Accepted papers
The following papers were accepted to the AI4PowerGrids workshop at NeurIPS 2026.
Oral presentations
Papers selected for oral presentation are also presented during the poster sessions.
Learning Adaptive Topology-Aware Line Margins for AC Optimal Power Flow under Forecast Uncertainty and Distribution Shift
FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations
Toward Out-of-Distribution Generalization in Neural AC Power Flow
Benchmarking CPU, GPU, and ML Power-Flow Solvers from 14 to 70,000 Buses
Poster presentations
Closing the Accuracy Gap in Electrical Model-Free OPF with Concurrent Voltage Estimation
Spatio-Temporal GraphSAGE Framework for Generalizable Power Grid Representations
Extrapolating to Unseen Solar PV Levels: Physics-Informed Voltage Calculation in Low-Voltage Networks
Towards a Generalization Benchmark for GNN Power-Flow Models: An Out-of-Distribution Evaluation for Transmission Grids
Diffusion-based Random Attack Generators for Interdiction Analysis in Electric Power Systems
PowerFORM: A General-Purpose Foundation Model for Power Systems
DERBench: A Benchmark for Evaluating LLMs on Distributed Energy Resource Operations
Compositional Power System Dynamic Model Using Causality-Aware Physics-Informed DeepONet
Benchmarking LLM Bidding Agents in Electricity Markets: Hour-Specific Pricing and Experience Effects
Ground Flash Density as a Function of Climate: Scenario-Conditioned Lightning Hazard with Calibrated Uncertainty
The Cost of Coverage: Conformalising Native Forecast Uncertainty for GB Wind Power
Sensor-Aware Joint Data Fusion and State Estimation under Sparse Multi-rate Distribution Grid Sensing
Learning-Enhanced Column Generation for Large-Scale Bulk Dispatch Optimization
FP-QF: A Matrix-Inversion-Free AC Power Flow Solver for Differentiable ML Pipelines
Causal Models for Electricity Markets and Power Grid Congestion
Beyond Average Error: SpikeBench-PJM for Real-Time Electricity Price Forecasting
FALCON-UC: Feasibility-Aware Learning for Network-Constrained Unit Commitment
Cross-Market Meta-Learning for Electricity Price Forecasting
Reconciling European Electricity Data with Diffusion Priors Learned from Observations Alone
Deep Learning-Accelerated Shapley Value for Fair Allocation in Power Systems at Real-World Grid Scale
AutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control
Metamorphic testing of learned AC-OPF evaluation reveals representation dependence
Decentralized Model-Free Voltage Calculation Using Neighboring Smart-Meter Data
Structured Equilibrium Learning for OPF Imitation
Beyond Price Signals: Coordinated Wholesale Market Participation for Flexible Data Centers
Structured Representation Learning for Behavior Cloning: How can we learn to safely control a nuclear power plant?
UNION: Topology-Conditioned AC-OPF under Structural Grid Shifts