I) diffusion models have the ability to build high-quality pictures from text prompts, but they pose safety concerns because they can generate offensive or disturb…
cs.CV2025
DiffuEraser: A Diffusion Model for Video Inpainting
Xiaowen Li, Haolan Xue, Peiran Ren +1
Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using inform…