UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

About this episode

The episode discusses UniVidX, a unified multimodal framework for versatile video generation using diffusion priors.

🤗 Upvotes: 70 | cs.CV Authors: Houyuan Chen, Hong Li, Xianghao Kong, Tianrui Zhu, Shaocong Xu, Weiqing Xiao, Yuwei Guo, Chongjie Ye, Lvmin Zhang, Hao Zhao, Anyi Rao Title: UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors Arxiv: http://arxiv.org/abs/2605.00658v1 Abstract: Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and limits the modeling of correlations across modalities. We present UniVidX, a unified multimodal framework that leverages VDM priors for versatile video generation. UniVidX formulates pixel-aligned tasks as conditional generation in a shared multimodal space, adapts to modality-specific distributions while preserving the backbone's native priors, and promotes cross-modal consistency during synthesis. It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• video generation
• multimodal framework
• diffusion models
• conditional generation
• machine learning

Keywords

• UniVidX
• video diffusion models
• multimodal graphics
• conditional generation
• Stochastic Condition Masking
• Decoupled Gated LoRA
• Cross-Modal Self-Attention

Mentioned in this episode

Organizations: Arxiv

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min