Transactions on Machine Learning Research

Following the success of last year's initiative, RL Conference 2025 (@rl-conference.bsky.social) is again having a Journal to Conference track!

Accepted TMLR within scope are invited to submit for consideration by May 1!
docs.google.com/forms/d/e/1F...

26.03.2025 17:45 — 👍 20    🔁 6    💬 0    📌 1

2024 TMLR Annual Report 2024 TMLR Annual Report Kyunghyun Cho Gautam Kamath Hugo Larochelle Naila Murray Paul Vicol Summary Editorial Team Submissions and Decisions Problematic Case(s) and Policies Certifications OpenReview...

Check out TMLR's 2024 Annual Report! Featuring stats, updates, and details about plans for the future!
docs.google.com/document/d/1...

28.01.2025 13:39 — 👍 9    🔁 3    💬 0    📌 0

New year, new editor-in-chief: we are excited to welcome Nihar B. Shah to the editors-in-chief of TMLR!

We bade farewell to founding EiC Kyunghyun Cho (@kyunghyuncho.bsky.social), who has done immense sevice by co-founding and helping TMLR thrive the last several years.

09.01.2025 16:18 — 👍 39    🔁 3    💬 0    📌 0

Announcing the 2024 TMLR Outstanding Certification By the 2024 TMLR Outstanding Paper Committee: Michael Bowling, Brian Kingsbury, Andreas Kirsch, Yingzhen Li, and Eleni Triantafillou

Thanks to Outstanding Certification committee: Michael Bowling, Brian Kingsbury, Andreas Kirsch, Yingzhen Li, Eleni Triantafillou.

Check out the blog post for details on the selection process! 7/7
medium.com/@TmlrOrg/ann...

08.01.2025 17:41 — 👍 0    🔁 0    💬 0    📌 0

Open Problems and Fundamental Limitations of Reinforcement Learning... Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large...

Outstanding Finalist 3: "Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback" by Stephen Casper, Xander Davies et al. 6/n openreview.net/forum?id=bx2...

08.01.2025 17:41 — 👍 2    🔁 0    💬 1    📌 0

DINOv2: Learning Robust Visual Features without Supervision The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could...

Outstanding Finalist 2: “DINOv2: Learning Robust Visual Features without Supervision," by Maxime Oquab, Timothée Darcet, Théo Moutakanni et al. 5/n openreview.net/forum?id=a68...

08.01.2025 17:41 — 👍 8    🔁 3    💬 2    📌 0

Beyond the Imitation Game: Quantifying and extrapolating the... Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet...

Outstanding Finalist 1: “Beyond the Imitation Game: Quantifying and Extrapolating the Capabilities of Language Models” (BIG-bench), by a very large team (450 authors). 4/n openreview.net/forum?id=uyT...

08.01.2025 17:41 — 👍 1    🔁 0    💬 1    📌 0

Holistic Evaluation of Language Models Language models (LMs) are becoming the foundation for almost all major language technologies, but their capabilities, limitations, and risks are not well understood. We present Holistic Evaluation...

Outstanding Certification 2: “Holistic Evaluation of Language Models” (HELM), by a large team led by Percy Liang, Rishi Bommasani, and Tony Lee 3/n
openreview.net/forum?id=iO4...

08.01.2025 17:41 — 👍 0    🔁 0    💬 1    📌 0

Inversion by Direct Iteration: An Alternative to Denoising... Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called ``regression to the mean'' effect and produces more realistic and detailed...

This year we have 2 outstanding certifications, and 3 finalists!

Outstanding Certification 1: “Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration” by Mauricio Delbracio & Peyman Milanfar. 2/n
openreview.net/forum?id=Vmy...

08.01.2025 17:41 — 👍 2    🔁 0    💬 1    📌 0

Announcing the 2024 TMLR Outstanding Certification By the 2024 TMLR Outstanding Paper Committee: Michael Bowling, Brian Kingsbury, Andreas Kirsch, Yingzhen Li, and Eleni Triantafillou

🎉Announcing... the 2024 TMLR Outstanding Certifications! (aka, our "best paper" awards!)

Are you bursting with anticipation to see what they are? Check out this blog post, and read down-thread!! 🎉🧵👇 1/n
medium.com/@TmlrOrg/ann...

08.01.2025 17:41 — 👍 20    🔁 7    💬 1    📌 1