Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feederblog.ml.cmu.edu
Blog | Machine Learning | Carnegie Mellon University
Get the latest updates from Blog | Machine Learning | Carnegie Mellon University directly as they happen.
Follow now 142 followers
Latest posts
Last updated 3 days ago
Forking-Sequences — Part II: Multi-Horizon Forecast Ensembling with Reduced Volatility
3 days ago
Based on: Potosnak, W., Wolff, M., Cao, M., Ma, R., Konstantinova, T.,...
Healthcare Benchmarks Are Only as Good as Their Assumptions
about 2 months ago
In healthcare settings where patients use LLMs as a medical assistant, LLM...
Pre-Training Isn’t Bitter Enough
about 2 months ago
Task construction as the control surface in continued pretraining. A construction rule...
Teaching Vision-Language Models to Speak Cinema
3 months ago
A year of building a video caption pipeline with 100+ professional creators,...
Introducing ARFBench: A time series question-answering benchmark based on real incidents
4 months ago
More than a trillion dollars are lost every year due to system...
Carnegie Mellon at ICLR 2026
4 months ago
CMU researchers are presenting 194 papers at the Fourteenth International Conference on...
When Should AI Step Aside?: Teaching Agents When Humans Want to Intervene
4 months ago
Recent advances in large language models (LLMs) have enabled AI agents to...
LumberChunker: Long-Form Narrative Document Segmentation
5 months ago
Links:Paper | Code | Data LumberChunker lets an LLM decide where a...
Yes, AI, There is a Santa Claus
8 months ago
People use LLMs to ask for insight on a variety of important...
Validating LLM-as-a-Judge Systems under Rating Indeterminacy
8 months ago
Figure 1: Our framework for validating LLM-as-a-judge systems under rating indeterminacy, where...
Carnegie Mellon at NeurIPS 2025
9 months ago
CMU researchers are presenting 156 papers at the Thirty-Ninth Annual Conference on...
How to Explore to Scale RL Training of LLMs on Hard Problems?
9 months ago
Figure 1. Three regimes of exploration: Current RL model can explore via:...