---
format: "aidr-story-markdown/v1"
id: "2927812d5bfc90b15c539625766d2cd6eb617726290c51367a04cf20169538e5"
canonical_url: "https://aidr.today/2927812d?lang=en"
title: "Few-Step Streaming Video Generation via Condition Shifting"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-11T00:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://huggingface.co/papers/2611.14033"]
summary: "APEX extends condition shifting to streaming video generation, removing the need for an independent fake-score network while achieving higher video instruction fulfillment and visual aesthetics compared to S2-Avatar on 180-second videos."
---

# Few\-Step Streaming Video Generation via Condition Shifting

> [Open the canonical story](<https://aidr.today/2927812d?lang=en>)

**Published:** 2026-11-11T00:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

APEX extends condition shifting to streaming video generation, removing the need for an independent fake\-score network while achieving higher video instruction fulfillment and visual aesthetics compared to S2\-Avatar on 180\-second videos\.

## Sources

- [Story source](<https://huggingface.co/papers/2611.14033>)