This repository is a curated collection of recent research papers on trajectory and motion prediction, targeting researchers and engineers in autonomous driving, robotics, and computer vision. It provides a centralized, up-to-date index of papers from top-tier conferences and arXiv, facilitating quick access to state-of-the-art methods and fostering collaboration.

How It Works

The repository functions as a living bibliography, systematically indexing papers by conference and year. It categorizes research across major venues like CVPR, ICCV, ECCV, NeurIPS, ICLR, ICRA, IROS, CoRL, RA-L, KDD, and AAAI, with ongoing updates for the latest publications. Each entry typically includes a title, a link to the paper (arXiv, official website, or code repository), and sometimes a brief description or associated project.

Quick Start & Requirements

This repository is a collection of papers and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Comprehensive indexing across 15+ major AI/robotics conferences and arXiv.
• Covers a wide range of sub-topics including multi-agent prediction, social interactions, generative models, diffusion models, graph neural networks, and attention mechanisms.
• Includes direct links to papers, code, and project websites where available.
• Regularly updated with the latest research, including papers from CVPR 2025 and ICLR 2025.

Maintenance & Community

The repository is maintained by colorfulfuture, with an invitation for community contributions via pull requests. Contact information for potential collaborations is provided.

Licensing & Compatibility

The repository itself contains links to external papers, each with its own licensing. The collection is for informational purposes.

Limitations & Caveats

This is a curated list of papers and does not provide code implementations, benchmarks, or direct functionality. The utility is purely informational, relying on the availability and quality of linked external resources.