AL

Andy Zeyi Liu

cs.AIcs.LGquant-phcs.CVstat.ML

On Valency

published · living versions

W_sz2b2m5q·v2 · currentpublished

How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks

with Ali Ansari, Haoran Sun, Mark Jabbour, Yongshan Ding +46

2 versions

Preprints & journals

7 papers in the corpus · 2025–2026

How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks2609.13009v2 · Ali Ansari, Haoran Sun, Andy Zeyi Liu et al.2026 · 0 citationsarXivon Valency

Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization2609.10464v1 · Andy Zeyi Liu, Haoran Sun, Lucas Baker et al.2026 · 0 citationsarXiv

Spectral Lens: Activation and Gradient Spectra as Diagnostics of LLM Optimization2605.05683v1 · Andy Zeyi Liu, Elliot Paquette, John Sous2026 · 0 citationsarXiv

Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs2605.06225v2 · Andy Zeyi Liu, Michael Zhang, Ilana Greenberg et al.2026 · 0 citationsarXiv

QGPU: Parallel logic in quantum LDPC codes2603.05398v1 · Boren Gu, Andy Zeyi Liu, Armanda O. Quintavalle et al.2026 · 0 citationsarXiv

Check-weight-constrained quantum codes: Bounds and examples2601.15446v1 · Lily Wang, Andy Zeyi Liu, Ray Li et al.2026 · 0 citationsarXiv

Fault-tolerant Preparation of Distant Logical Bell Pair -- with application in the magic square game2503.13673v1 · Andy Zeyi Liu, Debbie Leung2025 · 0 citationsarXiv

Career total: 7 works. 7 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.