LLM-generated synthetic datasets steered uniformly across a 2D performance space defined by two landmark algorithms improve meta-learner performance on algorithm selection for regression tasks.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 4years
2026 4roles
method 1polarities
use method 1representative citing papers
SPADE is a conditional diffusion model for offline black-box optimization that adds calibrated moment/ranking consistency and kNN support-proximity regularization, with a claimed first-order Bayesian equivalence.
DoTS decouples SFT and RLVR training then synthesizes their task vectors at inference time to match integrated training results at ~3% compute cost.
KUP-BI distills continuation-style knowledge from a train-only historical library to supply an approximate post-target proxy that is fused into forecasting backbones for improved performance on public datasets.
citing papers explorer
-
LLM-Driven Performance-Space Augmentation for Meta-Learning-Based Algorithm Selection
LLM-generated synthetic datasets steered uniformly across a 2D performance space defined by two landmark algorithms improve meta-learner performance on algorithm selection for regression tasks.
-
Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization
SPADE is a conditional diffusion model for offline black-box optimization that adds calibrated moment/ranking consistency and kNN support-proximity regularization, with a claimed first-order Bayesian equivalence.
-
Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors
DoTS decouples SFT and RLVR training then synthesizes their task vectors at inference time to match integrated training results at ~3% compute cost.
-
Beyond Extrapolation: Knowledge Utilization Paradigm with Bidirectional Inspiration for Time Series Forecasting
KUP-BI distills continuation-style knowledge from a train-only historical library to supply an approximate post-target proxy that is fused into forecasting backbones for improved performance on public datasets.