Edit the Motion, Keep the Video: MotionV2V

Kari Jaaskelainen

26 Nov 2025 — 1 min read

MotionV2V is a new way to edit videos: instead of repainting pixels, it edits the motion itself.

How it works: the system extracts a few motion trajectories from your video, you (or a prompt/tool) adjust them, and a motion-conditioned diffusion model regenerates the clip so content stays the same while motion changes. The team trained it with "motion counterfactuals"—pairs of videos with identical content but different motion—so edits can start at any timestamp and propagate naturally.

Stabilize or retime moves without reshoots
Re-route camera pans and dollies
Keep identity, lighting, and scene details intact

In a four-way user study, viewers preferred MotionV2V over prior methods more than 65% of the time.

See demos and details: https://ryanndagreat.github.io/MotionV2V — Paper: https://arxiv.org/abs/2511.20640

Paper: https://arxiv.org/abs/2511.20640v1

Register: https://www.AiFeta.com

#AI #VideoEditing #GenerativeAI #ComputerVision #DiffusionModels #VFX #PostProduction #Research

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added