2 papers
cs.RO2026
Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures
Bowen Li, Mayank Mishra, Y. Isabel Liu +7
Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforcement learning (RL) can learn re…
cs.CL2024
Aurora-M: Open Source Continual Pre-training for Multilingual Language and Code
Taishi Nakamura, Mayank Mishra, Simone Tedeschi +42
Pretrained language models are an integral part of AI applications, but their high computational cost for training limits accessibility. Initiatives such as Bloom and StarCoder aim…