Episode

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Podcast
Daily Paper Cast
Published
May 21, 2026
Duration seconds
1402
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/b64f1aec
Audio
https://media.transistor.fm/b64f1aec/3c0b4e98.mp3
JSON
/v1/public/podcasts/daily-paper-cast-7079649/episodes/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition
Markdown
/podcast/daily-paper-cast-7079649/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/daily-paper-cast-7079649/cogomnicontrol-reasoning-driven-controllable-video-generation-via-creative-intent-cognition.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

🤗 Upvotes: 31 | cs.CV Authors: Hongji Yang, Songlian Li, Yucheng Zhou, Xiaotong Zhao, Alan Zhao, Chengzhong Xu, Jianbing Shen Title: CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition Arxiv: http://arxiv.org/abs/2605.19995v1 Abstract: Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in professional production workflows such as storyboard sketches and clay render conditions. Existing video generation models, either inject conditions through adapters or couple a generic vision-language model (VLM) within a diffusion backbone, leaving a capability gap and failing to produce the videos that align with the user's creative intent. We present CogOmniControl, a reasoning-driven framework that factorizes controllable video generation into creative intent cognition and generation. Specifically, we train a specialized CogVLM using authentic anime production data. Compared to generic VLMs, it generates more professional and clear outputs, accurately cognizing user creative intent from sparse and abstract conditions and tuning these cues into dense reasoning output. Besides, CogOmniDiT unifies the controls from various conditions through in-context generation and is aligned to the CogVLM reasoning outputs via reinforcement learning. Furthermore, leveraging CogVLM's robust capability in guiding video generation, we release its potential in planning specific evaluators and enable a Best-of-N selection for the generated videos. This integration transforms the entire framework into a closed-loop "harness-like" architecture. We further introduce CogReasonBench and CogControlBench, built from professional workflows data…