EPISODE · Nov 26, 2025 · 22 MIN
In-Video Instructions: Visual Signals as Generative Control
from Daily Paper Cast · host Jingwen Liang, Gengyu Wang
🤗 Upvotes: 26 | cs.CV, cs.AI Authors: Gongfan Fang, Xinyin Ma, Xinchao Wang Title: In-Video Instructions: Visual Signals as Generative Control Arxiv: http://arxiv.org/abs/2511.19401v1 Abstract: Large-scale video generative models have recently demonstrated strong visual capabilities, enabling the prediction of future frames that adhere to the logical and physical cues in the current observation. In this work, we investigate whether such capabilities can be harnessed for controllable image-to-video generation by interpreting visual signals embedded within the frames as instructions, a paradigm we term In-Video Instruction. In contrast to prompt-based control, which provides textual descriptions that are inherently global and coarse, In-Video Instruction encodes user guidance directly into the visual domain through elements such as overlaid text, arrows, or trajectories. This enables explicit, spatial-aware, and unambiguous correspondences between visual subjects and their intended actions by assigning distinct instructions to different objects. Extensive experiments on three state-of-the-art generators, including Veo 3.1, Kling 2.5, and Wan 2.2, show that video models can reliably interpret and execute such visually embedded instructions, particularly in complex multi-object scenarios.
What this episode covers
🤗 Upvotes: 26 | cs.CV, cs.AI Authors: Gongfan Fang, Xinyin Ma, Xinchao Wang Title: In-Video Instructions: Visual Signals as Generative Control Arxiv: http://arxiv.org/abs/2511.19401v1 Abstract: Large-scale video generative models have recently demonstrated strong visual capabilities, enabling the prediction of future frames that adhere to the logical and physical cues in the current observation. In this work, we investigate whether such capabilities can be harnessed for controllable image-to-video generation by interpreting visual signals embedded within the frames as instructions, a paradigm we term In-Video Instruction. In contrast to prompt-based control, which provides textual descriptions that are inherently global and coarse, In-Video Instruction encodes user guidance directly into the visual domain through elements such as overlaid text, arrows, or trajectories. This enables explicit, spatial-aware, and unambiguous correspondences between visual subjects and their intended actions by assigning distinct instructions to different objects. Extensive experiments on three state-of-the-art generators, including Veo 3.1, Kling 2.5, and Wan 2.2, show that video models can reliably interpret and execute such visually embedded instructions, particularly in complex multi-object scenarios.
NOW PLAYING
In-Video Instructions: Visual Signals as Generative Control
No transcript for this episode yet
Similar Episodes
No similar episodes found.