# EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation

arXiv: https://arxiv.org/abs/2607.22655 · HTML: https://mlsanity.com/paper/2607.22655/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 56 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing](https://mlsanity.com/paper/2407.05600/) (2024)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information](https://mlsanity.com/paper/2012.00489/) (2020)
- [PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting](https://mlsanity.com/paper/2509.04545/) (2025)
- [Exploring Large Language Models for Human Mobility Prediction under Public Events](https://mlsanity.com/paper/2311.17351/) (2023)
- [LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model](https://mlsanity.com/paper/2406.03866/) (2024)
- [CityGPT: Empowering Urban Spatial Cognition of Large Language Models](https://mlsanity.com/paper/2406.13948/) (2024)
- [Learning Geo-Contextual Embeddings for Commuting Flow Prediction](https://mlsanity.com/paper/2005.01690/) (2020)
- [Multiscale Dynamic Human Mobility Flow Dataset in the U.S. during the COVID-19 Epidemic](https://mlsanity.com/paper/2008.12238/) (2020)
- [Event-Aware Multimodal Mobility Nowcasting](https://mlsanity.com/paper/2112.08443/) (2021)
- [A Machine Learning Approach to Modeling Human Migration](https://mlsanity.com/paper/1711.05462/) (2017)
- [An Interdisciplinary Survey on Origin-destination Flows Modeling: Theory and Techniques](https://mlsanity.com/paper/2306.10048/) (2023)
- [Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM](https://mlsanity.com/paper/2505.19901/) (2025)
- [CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Events](https://mlsanity.com/paper/2412.02155/) (2024)
- [Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion](https://mlsanity.com/paper/2505.20053/) (2025)
- [Exploring MLLM-Diffusion Information Transfer with MetaCanvas](https://mlsanity.com/paper/2512.11464/) (2025)
- [A County-level Dataset for Informing the United States' Response to COVID-19](https://mlsanity.com/paper/2004.00756/) (2020)
- [LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMs](https://mlsanity.com/paper/2507.19939/) (2025)
- [EventTSF: Event-Aware Non-Stationary Time Series Forecasting](https://mlsanity.com/paper/2508.13434/) (2025)
- [Event-aware analysis of cross-city visitor flows using large language models and social media data](https://mlsanity.com/paper/2505.03847/) (2025)
- [Programmable-Room: Interactive Textured 3D Room Meshes Generation Empowered by Large Language Models](https://mlsanity.com/paper/2506.17707/) (2025)
- [SeMob: Semantic Synthesis for Dynamic Urban Mobility Prediction](https://mlsanity.com/paper/2510.01245/) (2025)

## Abstract (arXiv)

Estimating origin-destination (OD) flows under disruptive events is important for disaster response and urban resilience. Existing deep OD models trained on routine mobility often degrade when extreme events abruptly alter regional functions and population activities, while retraining a new generator for each event is impractical under limited event-time supervision. We propose EventOD, an event-adaptive OD generation framework that steers a pretrained OD generator using structured event semantics. EventOD first uses a large language model to infer region-level functional and demographic control vectors from coarse event observations. It then learns two lightweight adaptation modules, AlphaNet and BetaNet, to calibrate the magnitude of these semantic shifts, and further introduces a retrieval-augmented fallback pathway for scenarios with sparse supervision. The resulting event-conditioned features are injected into a pretrained graph diffusion OD model through input-level modulation, enabling event-aware adaptation without updating generator parameters. Experiments on hurricane- and pandemic-induced mobility across U.S. counties show that EventOD consistently improves both reconstruction accuracy and distributional fidelity over strong baselines. Source code is available at https://anonymous.4open.science/r/EventOD-5C11/.