Latest News

Gift from Sebastian Man ’79, SM ’80 supports MIT Stephen A. Schwarzman College of Computing building | MIT News

The MIT Stephen A. Schwarzman College of Computing has received substantial support for its striking new headquarters on Vassar Street in Cambridge, Massachusetts. A major gift from Sebastian Man ’79, SM ’80 will be recognized with the naming of a…

Read MoreGift from Sebastian Man ’79, SM ’80 supports MIT Stephen A. Schwarzman College of Computing building | MIT News

Optimizing Reasoning Performance: A Comprehensive Analysis of Inference-Time Scaling Methods in Language Models

Language models have shown great capabilities across various tasks. However, complex reasoning remains challenging as it often requires additional computational resources and specialized techniques. This challenge has motivated the development of inference-time compute (ITC) scaling methods, which allocate additional computational…

Read MoreOptimizing Reasoning Performance: A Comprehensive Analysis of Inference-Time Scaling Methods in Language Models

ByteDance Introduces QuaDMix: A Unified AI Framework for Data Quality and Diversity in LLM Pretraining

The pretraining efficiency and generalization of large language models (LLMs) are significantly influenced by the quality and diversity of the underlying training corpus. Traditional data curation pipelines often treat quality and diversity as separate objectives, applying quality filtering followed by…

Read MoreByteDance Introduces QuaDMix: A Unified AI Framework for Data Quality and Diversity in LLM Pretraining

Like human brains, large language models reason about diverse data in a general way | MIT News

While early language models could only process text, contemporary large language models now perform highly diverse tasks on different types of data. For instance, LLMs can understand many languages, generate computer code, solve math problems, or answer questions about images and…

Read MoreLike human brains, large language models reason about diverse data in a general way | MIT News