arXiv AI
Diverse Motion Customization via Control-based Dynamic Optimization
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 27
Meta Inverse Prompting for Video Generative Models
arXiv:2610.24965v2 Announce Type: replace Abstract: Recent advances in video generative models have enabled flexible conditional generation and editing pipelines, such as text-to-video, image-to-vide...
arXiv AI
Oct 2
Video Generation Models: A Survey of Post-Training and Alignment
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamic...
arXiv Computer Vision
Sep 30
Reimagine Video Dynamics
arXiv:2609.36496v1 Announce Type: new Abstract: Most video editing methods focus on changing the appearance of the source video, while offering limited control over its dynamics. We introduce Reimagi...
arXiv Computer Vision
Oct 22
HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic Semantics
HorizonComposer is a new instruction‑guided video editing framework that preserves traffic semantics in driving videos. It uses a hybrid dataset of real and synthetic edits, applies advantage conditioning with dense pixel‑level rewards during training, and introduces thinking frames to reduce temporal shock. Experiments show state‑of‑the‑art spatiotemporal consistency, improved content preservation, and gains in downstream road line segmentation and multi‑object detection.
arXiv Computer Vision
Sep 25
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
ViRDM is a new post‑training method for few‑step causal video generation that eliminates the need for a large teacher model and an online critic. By applying representation distribution matching (RDM) with a precomputed target distribution, a lightweight VAE decoder, and staged vector–Jacobian products, ViRDM overcomes memory, optimization, and temporal dynamics challenges. The approach reduces GPU memory usage and training time, achieving state‑of‑the‑art VBench performance with only 20 generator updates and 16 A100 GPU‑hours.
arXiv AI
Jul 7
Motion Attribution for Video Generation
arXiv:2601. 08828v2 Announce Type: replace-cross Abstract: Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood.