Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation9просмотров8 месяцев назад
EmbodiedOneVision: Interleaved Vision-Text-Action Pretraining for General Robot Control7просмотров8 месяцев назад
BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design8просмотров8 месяцев назад
GOEDEL-PROVER-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction2просмотра8 месяцев назад
