Collecting Recent Trajectory and Motion Prediction Papers. Keep Updating. If you find this repo useful, please ⭐️ star it and feel free to submit a pull request to contribute more papers!

My Homepage Feel Free to contact me for any potential collaboration with relevant topics of motion/trajectory prediction, generative models, graph neural networks, etc.

Email: [email protected]
Wechat: 578138534

Zhihu

📌 Jun 02, 2025: Added a new LLM-based trajectory prediction survey categorizing relevant papers and outlining future directions. Read it here.

Oct 30, 2025: Updated all NeurIPS 2025 paper links.
Sept 29, 2025: Added two NeurIPS 2025 papers.
Sept 01, 2025: Updated one arXiv 2025 paper.

LLM-based Trajectory Prediction (2025)

A curated survey that summarizes recent works using Large Language Models for trajectory prediction tasks.

• CVPR
  • CVPR 2025
  • CVPR 2024
  • CVPR 2023
  • CVPR 2022
• ICCV
  • ICCV 2025
  • ICCV 2023
• ECCV
  • ECCV 2024
  • ECCV 2022
• NeurIPS
  • NeurIPS 2025
  • NeurIPS 2024
  • NeurIPS 2023
  • NeurIPS 2022
• ICLR
  • ICLR 2025
  • ICLR 2024
  • ICLR 2023
  • ICLR 2022
• ICML
  • ICML 2025
• ICRA
  • ICRA 2024
  • ICRA 2023
  • ICRA 2022
• IROS
  • IROS 2024
  • IROS 2023
• CoRL
  • CoRL 2024
  • CoRL 2023
  • CoRL 2022
• RA-L
  • RA-L 2024
• AAAI
  • AAAI 2024
• KDD
  • KDD 2024
• arXiv
  • arXiv 2022
  • arXiv 2025

CVPR 2025 All Papers List

• Adapting to Observation Length of Trajectory Prediction via Contrastive Learning. Paper

• Certified Human Trajectory Prediction. Paper arXiv

• Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework. Paper

• Leveraging SD Map to Augment HD Map-based Trajectory Prediction. Paper

• MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation Distillation. Paper arXiv Code Website

• Multi-modal Knowledge Distillation-based Human Trajectory Forecasting. Paper arXiv Code

• Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment. Paper arXiv

• Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations. Paper arXiv

• SocialMOIF：Multi-Order Intention Fusion for Pedestrian Trajectory Prediction. Paper arXiv

• Trajectory-Mamba: An Efficient Attention-Mamba Forecasting Model Based on Selective SSM. Paper arXiv

• Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning. Paper arXiv

• Towards Generalizable Trajectory Prediction using Dual-Level Representation Learning and Adaptive Prompting. Paper arXiv

• Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling. Paper arXiv

CVPR 2024 All Papers List

• Adapting to Length Shift: FlexiLength Network for Trajectory Prediction. arXiv

• Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving. arXiv

• CaDeT: a Causal Disentanglement Approach for Robust Trajectory Prediction in Autonomous Driving. Paper

• Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction. arXiv Code Website

• Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction. Paper

• Higher-order Relational Reasoning for Pedestrian Trajectory Prediction. Paper

• HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention. arXiv Code

• Human Motion Prediction under Unexpected Perturbation. Code

• MoST: Multi-modality Scene Tokenization for Motion Prediction. arXiv

• Producing and Leveraging Online Map Uncertainty in Trajectory Prediction. arXiv Code

• Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations. arXiv Code

• SingularTrajectory: Universal Trajectory Predictor using Diffusion Model. arXiv Website Code

• SmartRefine: An Scenario-Adaptive Refinement Framework for Efficient Motion Prediction. arXiv Code

• SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction. arXiv Code

• T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory. arXiv

• Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning. arXiv

CVPR 2023 All Papers List

• Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction. Paper

• DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback. Paper arXiv

• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning. Paper arXiv Code

• FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-tail Trajectory Prediction. Paper arXiv

• FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphs. Paper arXiv Website Code

• Improving Multi-Agent Motion Prediction with Heuristic Goals and Motion Refinement.(CVPR23 workshop) Paper Code

• IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction. Paper arXiv

• Leapfrog Diffusion Model for Stochastic Trajectory Prediction. Paper arXiv Code

• MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion. Paper

• Planning-oriented Autonomous Driving. Paper arXiv Code Website

• ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals. Paper arXiv

• Query-Centric Trajectory Prediction. Paper Code

• Stimulus Verification is a Universal and Effective Sampler in Multi-modal Human Trajectory Prediction. Paper

• Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion. Paper arXiv Website

• Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting. Paper arXiv Code

• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction. Paper arXiv Code

• Unsupervised Sampling Promoting for Stochastic Human Trajectory Prediction. Paper arXiv Code

• ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries. Paper arXiv Code Website

• Weakly Supervised Class-agnostic Motion Prediction for Autonomous Driving. Paper

• Adaptive Trajectory Prediction via Transferable GNN. arXiv Paper

• ATPFL: Automatic Trajectory Prediction Model Design Under Federated Learning Framework. Paper

• Convolutions for Spatial Interaction Modeling. arXiv Paper

• End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps. arXiv Paper Code

• Forecasting from LiDAR via Future Object Detection. arXiv Paper Code

• Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction. Paper Code

• GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning. arXiv Paper Code

• How Many Observations are Enough? Knowledge Distillation for Trajectory Forecasting. arXiv Paper

• LTP: Lane-Based Trajectory Prediction for Autonomous Driving. Paper

• M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction. arXiv Paper Code

• Neural Prior for Trajectory Estimation. Paper Website

• Non-Probability Sampling Network for Stochastic Human Trajectory Prediction. arXiv Paper Code

• On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles. arXiv Paper Code

• Remember Intentions: Retrospective-Memory-based Trajectory Prediction. arXiv Paper Code

• ScePT: Scene-consistent, Policy-based Trajectory Predictions for Planning. Paper Code

• Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion. arXiv Paper Code

• Vehicle Trajectory Prediction Works, But Not Everywhere. arXiv Paper Code

• Whose Track Is It Anyway? Improving Robustness to Tracking Errors With Affinity-Based Trajectory Prediction. Paper Code

• Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction. (CVPR'22 Workshop Precognition: Seeing Through the Future) arXiv Paper

• Importance Is in Your Attention: Agent Importance Prediction for Autonomous Driving. (CVPR'22 Workshop Precognition: Seeing Through the Future) arXiv Paper

• TENET: Transformer Encoding Network for Effective Temporal Flow on Motion Prediction (CVPR'22 Workshop) arXiv

• BE-STI: Spatial-Temporal Integrated Network for Class-Agnostic Motion Prediction With Bidirectional Enhancement. Paper Code

• Forecasting Characteristic 3D Poses of Human Actions. arXiv Paper Code

• HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction. Paper Code

• Human Trajectory Prediction With Momentary Observation. Paper

• MotionAug: Augmentation With Physical Correction for Human Motion Prediction. arXiv Paper Code

• Motron: Multimodal Probabilistic Human Motion Forecasting. arXiv Paper Code

• Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation. Paper

• Multi-Person Extreme Motion Prediction. arXiv Paper Code

• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction. arXiv Paper Code

• Spatial-Temporal Gating-Adjacency GCN for Human Motion Prediction. arXiv Paper

• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective. arXiv Paper Code

• Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction. arXiv Paper Code

ICCV 2025 All Papers List

• AMD: Adaptive Momentum and Decoupled Contrastive Learning Framework for Robust Long-Tail Trajectory Prediction. arXiv

• DONUT: A Decoder-Only Model for Trajectory Prediction. arXiv

• Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics. arXiv

• ForeSight: Multi-View Streaming Joint Object Detection and Trajectory Forecasting.

• Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model. arXiv

• NATRA: Noise-Agnostic Framework for Trajectory Prediction with Noisy Observations.

• SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement. arXiv

• TOTP: Transferable Online Pedestrian Trajectory Prediction with Temporal-Adaptive Mamba Latent Diffusion.

• Unified Multi-Agent Trajectory Modeling with Masked Trajectory Diffusion.

