88 citations · 715 across the 43 of their papers we have counts for
9 papers · 1 filter
How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks
Ali Ansari, Haoran Sun, Andy Zeyi Liu +48
Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still strugg…
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
Andy Zeyi Liu, Haoran Sun, Lucas Baker +2
Joint-Embedding Predictive Architecture (JEPA) world models learn a compact latent representation of the world that supports prediction and planning, but their capability to learn…
Finite-temperature Green's function cluster expansion from thermofield doubles: Breakdown of the polaron picture
M. R. Carbone, S. Fomichev, B. Kloss +4
We introduce a method, numerically exact in principle, for computing the momentum- and frequency-resolved single-particle Green's function of a polaron at finite temperature. The m…
Self-consistent GW theory for superconductivity in SrTiO3 models
Zhi-Hao Cui, John Sous, Andrew J. Millis +1
Superconductivity in doped SrTiO occurs over a wide range of carrier densities, including those for which the Fermi energy is below the polar longitudinal optical phonon scale.…
Assign and Add: A Mechanistic Study of Compositional Arithmetic
Brady Exoo, Alberto Bietti, John Sous
Large language models are able to compose skills in order to perform complex tasks, many of which might not have been seen during training. The details of how exactly this composit…
Asymmetric Scaling Laws from Sparse Features
John Sous, Michael Winer
We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input.…