# Event-Driven Video Generation

Source: [Event-Driven Video Generation](<https://www.sota2.com/research/paper/69b8e00a0636e5bf4afbea06>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-02T05:00:05.659Z

Authors: Chika Maduabuchi, Jindong Wang

Published: 2026-03-12T00:16:56.000Z

## Abstract

Current text-to-video models can make individual frames look convincing while still getting simple interactions wrong: objects move before contact, an intended action is skipped, a placed object keeps drifting, or a support relation breaks. Our starting point is that standard frame-first denoising updates every latent region at every step, even when the prompt implies that only a local interaction should be active. We introduce Event-Driven Video Generation (EVD), a small DiT-compatible intervention that gives the sampler an explicit event signal. A lightweight head predicts token-level event activity; training losses tie that activity to latent state change; and event-gated sampling, with hysteresis and an early-step schedule, applies the update field mainly where an interaction is forming. On EVD-Bench, EVD improves human preference and VBench dynamics for state persistence, spatial accuracy, support relations, and contact stability, while keeping appearance quality comparable to the base model. The results suggest that a modest amount of event structure can correct several interaction failures that otherwise remain hidden behind good frame-level appearance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Generation on EVD-Bench](<https://www.sota2.com/research/sota/video-generation-on-evd-bench.md>): Video Generation; EVD-Bench; Human Eval: Text Fidelity: 89.7.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.13402>)

[PDF](<https://arxiv.org/pdf/2603.13402.pdf>)
