178 articles tagged "cs-CV" — page 5 of 6
Canvas-to-Image: Compositional Image Generation with Multimodal Controls(arxiv.org)
|paper|arXiv
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously s...
TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos(arxiv.org)
|paper|arXiv
Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robots - are abundant, d...
Continual Error Correction on Low-Resource Devices [TOP LAB](arxiv.org)
|paper|arXiv
The proliferation of AI models in everyday devices has highlighted a critical challenge: prediction errors that degrade user experience. While existing solutions focus on error detection, they rarely ...