MotionV2V: Edit Motion, Not Pixels

Kari Jaaskelainen

26 Nov 2025 — 1 min read

What if you could change how a video moves—without changing how it looks? MotionV2V lets editors "edit motion, not pixels."

The team defines a motion edit as a small tweak to the sparse paths (trajectories) objects follow—like a hand wave, a camera pan, or a dancer's step. Those edits guide a motion-conditioned diffusion model to regenerate the clip with new motion while preserving content and style.

Precise, timestamped edits that naturally propagate through the video
Consistent identity, lighting, and background
Useful for smoothing shaky shots, re-timing gestures, changing choreography, or refining camera moves

To train this control, they create "motion counterfactuals": paired videos with the same content but different motion, and fine-tune the model on them. In a four-way user study, MotionV2V was preferred over prior methods in 65%+ of comparisons.

Project page: https://ryanndagreat.github.io/MotionV2V • Paper: https://arxiv.org/abs/2511.20640v1

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

Register: https://www.AiFeta.com

#AI #VideoEditing #ComputerVision #GenerativeAI #DiffusionModels #Research

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

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 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

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

Read more

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

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

AI that explains itself—by following the science

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