#video diffusion

try —

5 papers match

cs.CV2026

Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion

Henglin Liu, Fangyuan Kong, Jing Wang +7

The paper introduces concentrated Implicit Preference Optimization (cIPO), a post‑training method for text‑to‑video diffusion models that derives preference signals from reconstruc…

#video diffusion#preference optimization#temporal consistency#implicit reward
cs.RO2026

AeroAct: Action-Centered World-Action Models for Language-Conditioned Quadrotor Flight

Xinhong Zhang, Qiyuan Zhu, Yubo Huang +8

The paper introduces AeroAct, a world-action model that predicts quadrotor flight actions from egocentric video, proprioceptive data, and language commands, using a video diffusion…

#quadrotor navigation#language-conditioned control#world-action model#visual grounding
cs.CV2026

Cyclone: Diffusion Model for Cycle-Consistent Weather Editing from Unpaired Driving Data

Thang-Anh-Quan Nguyen, Moussab Bennehar, Luis Guillermo Roldao Jimenez +5

Cyclone is a latent diffusion framework that edits weather conditions in driving images without paired data, using cycle-consistent constraints and image‑text knowledge to produce…

#weather editing#diffusion models#autonomous driving#cycle consistency
cs.CV2026

WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction

Li Hu, Guangyuan Wang, Peng Zhang +1

WanToFight is a generative game engine that uses a video diffusion transformer to produce real-time, two-player fighting game visuals from keyboard inputs, handling multi-player co…

#generative models#real-time inference#multi-player gaming#video diffusion
cs.LG2026

The Seriality Gap in Video Diffusion Models

Jorge Diaz Chao, Konpat Preechakul, Yuxi Liu +1

The paper investigates why video diffusion models struggle with tasks that require sequential causal reasoning, such as multi‑ball collisions, and identifies a "seriality gap" wher…

#video diffusion#causal reasoning#serial computation#simulation