Skip to content

šŸš— Autonomous Driving

šŸ’¬ ACL2025 Ā· 1 paper notes

šŸ“Œ Same area in other venues: šŸ“· CVPR2026 (157) Ā· šŸ”¬ ICLR2026 (50) Ā· šŸ§Ŗ ICML2026 (8) Ā· šŸ¤– AAAI2026 (56) Ā· šŸ§  NeurIPS2025 (47) Ā· šŸ“¹ ICCV2025 (91)

Embracing Large Language Models in Traffic Flow Forecasting

The LEAF framework is proposed, which utilizes a dual-branch predictor comprising a graph branch (for pair-wise relations) and a hypergraph branch (for non-pair-wise relations) to generate candidate forecasts. A frozen LLM is then employed as a selector (interpreting discriminatively rather than generatively) to choose the optimal forecast, optimizing the predictor through feedback via ranking loss, achieving SOTA on PEMS datasets.