Ax Nima Dehmamy, Benjamin Hoover, Bishwajit Saha, Leo Kozachkov, Jean-Jacques Slotine, Dmitry Krotov 5/4/2026

NRGPT: An Energy-based Alternative for GPT

NRGPT reframes GPT inference as energy-based model exploration, proposing minimal architectural modifications to unify with EBM framework.

Ax Dongyeop Woo, Marta Skreta, Seonghyun Park, Kirill Neklyudov, Sungsoo Ahn 5/4/2026

Riemannian MeanFlow

Riemannian MeanFlow framework reduces neural network evaluations needed for diffusion models on Riemannian manifolds for generative modeling.

Ax Wenshuo Zhao (May), Qi Zhu (May), Xingshan Zeng (May), Fei Mi (May), Lifeng Shang (May), Yi R. (May), Fung 5/4/2026

Entropy Centroids as Intrinsic Rewards for Test-Time Scaling

Intrinsic reward method using entropy centroids for test-time compute scaling and response selection in large language models.

Ax Preston Rozwood, Edward Mehrez, Ludger Paehler, Wen Sun, Steven L. Brunton 5/4/2026

Koopman-Assisted Reinforcement Learning

Reinforcement learning algorithms using data-driven Koopman operator to linearize nonlinear dynamics for tractable control.

Ax Cameron Yetman 5/4/2026

Representation in large language models

Research paper analyzing internal representations and mechanisms in LLMs, addressing theoretical disagreements about how these models function.

Ax Chenhui Xu, Fuxun Yu, Michael J. Bianco, Jacob Kovarskiy, Raphael Tang, Qi Zhang, Zirui Xu, Will LeVine, Brandon Dubbs, Heming Liao, Cassandra Burgess, Suvam Bag, Jay Patravali, Rupanjali Kukal, Mikael Figueroa, Rishi Madhok, Nikolaos Karianakis, Jinjun Xiong 5/4/2026

Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards

Method for zero-shot geospatial reasoning in vision-language models using indirect rewards from metadata to overcome supervision scarcity.

Ax Alexius Wadell, Anoushka Bhutani, Victor Azumah, Austin R. Ellis-Mohr, Andrew J. Stier, Kareem Hegazy, Alexander Brace, Hancheng Zhao, Celia Kelly, Anuj K. Nayak, Yuhan Chen, Dimitrios Simatos, Hongyi Lin, Murali Emani, Venkatram Vishwanath, Kevin Gering, Melisa Alkan, Tom Gibbs, Jack Wells, Wesley W. Qian, Richard C. Gerkin, Benjamin Amorelli, Alexander B. Wiltschko, Lav R. Varshney, Bharath Ramsundar, Karthik Duraisamy, Michael W. Mahoney, Arvind Ramanathan, Venkatasubramanian Viswanathan 5/4/2026

Foundation Models for Discovery and Exploration in Chemical Space

MIST foundation models family for molecular property prediction and chemical space discovery, trained on large unlabeled datasets for materials innovation.

Ax William R\'eveillard, Vasileios Saketos, Alexandre Proutiere, Richard Combes 5/4/2026

Minimizing Human Intervention in Online Classification

Active learning framework for LLM classification systems minimizing costly human feedback while maintaining error guarantees through efficient labeling strategies.