| --- |
| license: apache-2.0 |
| pipeline_tag: robotics |
| --- |
| |
| # EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies |
|
|
| EventVLA is an end-to-end vision-language-action framework designed for long-horizon robotic manipulation tasks. It introduces an event-driven visual evidence memory mechanism to address memory bottlenecks when task-relevant cues become occluded or unobservable over time. |
|
|
| - **Project Page:** [ganlin-yang.github.io/EventVLA.github.io](https://ganlin-yang.github.io/EventVLA.github.io/) |
| - **Repository:** [GitHub - InternRobotics/EventVLA](https://github.com/InternRobotics/EventVLA) |
| - **Paper:** [EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies](https://huggingface.co/papers/2606.20092) |
| - **Dataset:** [RoboTwin-MeM on Hugging Face](https://huggingface.co/datasets/ganlinyang/RoboTwin-MeM) |
|
|
| ## Model Description |
|
|
| EventVLA addresses the memory constraints of standard Vision-Language-Action (VLA) policies by employing a dynamic Keyframe Evidence Memory (KEM) module alongside foundational visual anchors. KEM predicts future keyframe probabilities from latent embeddings to store sparse, task-critical visual events, preserving visual evidence before it is lost or obscured. |
|
|
| This repository contains the trained weights evaluated on two benchmarks: |
| * **RoboTwin-MeM**: Checkpoints for evaluation on the eight RoboTwin-MeM tasks. |
| * **RMBench**: Checkpoints for evaluation on the RMBench benchmark. |
|
|
| Each release directory contains: |
| - `pytorch_model.pt` |
| - `config.yaml` |
| - `dataset_statistics.json` |
| - `summary.jsonl` |
|
|
| Please refer to the [official GitHub repository](https://github.com/InternRobotics/EventVLA) for instructions on installation, training, and evaluation. |
|
|
| ## Citation |
|
|
| If you find this work useful, please cite: |
|
|
| ```bibtex |
| @article{yang2026eventvla, |
| title={EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies}, |
| author={Yang, Ganlin and Tu, Zhangzheng and Yang, Yuqiang and Mao, Sitong and Dong, Junyi and Chen, Tianxing and Peng, Jiaqi and Xiong, Jing and Cao, Jiafei and Dai, Jifeng and others}, |
| journal={arXiv preprint arXiv:2606.20092}, |
| year={2026} |
| } |
| ``` |