ICCV 2023 All Papers List

• ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation. Paper arXiv Code Website

• BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction. Paper arXiv Code Website

• BiFF: Bi-level Future Fusion with Polyline-based Coordinate for Interactive Trajectory Prediction. Paper arXiv

• Bootstrap Motion Forecasting With Self-Consistent Constraints. Paper

• EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting. Paper arXiv Code Website

• Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction. Paper arXiv Code

• Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders. Paper arXiv Code

• GameFormer: Game-theoretic Modeling and Learning of Transformer-based Interactive Prediction and Planning for Autonomous Driving. Paper arXiv Code Website

• HumanMAC: Masked Motion Completion for Human Motion Prediction. Paper arXiv Code Website

• INT2: Interactive Trajectory Prediction at Intersections. Paper Code Website

• InterDiff: Generating 3D Human-Object Interactions with Physics-Informed Diffusion. Paper arXiv Code Website

• Joint Metrics Matter: A Better Standard for Trajectory Forecasting. Paper arXiv

• Learn TAROT with MENTOR: A Meta-Learned Self-Supervised Approach for Trajectory Prediction. Paper

• MotionLM: Multi-Agent Motion Forecasting as Language Modeling. Paper

• R-Pred: Two-Stage Motion Prediction Via Tube-Query Attention-Based Trajectory Refinement. Paper arXiv

• Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction. Paper arXiv

• Sparse Instance Conditioned Multimodal Trajectory Prediction. Paper

• Traj-MAE:Masked Autoencoders for Trajectory Prediction. Paper arXiv

• Trajectory Unified Transformer for Pedestrian Trajectory Prediction. Paper Code

• TrajPAC: Towards Robustness Verification of Pedestrian Trajectory Prediction Models. Paper arXiv

• Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction. arXiv Code

• MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction. arXiv Code

• Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation. arXiv Project Code

• Progressive Pretext Task Learning for Human Trajectory Prediction. arXiv Code

• PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving. arXiv Code

• Scene-aware Human Motion Forecasting via Mutual Distance Prediction. arXiv Code

• UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction. arXiv Code

ECCV 2022 All Paper List List

• Action-based Contrastive Learning for Trajectory Prediction. arXiv

• AdvDO: Realistic Adversarial Attacks for Trajectory Prediction. arXiv

• Aware of the History: Trajectory Forecasting with the Local Behavior Data. arXiv Code

• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors arXiv Code Website

• D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights. arXiv Code

• Entry-Flipped Transformer for Inference and Prediction of Participant Behavior. arXiv

• Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting. arXiv

• Human Trajectory Prediction via Neural Social Physics. arXiv Code

• Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction. arXiv Code Website

• Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction. arXiv

• Polarimetric Pose Prediction. arXiv

• PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map. arXiv Code

• Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction. arXiv Code

• Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimatio. arXiv Code Website

• Social ODE: Multi-Agent Trajectory Forecasting with Neural Ordinary Differential Equations. Paper

• Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-Agent Trajectory Prediction. Paper Code

• SocialVAE: Human Trajectory Prediction using Timewise Latents. arXiv Code

• ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning. arXiv Code

• View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums. arXiv

• A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction. Paper

• Towards Predicting Any Human Trajectory In Context. Paper arXiv

• DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States. Paper arXiv Code

• Motion Forecasting in Continuous Driving. Paper arXiv Code

• MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction. Paper arXiv Code

• LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations. Paper

• Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking. Paper arXiv Code

• Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving. Paper arXiv Code

• SMART: Scalable Multi-agent Real-time Motion Generation Via Next-token Prediction. Paper arXiv Code

• TrajCLIP: Pedestrian Trajectory Prediction Method Using Contrastive Learning and Idempotent Networks. Paper

• BCDiff: Bidirectional Consistent Diffusion for Instantaneous Trajectory Prediction. OpenReview

• Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding. arXiv Code Website

• Social Motion Prediction with Cognitive Hierarchies. arXiv Code Website

• trajdata: A Unified Interface to Multiple Human Trajectory Datasets. arXiv Code

• What Truly Matters in Trajectory Prediction for Autonomous Driving? arXiv Code Website

• Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context. OpenReview Code

• SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots. OpenReview Code Website

• trajdata: A Unified Interface to Multiple Human Trajectory Datasets. arXiv Code

NeurIPS 2022 All Paper List List

• Contact-aware Human Motion Forecasting. OpenReview arXiv Code

• Forecasting Human Trajectory from Scene History. OpenReview arXiv

• Interaction Modeling with Multiplex Attention. OpenReview arXiv

• Motion Forecasting Transformer with Global Intention Localization and Local Movement Refinement. OpenReview arXiv Code

• Interactive Adjustment for Human Trajectory Prediction with Individual Feedback. Paper

• Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction. Paper Code

• Neuralized Markov Random Field for Interaction-Aware Stochastic Human Trajectory Prediction. Paper Code

• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports. Paper arXiv Code

• Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving. Paper Code

• TSC-Net: Prediction of Pedestrian Trajectories by Trajectory-Scene-Cell Classification. Paper

