TWIML AI Podcast
Is It Time to Rethink LLM Pre-Training? with Aditi Raghunathan - #747
Sep 16, 2025
· 58m
Today, we're joined by Aditi Raghunathan, assistant professor at Carnegie Mellon University, to discuss the limitations of LLMs and how we can build more adaptable and creative models. We dig into her ICML 2025 Outstanding Paper Award winner, “Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction,” which examines why LLMs struggle with generating truly novel ideas. We dig into the "Roll the dice" approach, which encourages structured exploration by injecting randomness at …
Dan l-episodju għadu ma ġiex traskritt
Uża STT.ai biex tittraskrivi dan l-episodju bl-AI.Ikseb test preċiż b'sejbien tal-kelliem, timestamps, u esportazzjoni f'formati multipli.
Sejbien tal-kelliem
Timbru tal-ħin fil-livell tal-kelma
Esportazzjoni bħala SRT, TXT, JSON