On higher regulators of Picard modular surfaces
Linli Shi
TL;DR
The paper advances Beilinson’s conjectures in the setting of Picard modular surfaces by constructing nontrivial motivic classes in $H^3_M(S,V(2))$ via Eisenstein symbols and showing their Beilinson regulators land in a well-behaved subspace tied to interior cohomology. It then establishes a precise link between these motivic classes and non-critical values of motivic L-functions attached to cuspidal automorphic representations of GU(2,1), encoding this relation in explicit period comparisons and L-value formulas. A core technical achievement is the simultaneous vanishing-on-the-boundary analysis in both absolute Hodge and motivic cohomology, implemented through boundary triangles, Burgos–Wildeshaus/Kostant degeneration, and motivic weight structures, yielding a motivic lifting of boundary-vanishing phenomena. The results provide evidence for Beilinson-type conjectures in a higher-rank unitary setting, and offer a framework for relating Eisenstein-derived motivic classes to automorphic L-values via explicit regulators and period relations, with potential implications for constructing Euler systems in families.
Abstract
We prove the motivic classes in the motivic cohomology groups of Picard modular surfaces with non-trivial coefficients constructed in a paper of Loeffler\textendash Skinner\textendash Zerbes are in the motivic cohomology groups of the interior motives. Then we establish a relation between the motivic classes and non-critical values of the motivic $L$-functions associated to cuspidal automorphic representations of $\mathrm{GU}(2,1)$, thus deducing non-triviality of the motivic classes and providing evidence for Beilinson's conjectures.
