# Relative Transitions, Not Absolute Destinations: A Transfer-and-Ground Framework for Target-Trajectory-Free Human Mobility Generation

arXiv: https://arxiv.org/abs/2610.02033 · HTML: https://mlsanity.com/paper/2610.02033/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 76 references that are in the map.
- First posted on arXiv 1 Oct 2026.

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

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Improving and generalizing flow-based generative models with minibatch optimal transport](https://mlsanity.com/paper/2302.00482/) (2023)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection](https://mlsanity.com/paper/2006.10521/) (2020)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2007.14189/) (2020)
- [Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2404.17591/) (2024)
- [Continuous Trajectory Generation Based on Two-Stage GAN](https://mlsanity.com/paper/2301.07103/) (2023)
- [Diff-RNTraj: A Structure-aware Diffusion Model for Road Network-constrained Trajectory Generation](https://mlsanity.com/paper/2402.07369/) (2024)
- [COLA: Cross-city Mobility Transformer for Human Trajectory Simulation](https://mlsanity.com/paper/2403.01801/) (2024)
- [Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags](https://mlsanity.com/paper/2111.00970/) (2021)
- [Be More Real: Travel Diary Generation Using LLM Agents and Individual Profiles](https://mlsanity.com/paper/2407.18932/) (2024)
- [Data-driven generation of spatio-temporal routines in human mobility](https://mlsanity.com/paper/1607.05952/) (2016)
- [PateGail: A Privacy-Preserving Mobility Trajectory Generator with Imitation Learning](https://mlsanity.com/paper/2407.16729/) (2024)
- [Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasaurus](https://mlsanity.com/paper/2409.13790/) (2024)
- [GTG: Generalizable Trajectory Generation Model for Urban Mobility](https://mlsanity.com/paper/2502.01107/) (2025)
- [Traj-MLLM: Can Multimodal Large Language Models Reform Trajectory Data Mining?](https://mlsanity.com/paper/2509.00053/) (2025)
- [Think2Go: Generative Next POI Recommendation with LLM Reasoning](https://mlsanity.com/paper/2607.28997/) (2026)

## Abstract (arXiv)

Individual mobility trajectories support urban analysis and location-based services, yet most trajectory generators require observations from their deployment city. This assumption excludes precisely the cities where trajectories are unavailable even though points of interest (POIs) and their attributes can be obtained from public maps. We study target-trajectory-free generation: learning from POIs and trajectories in source cities while utilizing only POI coordinates and categories in a target city, with no target trajectory or trajectory-derived statistic available for training, model selection, or generation. Existing trajectory generators typically predict absolute destinations, entangling reusable movement behavior with city-specific POI identities and spatial layouts. Our core insight is to replace this city-bound output with context-conditioned relative transitions. We propose Nomad, a transfer-and-ground framework that separates learning how people move from determining where those movements are realized. Specifically, a history-conditioned flow-matching model learns from source trajectories a transition prior over semantic displacement between POI contexts, geographic displacement, and elapsed time; at inference, a behavior graph and an exploration--return walk ground sampled transitions onto the target POI map. This factorization enables a direct test of representation level transferability without assuming invariance of the full mobility distribution. Extensive experiments across ten cities and 14 transfers show that Nomad outperforms adaptation baselines in trajectory fidelity and downstream utility, lowering the average error over the best baseline of each metric by about 15% in distributional fidelity and about 3% in downstream utility.