MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiBench benchmark.
arXiv preprint arXiv:2510.13809 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
ProPhy adds explicit physics-aware conditioning via semantic and refinement experts plus VLM knowledge transfer to produce more physically coherent dynamic videos than prior methods.
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
citing papers explorer
-
MotiMotion: Motion-Controlled Video Generation with Visual Reasoning
MotiMotion adds visual reasoning via a training-free VLM to refine primary trajectories and hallucinate secondary motions, plus a confidence-aware guidance scheme, yielding more plausible interactions on the new MotiBench benchmark.
-
ProPhy: Progressive Physical Alignment for Dynamic World Simulation
ProPhy adds explicit physics-aware conditioning via semantic and refinement experts plus VLM knowledge transfer to produce more physically coherent dynamic videos than prior methods.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.