150 articles tagged "cs-LG" — page 4 of 5
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 ...
Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining [TOP LAB](arxiv.org)
|paper|arXiv
Incorporating metadata in Large Language Models (LLMs) pretraining has recently emerged as a promising approach to accelerate training. However prior work highlighted only one useful signal-URLs, leav...