Differentiable programming connects scientific computation with gradient-based inference, learning and design. Extending these capabilities across a heterogeneous software ecosystem requires specialized effort to implement derivatives, integrate interfaces and evaluate quality. AI coding agents can accelerate this tran...
Peng-Cheng Hou, Xiao-Jun Tan, Si-Han Hu et al.· 0 citations
The Large Knowledge Model is proposed, a growing, agent-native knowledge foundation that provides a general representation of scientific knowledge across disciplines and an agent-native, reasoning-aware scientific retrieval system that retrieves claims together with their reasoning chains and sources, enabling agents t...
Yuan Huang, Si-Han Hu, Hong-Yu Gu et al.· 0 citations
We study the two-dimensional XY model with the nonanalytic pair potential $2[(1-\cos\delta)/2]^{p}$, whose small-angle law $\propto|\delta|^{2p}$ carries a cusp for $p<1$ and a flat bottom for $p>1$, invalidating the harmonic spin-wave expansion. Two questions arise: the nature of the low-temperature ($T$) phase and of...
State-of-the-art models are far more proficient in scientific coding than SciCode has suggested---the bottleneck was not model capability, but the quality of the evaluation instrument.
Sihan Hu, Lyuhan Huang, You-Jin Deng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.