Tag
This paper introduces RiskTraf, a residual learning plug-in for multi-variate traffic flow prediction, and presents a new benchmark PEMSB-3V to enhance forecasting accuracy by extrapolating risk from speed and occupancy data.
Proposes OGR-MARL, an option-guided residual multi-agent reinforcement learning framework for heterogeneous USV cooperative pursuit in constrained port waterways. The MASAC instantiation achieves a 75% capture rate and shows promising zero-shot transfer to a real map scenario.
This arXiv paper studies the problem of factor-derived proxy supervision in scientific machine learning, using RUSLE-based soil-loss prediction as a case study. It introduces a diagnostic framework and proposes RASPL, a formula-preserving residual learning framework that outperforms direct prediction and improves robustness to degraded factor information.
RouteCost is a multi-stage framework for pre-order shipping cost estimation in e-commerce, combining time-aware demand forecasting, fee-card baseline pricing, residual correction, and box consolidation inference. The method improves predictive quality over 250,000 orders and 260 products while maintaining interpretability.
This paper introduces StateFlow, a recurrent forecasting framework that extends the Variability-Aware Recursive Neural Network (VARNN) to long-horizon multivariate time series forecasting by using a dual-state recurrent backbone and a chunk-based decoder, achieving competitive performance against strong baselines.
Operator Boosting is a stagewise residual-learning framework that constructs compact neural operator surrogates for PDEs by training tiny models on residual fields. It achieves accuracy comparable to or better than full-size models while reducing parameters by up to 95%, demonstrating Pareto improvements on several benchmarks.
XOResNet introduces OR-ADD shortcut connections and XOR meta-residuals to address spike redundancy and information loss in deep spiking neural networks, achieving state-of-the-art results on Fashion-MNIST, CIFAR-10, CIFAR-100, and miniImageNet.
Introduces Multi-Agent Residual In-Context Learning (MARICL), an agentic framework that uses LLM agents to analyze residuals from a base model on tabular data, hypothesize missing structure, and produce explicit correction terms via textual gradient optimization. Across nine benchmarks, MARICL consistently improves over its base model and demonstrates mechanistic generalization in cell-free protein predictions.