Manling Li
2 papers · Latest:
Artificial Intelligence
Using large language models for embodied planning introduces systematic safety risks
LLMs used for robotic planning show significant safety risks, with even high-performing models generating dangerous plans, highlighting a critical challenge.
2604.18463
Computer VisionEgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
EgoTL introduces a think-aloud data pipeline to improve VLM performance on long-horizon egocentric tasks by providing accurate human CoT and spatial annotations.
2604.09535
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.