CrashTwin recovers metric-scale crash dynamics from monocular rollouts and shows that strong visual scores routinely mask large momentum, energy, and identity violations in world models.
Towards a better metric for text-to-video generation.arXiv preprint arXiv:2401.07781
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
ARGUS converts MLLM-selected identity evidence into a synchronized 3x3 mosaic injected as negative-time memory in a diffusion model, plus supporting training techniques, to achieve SOTA subject preservation on human video benchmarks.
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.
citing papers explorer
-
A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models
CrashTwin recovers metric-scale crash dynamics from monocular rollouts and shows that strong visual scores routinely mask large momentum, energy, and identity violations in world models.
-
ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
ARGUS converts MLLM-selected identity evidence into a synchronized 3x3 mosaic injected as negative-time memory in a diffusion model, plus supporting training techniques, to achieve SOTA subject preservation on human video benchmarks.
-
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models
NUMINA improves counting accuracy in text-to-video diffusion models by up to 7.4% via a training-free identify-then-guide framework on the new CountBench dataset.