Please turn JavaScript on
header-image

Machine Learning Blog | ML@CMU | Carnegie Mellon University

Get updates from Machine Learning Blog | ML@CMU | Carnegie Mellon University via email, on your phone or read them on follow.it on your own custom news page.

You can filter the news from Machine Learning Blog | ML@CMU | Carnegie Mellon University that get delivered to you using tags or topics or you can opt for all of them. Unsubscription is also very simple.

See the latest news from Machine Learning Blog | ML@CMU | Carnegie Mellon University below.

Site title: Machine Learning Blog | ML@CMU | Carnegie Mellon University

Is this your feed? Claim it!

Publisher:  Unclaimed!
Message frequency:  0.58 / week

Message History

CMU researchers are presenting 156 papers at the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), held from December 2nd-December 7th at the San Diego Convention. Here is a quick overview of the areas our researchers are working on:

Here are our most frequent collaborator institutions:

class="wp-block-ima...

Read full story

Figure 1. Three regimes of exploration: Current RL model can explore via: (1) sharpening: simply increases likelihood on traces it can sample with high probability; (2) chaining: chain asymmetric skills in the base model (e.g., href="https://arxiv.org/abs/2506.09026" target="_blank" rel="noope...

Read full story

CMU researchers are presenting 50 papers at the Thirtieth Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), held from November 4 – 9 in Suzhou, China. This includes 27 papers in the main conference, 19 papers in the Findings track, 2 system demonstrations papers, and 2 industry track papers. This blog post provides aggregated information about E...

Read full story

This blog post is based on the work BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards.

Tackling Very Hard Problems

The ultimate aim of machine learning research is to push machines beyond human limits in critical applications, including the next generat...

Read full story

TLDR:

If you are compute-constrained, use autoregressive models; if you are data-constrained, use diffusion models.

Motivation

Progress in AI over the past decade has largely been driven by scaling compute and data. The recipe from GPT-1 to ...

Read full story