• SEPT: Towards Efficient Scene Representation Learning for Motion Prediction. arXiv

• Social-Transmotion: Promptable Human Trajectory Prediction. arXiv Code

ICLR 2023 All Paper List List

• Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network. OpenReview arXiv

• Stochastic Multi-Person 3D Motion Forecasting. OpenReview

• Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction. OpenReview

• D-CODE: Discovering Closed-form ODEs from Observed Trajectories. Paper Code

• Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Prediction. Paper Code

• ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics. Paper Website

• Scene Transformer: A Unified Architecture for Predicting Multiple Agent Trajectories. Paper

• THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling. Paper

• You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction. Paper

• DriveGPT: Scaling Autoregressive Behavior Models for Driving. Paper arXiv

• SAH-Drive: A Scenario-Aware Hybrid Planner for Closed-Loop Vehicle Trajectory Generation. Paper arXiv

• Three-Dimensional Trajectory Prediction with 3DMoTraj Dataset. Paper Code

• CRITERIA: A New Benchmarking Paradigm for Evaluating Trajectory Prediction Models for Autonomous Driving. arXiv

• A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Prediction. arXiv

• Context-Aware Timewise VAEs for Real-Time Vehicle Trajectory Prediction. arXiv

• DESTINE: Dynamic Goal Queries with Temporal Transductive Alignment for Trajectory Prediction. arXiv

• Disentangled Neural Relational Inference for Interpretable Motion Prediction. arXiv

• FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction. arXiv

• LaCE-LHMP: Airflow Modelling-Inspired Long-Term Human Motion Prediction by Enhancing Laminar Characteristics in Human Flow. arXiv Code

• MacFormer: Map-Agent Coupled Transformer for Real-time and Robust Trajectory Prediction. arXiv

• MGTR: Multi-Granular Transformer for Motion Prediction with LiDAR. arXiv

• Human Observation-Inspired Trajectory Prediction for Autonomous Driving in Mixed-Autonomy Traffic Environments. arXix Code

• Human Observation-Inspired Trajectory Prediction for Autonomous Driving in Mixed-Autonomy Traffic Environments. arXiv Code

• Improving Autonomous Driving Safety with POP: A Framework for Accurate Partially Observed Trajectory Predictions. Project arXiv Code

• Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning. arXiv

• PBP: Path-based Trajectory Prediction for Autonomous Driving. arXiv

• Scene Informer: Anchor-based Occlusion Inference and Trajectory Prediction in Partially Observable Environments. arXiv Code

• Expanding the Deployment Envelope of Behavior Prediction via Adaptive Meta-Learning. arXiv

• GANet: Goal Area Network for Motion Forecasting. arXiv Code

• TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction. arXiv Code Website

• Path-Aware Graph Attention for HD Maps in Motion Prediction. arXiv

• Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed arXiv Code

• Improving Out-of-Distribution Generalization of Trajectory Prediction for Autonomous Driving via Polynomial Representations arXiv

• Deep Stochastic Kinematic Models for Probabilistic Motion Forecasting in Traffic arXiv

• Interpretable Trajectory Prediction for Autonomous Vehicles via Counterfactual Responsibility. Website

• Joint Out-of-Distribution Detection and Uncertainty Estimation for Trajectory Prediction. arXiv Code

• Streaming Motion Forecasting for Autonomous Driving. arXiv Code

• ESCIRL: Evolving Self-Contrastive IRL for Trajectory Prediction in Autonomous Driving. Paper

• JointMotion: Joint Self-supervision for Joint Motion Prediction. Paper Code

• Multi-Transmotion: Pre-trained Model for Human Motion Prediction. arXiv Code

• Not All Errors Are Made Equal: A Regret Metric for Detecting System-level Trajectory Prediction Failures. arXiv Project

• Multi-Predictor Fusion: Combining Learning-based and Rule-based Trajectory Predictors. arXiv

• SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving. arXiv Code

• SIMPL: A Simple and Efficient Multi-agent Motion Prediction Baseline for Autonomous Driving. arXiv Code

• ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model. arXiv Code

• ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving. arXiv

• Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation. arXiv Code

• Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting. arXiv

• Wayformer: Motion Forecasting via Simple & Efficient Attention Networks. arXiv

• A Retrieval Augmented Spatio-Temporal Framework for Traffic Prediction. arXiv