# SynHAT: A Two-stage Coarse-to-Fine Diffusion Framework for Synthesizing Human Activity Traces

arXiv: https://arxiv.org/abs/2604.14705 · HTML: https://mlsanity.com/paper/2604.14705/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 98 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Builds on (most cited first, 30 of 33)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [WaveGrad: Estimating Gradients for Waveform Generation](https://mlsanity.com/paper/2009.00713/) (2020)
- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech](https://mlsanity.com/paper/2207.06389/) (2022)
- [UrbanGPT: Spatio-Temporal Large Language Models](https://mlsanity.com/paper/2403.00813/) (2024)
- [SinDDM: A Single Image Denoising Diffusion Model](https://mlsanity.com/paper/2211.16582/) (2022)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatches](https://mlsanity.com/paper/1609.06354/) (2016)
- [Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D](https://mlsanity.com/paper/2305.13266/) (2023)
- [Mobility-LLM: Learning Visiting Intentions and Travel Preferences from Human Mobility Data with Large Language Models](https://mlsanity.com/paper/2411.00823/) (2024)
- [A Deep Adversarial Model for Suffix and Remaining Time Prediction of Event Sequences](https://mlsanity.com/paper/2102.07298/) (2021)
- [GeoGen: A Two-stage Coarse-to-Fine Framework for Fine-grained Synthetic Location-based Social Network Trajectory Generation](https://mlsanity.com/paper/2510.07735/) (2025)
- [STUaNet: Understanding uncertainty in spatiotemporal collective human mobility](https://mlsanity.com/paper/2102.06027/) (2021)
- [UQGNN: Uncertainty Quantification of Graph Neural Networks for Multivariate Spatiotemporal Prediction](https://mlsanity.com/paper/2508.08551/) (2025)
- [HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction](https://mlsanity.com/paper/2602.05286/) (2026)
- [Geo-Llama: Leveraging LLMs for Human Mobility Trajectory Generation with Spatiotemporal Constraints](https://mlsanity.com/paper/2408.13918/) (2024)
- [Uncertainty-aware Predict-Then-Optimize Framework for Equitable Post-Disaster Power Restoration](https://mlsanity.com/paper/2508.04780/) (2025)
- [HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing](https://mlsanity.com/paper/2508.04811/) (2025)
- [TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecasting](https://mlsanity.com/paper/2506.17609/) (2025)
- [STS-CCL: Spatial-Temporal Synchronous Contextual Contrastive Learning for Urban Traffic Forecasting](https://mlsanity.com/paper/2307.02507/) (2023)
- [BTS: A Comprehensive Benchmark for Tie Strength Prediction](https://mlsanity.com/paper/2410.19214/) (2024)
- [Learning from the Storm: A Multivariate Machine Learning Approach to Predicting Hurricane-Induced Economic Losses](https://mlsanity.com/paper/2506.17964/) (2025)
- [TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction](https://mlsanity.com/paper/2601.13422/) (2026)
- [CREDIT: Certified Ownership Verification of Deep Neural Networks Against Model Extraction Attacks](https://mlsanity.com/paper/2602.20419/) (2026)

## Built on by (most cited first, 4 of 4)

- [LatentRouter: Can We Choose the Right Multimodal Model Before Seeing Its Answer?](https://mlsanity.com/paper/2605.11301/) (2026)
- [E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation](https://mlsanity.com/paper/2606.01634/) (2026)
- [ZeroHAT: Behavior-Conditioned Zero-Shot Human Activity Trace Generation](https://mlsanity.com/paper/2609.20310/) (2026)
- [Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching](https://mlsanity.com/paper/2609.32732/) (2026)

## Abstract (arXiv)

Human activity traces (HATs) are critical for many applications, including human mobility modeling and point-of-interest (POI) recommendation. However, growing privacy concerns have severely limited access to authentic large-scale HAT datasets. Recent advances in generative AI provide new opportunities to synthesize realistic and privacy-preserving HATs for such applications. Yet two major challenges remain: (i) HATs are highly irregular and dynamic, with long and varying time intervals, making it difficult to capture their complex spatio-temporal dependencies and underlying distributions; and (ii) generative models are often computationally expensive, making long-term, fine-grained HAT synthesis inefficient. To address these challenges, we propose SynHAT, a computationally efficient coarse-to-fine HAT synthesis framework built on a novel spatio-temporal denoising diffusion model. In Stage 1, we develop Coarse-HADiff, which models the overall spatio-temporal dependencies of coarse-grained latent spatio-temporal traces. It incorporates a novel Latent Spatio-Temporal U-Net with dual Drift-Jitter branches to jointly model smooth spatial transitions and temporal variations during denoising. In Stage 2, we introduce a three-step pipeline consisting of Behavior Pattern Extraction, Fine-HADiff, which shares the same architecture as Coarse-HADiff, and Semantic Alignment to generate fine-grained latent spatio-temporal traces from the Stage 1 outputs. We extensively evaluate SynHAT in terms of data fidelity, utility, privacy, robustness, and scalability. Experiments on real-world HAT datasets from four cities across three countries show that SynHAT substantially outperforms state-of-the-art baselines, achieving 52% and 33% improvements on spatial and temporal metrics, respectively.