A Transformer RL agent is trained to generate valid heterotic line bundle sums on CICYs that satisfy gauge embedding, anomaly cancellation, poly-stability, chirality, and no-exotics constraints.
Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
verdicts
UNVERDICTED 11representative citing papers
Neural network-parameterized regression splines enable joint optimization of forecast quality and stability in distribution-free probabilistic time series models by penalizing dissimilarities from forecast updates.
Equivariant neural networks produce dipole and polarizability surfaces for methanol that enable variational computation of vibrational IR and Raman spectra agreeing with experiment to 2.2 cm^{-1} RMSD on fundamentals.
UniGraphLM uses a multi-domain multi-task GNN encoder and adaptive alignment to create unified graph tokens for LLMs across diverse domains and tasks.
The Spatial Adapter equips frozen predictors with a spatially regularized orthonormal basis for residuals and derives a closed-form low-rank-plus-noise covariance for spatial prediction and kriging.
VISTA adaptively tunes consistency thresholds in decentralized SGD so that the system converges asymptotically like standard SGD even when adversaries dominate the worker pool.
MC-GenRef performs annotation-free microcalcification segmentation via synthetic data from a lightweight image formation model plus test-time generative posterior refinement with a rectified-flow generator, yielding top Dice on INbreast and gains on an external cohort.
LayerPipe2 derives per-layer delay assignments for multistage pipelined training and uses an improved moving average to recompute past weights without explicit storage.
Exact critic in entropy-regularized actor-critic yields strong variance reduction, enabling Õ(log(1/ε)) sample complexity for ε-optimal regularized value.
A domain-adapted diffusion model synthesizes heterogeneous PET images from uniform organ activity maps, achieving high quantitative accuracy (CCC > 0.92) and visual realism comparable to real scans.
Observability-constrained test-time prompt tuning for LiDAR semantic segmentation reweights spatial supervision using per-location reliability estimates from beam terminations and neighborhood support, with prompt adapters and temporal prototype alignment.
citing papers explorer
-
A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning
UniGraphLM uses a multi-domain multi-task GNN encoder and adaptive alignment to create unified graph tokens for LLMs across diverse domains and tasks.