8 papers
Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement
Alec Helbling, Andrey Bryutkin, Mauro Martino +2
Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puz…
NRGPT: An Energy-based Alternative for GPT
Nima Dehmamy, Benjamin Hoover, Bishwajit Saha +3
Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dy…
Discovering Symbolic Differential Equations with Symmetry Invariants
Jianke Yang, Manu Bhat, Bryan Hu +4
Discovering symbolic differential equations from data uncovers fundamental dynamical laws underlying complex systems. However, existing methods often struggle with the vast search…
Small Models, Smarter Learning: The Power of Joint Task Training
Csaba Both, Benjamin Hoover, Hendrik Strobelt +4
Multi-task learning improves generalization, but when does it reduce the model capacity required to learn? We provide a systematic study of how joint training affects the learning…
AtlasD: Automatic Local Symmetry Discovery
Manu Bhat, Jonghyun Park, Jianke Yang +3
Existing symmetry discovery methods predominantly focus on global transformations across the entire system or space, but they fail to consider the symmetries in local neighborhoods…
Understanding Mode Connectivity via Parameter Space Symmetry
Bo Zhao, Nima Dehmamy, Robin Walters +1
Neural network minima are often connected by curves along which train and test loss remain nearly constant, a phenomenon known as mode connectivity. While this property has enabled…