Showing 2026Show all
2 papers · 1 filter
cs.RO2026
StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
Shangyuan Yuan, Xinda Qi, Yujiang Pu +2
Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process t…
cs.CV2026
NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation
Yujiang Pu, Yu Kong
Diffusion models have recently advanced text-to-video (T2V) generation, yet they still struggle with fine-grained compositional alignment, such as attribute binding, spatial relati…