Популярное

Музыка Кино и Анимация Автомобили Животные Спорт Путешествия Игры Юмор

Интересные видео

2025 Сериалы Трейлеры Новости Как сделать Видеоуроки Diy своими руками

Топ запросов

смотреть а4 schoolboy runaway турецкий сериал смотреть мультфильмы эдисон
dTub
Скачать

RI Seminar: Jacob Andreas : Just Asking Questions

Автор: CMU Robotics Institute

Загружено: 2025-11-25

Просмотров: 250

Описание:

Jacob Andreas
Associate Professor
Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology
November 14, 2025

https://www.ri.cmu.edu/event/just-ask...

Just Asking Questions
Abstract: In the age of deep networks, “learning” almost invariably means “learning from examples”. We train language models with human-generated text and labeled preference pairs, image classifiers with large datasets of images, and robot policies with rollouts or demonstrations. When human learners acquire new concepts and skills, we often do so with richer supervision, especially in the form of language—we learn new concepts from examples accompanied by descriptions or definitions, and new skills from demonstrations accompanied by instructions. Crucially, language-based supervision involves not only instructions but *questions*—students ask questions to elicit the most useful pieces of supervision, and teachers ask questions to probe student knowledge and encourage them to acquire new skills or aspects of understanding on their own. This talk will focus on a few recent projects focused on building computational models that can ask good questions for both learning and teaching, with applications spanning LM alignment, policy learning, and education. This is joint work with Belinda Li, Alex Tamkin, Noah Goodman, Andi Peng, Ilia Sucholutsky, Nishanth Kumar, Julie A Shah, Andreea Bobu, Alexis Ross, Gabe Grand, Valerio Pepe and Josh Tenenbaum.

Bio: Jacob Andreas is an associate professor at MIT in the Department of Electrical Engineering and Computer Science as well as the Computer Science and Artificial Intelligence Laboratory. His research aims to understand the computational foundations of language learning, and to build intelligent systems that can learn from human guidance. Jacob earned his Ph.D. from UC Berkeley, his M.Phil. from Cambridge (where he studied as a Churchill scholar) and his B.S. from Columbia. He has received a Sloan fellowship, an NSF CAREER award, MIT’s Junior Bose and Kolokotrones teaching awards, and paper awards at ACL, ICML and NAACL.

RI Seminar: Jacob Andreas : Just Asking Questions

Поделиться в:

Доступные форматы для скачивания:

Скачать видео mp4

  • Информация по загрузке:

Скачать аудио mp3

Похожие видео

2025 MIT Integration Bee - Finals

2025 MIT Integration Bee - Finals

RI Seminar: Yuke Zhu : Toward Generalist Humanoid Robots

RI Seminar: Yuke Zhu : Toward Generalist Humanoid Robots

RI Seminar: Sangbae Kim : Physical Intelligence and Cognitive Biases Toward AI

RI Seminar: Sangbae Kim : Physical Intelligence and Cognitive Biases Toward AI

RI Seminar: Charlie Kemp : Human-scale mobile manipulators happily used in homes?

RI Seminar: Charlie Kemp : Human-scale mobile manipulators happily used in homes?

Как работала машина

Как работала машина "Энигма"?

МФТИ — как учат ГЕНИЕВ? Полнометражный фильм

МФТИ — как учат ГЕНИЕВ? Полнометражный фильм

"Ревность - постыдный инстинкт. Крах любви втроём". МАЯКОВСКИЙ-БРИКИ. 3 серия

Circular AI Deals Fuel Bubble Debate | Bloomberg Tech: Asia 11/28/25

Circular AI Deals Fuel Bubble Debate | Bloomberg Tech: Asia 11/28/25

Джазовый пианист реагирует на классических пианистов, пытающихся играть джаз (Юйцзя, Горовиц, Сум...

Джазовый пианист реагирует на классических пианистов, пытающихся играть джаз (Юйцзя, Горовиц, Сум...

David Emil Reich, Professor of Genetics, Harvard Medical School

David Emil Reich, Professor of Genetics, Harvard Medical School

Вы ОТСТОЙ в подсказках ИИ (Вот в чем секрет)

Вы ОТСТОЙ в подсказках ИИ (Вот в чем секрет)

RI Seminar: Jiaoyang Li : How to Coordinate Thousands of Robots

RI Seminar: Jiaoyang Li : How to Coordinate Thousands of Robots

Демократия сейчас! — 27 ноября 2025 г.

Демократия сейчас! — 27 ноября 2025 г.

Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind

Stanford CS25: V5 I Large Language Model Reasoning, Denny Zhou of Google Deepmind

RI Seminar: Nikolay Atanasov : Learning Environment Models for Mobile Robot Autonomy

RI Seminar: Nikolay Atanasov : Learning Environment Models for Mobile Robot Autonomy

RI Seminar : Matt Mason : A Manipulation Journey

RI Seminar : Matt Mason : A Manipulation Journey

Новый прокурор ОТКЛОНЯЕТ дело Трампа о вмешательстве в выборы в Джорджии

Новый прокурор ОТКЛОНЯЕТ дело Трампа о вмешательстве в выборы в Джорджии

1. Algorithms and Computation

1. Algorithms and Computation

RI Seminar: Alfred Rizzi : Developing Physically Capable and Intelligent Robots

RI Seminar: Alfred Rizzi : Developing Physically Capable and Intelligent Robots

Французская защита за 60 минут

Французская защита за 60 минут

© 2025 dtub. Все права защищены.



  • Контакты
  • О нас
  • Политика конфиденциальности



Контакты для правообладателей: [email protected]