6 papers
MosaicMem: Hybrid Spatial Memory for Controllable Video World Models
Wei Yu, Runjia Qian, Yumeng Li +8
Video diffusion models are moving beyond short, plausible clips toward world simulators that must remain consistent under camera motion, revisits, and intervention. Yet spatial mem…
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
Zongjian Li, Zheyuan Liu, Qihui Zhang +10
Instruction-based image editing has achieved remarkable progress; however, models solely trained via supervised fine-tuning often overfit to annotated patterns, hindering their abi…
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Bin Lin, Zongjian Li, Xinhua Cheng +9
Although existing unified models achieve strong performance in vision-language understanding and text-to-image generation, they remain limited in addressing image perception and ma…
OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
Shenghai Yuan, Xianyi He, Yufan Deng +5
Subject-to-Video (S2V) generation aims to create videos that faithfully incorporate reference content, providing enhanced flexibility in the production of videos. To establish the…
ImgEdit: A Unified Image Editing Dataset and Benchmark
Yang Ye, Xianyi He, Zongjian Li +5
Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterpa…
WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
Zongjian Li, Bin Lin, Yang Ye +4
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model train…