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.
arXiv:2609.08032v1 Announce Type: cross Abstract: We introduce FlexMoGen, a novel framework for flexible human motion synthesis conditioned on both natural language descriptions and motion style refe...
arXiv:2609.23817v1 Announce Type: new Abstract: We present VISTA, a two-stage framework for generating stylized 3D human motion by fusing structural content from text prompts with expressive style fr...
arXiv:2609.25775v1 Announce Type: new Abstract: Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video d...
arXiv:2606. 19676v1 Announce Type: cross Abstract: Diffusion models have achieved remarkable success in image and video generation and editing.
arXiv:2510.24904v2 Announce Type: replace Abstract: Although recent video generative models are getting more capable of following external camera controls, imposed by either text descriptions or came...
arXiv:2605. 23045v2 Announce Type: replace-cross Abstract: Video representation learning has seen tremendous progress in recent years.
arXiv:2608.20770v1 Announce Type: new Abstract: Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does...
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
arXiv:2609.22267v1 Announce Type: new Abstract: Camera motion often reflects directorial intent and requires professional equipment, making it a high value form of intellectual property. However, gen...
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:2607. 22830v2 Announce Type: replace Abstract: In visual storytelling, human performances are central to creative intent and narrative meaning.
The paper compares diffusion and rectified flow objectives within the MotionGPT3 framework for text-driven motion generation. Experiments on HumanML3D show that rectified flow converges faster, achieves strong test performance earlier, and matches or exceeds diffusion quality while requiring fewer sampling steps. The study isolates the generative objective’s impact, demonstrating that rectified flow’s benefits transfer to continuous-latent motion generation.