# TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting

arXiv: https://arxiv.org/abs/2402.00066 · HTML: https://mlsanity.com/paper/2402.00066/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Transformer Networks for Trajectory Forecasting](https://mlsanity.com/paper/2003.08111/) (2020)
- [TimeGPT-1](https://mlsanity.com/paper/2310.03589/) (2023)
- [Deep Learning Methods for Vessel Trajectory Prediction based on Recurrent Neural Networks](https://mlsanity.com/paper/2101.02486/) (2021)
- [GeoTrackNet-A Maritime Anomaly Detector using Probabilistic Neural Network Representation of AIS Tracks and A Contrario Detection](https://mlsanity.com/paper/1912.00682/) (2019)
- [Predicting Like A Pilot: Dataset and Method to Predict Socially-Aware Aircraft Trajectories in Non-Towered Terminal Airspace](https://mlsanity.com/paper/2109.15158/) (2021)

## Built on by (most cited first, 13 of 13)

- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration](https://mlsanity.com/paper/2505.20256/) (2025)
- [InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models](https://mlsanity.com/paper/2412.14006/) (2024)
- [UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning](https://mlsanity.com/paper/2509.18094/) (2025)
- [Online Reasoning Video Segmentation with Just-in-Time Digital Twins](https://mlsanity.com/paper/2503.21056/) (2025)
- [VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning](https://mlsanity.com/paper/2511.16077/) (2025)
- [Rotary Masked Autoencoders are Versatile Learners](https://mlsanity.com/paper/2505.20535/) (2025)
- [Motion-Aware Vision-Reference Alignment for Referring Multi-Object Tracking](https://mlsanity.com/paper/2511.17681/) (2025)
- [STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning](https://mlsanity.com/paper/2602.11730/) (2026)
- [UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models](https://mlsanity.com/paper/2512.11336/) (2025)
- [SVAC: Scaling Is All You Need For Referring Video Object Segmentation](https://mlsanity.com/paper/2509.24109/) (2025)
- [SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction](https://mlsanity.com/paper/2601.18537/) (2026)
- [MoVISA: Multi-Token Reasoning for Video Object Segmentation](https://mlsanity.com/paper/2609.28956/) (2026)

## Abstract (arXiv)

The forecasting of entity trajectories at future points in time is a critical capability gap in applications across both Commercial and Defense sectors. Transformers, and specifically Generative Pre-trained Transformer (GPT) networks have recently revolutionized several fields of Artificial Intelligence, most notably Natural Language Processing (NLP) with the advent of Large Language Models (LLM) like OpenAI's ChatGPT. In this research paper, we introduce TrackGPT, a GPT-based model for entity trajectory forecasting that has shown utility across both maritime and air domains, and we expect to perform well in others. TrackGPT stands as a pioneering GPT model capable of producing accurate predictions across diverse entity time series datasets, demonstrating proficiency in generating both long-term forecasts with sustained accuracy and short-term forecasts with high precision. We present benchmarks against state-of-the-art deep learning techniques, showing that TrackGPT's forecasting capability excels in terms of accuracy, reliability, and modularity. Importantly, TrackGPT achieves these results while remaining domain-agnostic and requiring minimal data features (only location and time) compared to models achieving similar performance. In conclusion, our findings underscore the immense potential of applying GPT architectures to the task of entity trajectory forecasting, exemplified by the innovative TrackGPT model.