# EventFlash: Towards Efficient MLLMs for Event-Based Vision

arXiv: https://arxiv.org/abs/2602.03230 · HTML: https://mlsanity.com/paper/2602.03230/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 47 of its 65 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Events-to-Video: Bringing Modern Computer Vision to Event Cameras](https://mlsanity.com/paper/1904.08298/) (2019)
- [Learning to Detect Objects with a 1 Megapixel Event Camera](https://mlsanity.com/paper/2009.13436/) (2020)
- [MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding](https://mlsanity.com/paper/2406.14515/) (2024)
- [Streaming Long Video Understanding with Large Language Models](https://mlsanity.com/paper/2405.16009/) (2024)
- [LongVLM: Efficient Long Video Understanding via Large Language Models](https://mlsanity.com/paper/2404.03384/) (2024)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Event-based Asynchronous Sparse Convolutional Networks](https://mlsanity.com/paper/2003.09148/) (2020)
- [N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras](https://mlsanity.com/paper/2112.01041/) (2021)
- [PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding](https://mlsanity.com/paper/2504.13180/) (2025)
- [GET: Group Event Transformer for Event-Based Vision](https://mlsanity.com/paper/2310.02642/) (2023)
- [MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models](https://mlsanity.com/paper/2501.02955/) (2025)
- [Learning Dense and Continuous Optical Flow from an Event Camera](https://mlsanity.com/paper/2211.09078/) (2022)
- [Event Camera Data Pre-training](https://mlsanity.com/paper/2301.01928/) (2023)
- [STORM: Token-Efficient Long Video Understanding for Multimodal LLMs](https://mlsanity.com/paper/2503.04130/) (2025)
- [HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors](https://mlsanity.com/paper/2211.09648/) (2022)
- [ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification](https://mlsanity.com/paper/2410.08584/) (2024)

## Built on by (most cited first, 3 of 3)

- [Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets](https://mlsanity.com/paper/2603.24991/) (2026)
- [Neuromorphic Object Detection: An In-Depth Study and Future Directions](https://mlsanity.com/paper/2607.23576/) (2026)
- [Event ActivityNet: A Large-Scale Simulated-Event Benchmark for Untrimmed Action Understanding](https://mlsanity.com/paper/2608.01948/) (2026)

## Abstract (arXiv)

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like processing paradigms, overlooking the spatiotemporal sparsity of event streams and resulting in high computational cost. In this paper, we propose EventFlash, a novel and efficient MLLM to explore spatiotemporal token sparsification for reducing data redundancy and accelerating inference. Technically, we build EventMind, a large-scale and scene-diverse dataset with over 500k instruction sets, providing both short and long event stream sequences to support our curriculum training strategy. We then present an adaptive temporal window aggregation module for efficient temporal sampling, which adaptively compresses temporal tokens while retaining key temporal cues. Finally, a sparse density-guided attention module is designed to improve spatial token efficiency by selecting informative regions and suppressing empty or sparse areas. Experimental results show that EventFlash achieves a 12.4× throughput improvement over the baseline (EventFlash-Zero) while maintaining comparable performance. It supports long-range event stream processing with up to 1,000 bins, significantly outperforming the 5-bin limit of EventGPT. We believe EventFlash serves as an efficient foundation model for event-based vision.