MLRC 2025

Welcome to the home of ML Reproducibility Challenge. This is an annual event promoting research into reproducibility of Machine Learning literature. (v1, v2, v3, v4, v5, v6, v7). This conference is an unique venue in the Machine Learning community to share, disseminate and discuss reproducible methods and tools, investigate reproducibility of papers accepted for publication at top conferences, and test generalizability of scientific findings by adding novel insights and empirical results.

  • 🔔 Join our Discord Server to connect with fellow attendees, ask orgaziner questions, post questions for panel discussions and more!
  • 🔔 Decisions for MLRC 2025 announced, congratulations to all accepted papers!
  • 🔔 Registration for MLRC 2025 In-Person event is now live!
  • MLRC 2025 Call for Papers is out! Checkout our announcement blog post.

Venue

We are happy to announce that the Princeton Laboratory for Artificial Intelligence is hosting MLRC 2025, which will be held in-person as a one-day conference, a Princeton University, NJ, USA on August 21st, 2025. The conference will be single-track, with a mix of invited talks, oral presentations and poster sessions. Checkout our announcement blog for more details!

Agenda

The conference will be held at Friend Center, William Street Room 101 Princeton, NJ 08540. The tentative agenda is provided here. Please register to attend the conference.

  • 9am-9.30am - Breakfast
  • 9:30am-9.45am - Opening remarks
  • 9.45am - 10:30am - Keynote talk by Arvind Narayanan, Professor of Computer Science at Princeton University, Director of the Center for Information Technology Policy; “The slowdown in scientific progress and the role of reproducibility”
  • 10:30am-11:15am - Keynote talk by Soumith Chintala, Pytorch @ Meta; “Reproducibility Is a Heroic Act: Not Efficient, Not Legal, Not Credited”
  • 11:15-11.45am - Invited Talk by Kelvin Niu, Researcher @ Meta; The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
  • Lunch Break : 12.00PM
  • 1:00pm-1:45pm - Keynote talk by Stella Biderman, Executive Director, Eleuther AI; “Lessons from the Trenches on Reproducible Evaluations of Language Models”
  • 1:45pm- 2:30pm - Keynote talk by Jonathan Frankle, Chief AI Scientist, Databricks; “The Humble Prompt Engineer: Looking to 1968 for the future of AI”
  • 2.30pm - 2.45pm - Coffee break
  • 2.45pm - 3.15pm - Oral Talks
  • 3:15pm - 4pm - Panel Discussion led by Sayash Kapoor (Princeton University) - “Reproducibility of and by language models”
  • 4pm-4.15pm - Closing remarks
  • 4.15pm- 5pm - Poster presentations

Accepted Papers

We are now happy to announce the list of accepted papers at MLRC 2025 - congratulations to all authors!

Important Dates

  • Submit to TMLR OpenReview: https://openreview.net/group?id=TMLR
  • Deadline to share your intent to submit a TMLR paper to MLRC: February 21st, 2025
  • This form requires that you provide a link to your TMLR submission. Once it gets accepted (if it isn’t already), you should then update the same form with your paper camera ready details.
  • Cutoff deadline for receiving TMLR decisions: June 20th, 2025
  • Deadline for announcing accepted papers: June 27th, 2025
  • Conference day: August 21st, 2025 at Princeton University, NJ, USA

Keynote Speakers

Panel Moderator

Organizer

Co-Organizers

General Chair

Program Chairs

Local Chairs

Senior Program Chair

Event Sponsors

The Machine Learning Reproducibility Challenge Conference is hosted by Princeton University’s AI Lab, with generous support from the following sponsors:

Contact

Last updated on Dec 12, 2024