2021年5月4日 - 2021年5月7日

Microsoft at ICLR 2021

地点： Virtual

微软研究院博客

A graphic depicting audio and video content items passing through an audio transformer layer and a video transformer layer, respectively, before being combined while passing through a multimodal transformer layer
微软研究院博客

| Yale Song

Understanding video is one of the most challenging problems in AI, and an important underlying requirement is learning multimodal representations that capture information about objects, actions, sounds, and their long-range statistical dependencies from audio-visual signals. Recently, transformers have been successful in…

An example of a multi-turn text-to-SQL task. The user query “Find the names of the top 3 highest sales books” corresponds to the formal program “SELECT title FROM book ORDER BY sale_amount DESC LIMIT 3”. The follow-up user query, “Who are their authors,” corresponds to the formal program “SELECT t1.title, t1.name FROM author AS t1 JOIN book AS t2 ON t1.id = t2.author_id ORDER BY t2.sale_amount DESC LIMIT 3”. In the corresponding database, there is an “Author” table with an “id” column, a “name” column, a “country” column, and an ellipsis signifying additional columns; a “Press” table with an “id” column, a “name” column, an “address” column, and an ellipsis signifying additional columns; and a “Book” table with an “id” column, a “title” column, an “author id” column, a “sale_amount” column, and an ellipsis signifying additional columns.
微软研究院博客

| Alex Polozov, Chris Meek, 和 Ahmed Awadallah

One key aspiration of AI is to develop natural and effective task-oriented conversational systems. Task-oriented conversational systems use a natural language interface to collaborate with and support people in accomplishing specific goals and activities. They go beyond chitchat conversation. For…

diagram
微软研究院博客

| Misha Khodak, Neil Tenenholtz, Lester Mackey, 和 Nicolo Fusi

From BiT (928 million parameters) to GPT-3 (175 billion parameters), state-of-the-art machine learning models are rapidly growing in size. With the greater expressivity and easier trainability of these models come skyrocketing training costs, deployment difficulties, and even climate impact. As…