# LET-US: Long Event-Text Understanding of Scenes

arXiv: https://arxiv.org/abs/2508.07401 · HTML: https://mlsanity.com/paper/2508.07401/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 35 references that are in the map.
- First posted on arXiv 10 Aug 2025.

## Builds on (most cited first, 23 of 23)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [MovieChat: From Dense Token to Sparse Memory for Long Video Understanding](https://mlsanity.com/paper/2307.16449/) (2023)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding](https://mlsanity.com/paper/2311.08046/) (2023)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [DSEC: A Stereo Event Camera Dataset for Driving Scenarios](https://mlsanity.com/paper/2103.06011/) (2021)
- [N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras](https://mlsanity.com/paper/2112.01041/) (2021)
- [Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks](https://mlsanity.com/paper/2302.08890/) (2023)
- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [Don't Look Twice: Faster Video Transformers with Run-Length Tokenization](https://mlsanity.com/paper/2411.05222/) (2024)
- [OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2405.05259/) (2024)
- [EventBind: Learning a Unified Representation to Bind Them All for Event-based Open-world Understanding](https://mlsanity.com/paper/2308.03135/) (2023)
- [Enhancing Long Video Understanding via Hierarchical Event-Based Memory](https://mlsanity.com/paper/2409.06299/) (2024)
- [EF-Calib: Spatiotemporal Calibration of Event- and Frame-Based Cameras Using Continuous-Time Trajectories](https://mlsanity.com/paper/2405.17278/) (2024)

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

- [Video-Based Reward Modeling for Computer-Use Agents](https://mlsanity.com/paper/2603.10178/) (2026)
- [EventBench: Towards Comprehensive Benchmarking of Event-based MLLMs](https://mlsanity.com/paper/2511.18448/) (2025)
- [Reconstruction as a Bridge for Event-Based Visual Question Answering](https://mlsanity.com/paper/2512.11510/) (2025)

## Abstract (arXiv)

Event cameras output event streams as sparse, asynchronous data with microsecond-level temporal resolution, enabling visual perception with low latency and a high dynamic range. While existing Multimodal Large Language Models (MLLMs) have achieved significant success in understanding and analyzing RGB video content, they either fail to interpret event streams effectively or remain constrained to very short sequences. In this paper, we introduce LET-US, a framework for long event-stream--text comprehension that employs an adaptive compression mechanism to reduce the volume of input events while preserving critical visual details. LET-US thus establishes a new frontier in cross-modal inferential understanding over extended event sequences. To bridge the substantial modality gap between event streams and textual representations, we adopt a two-stage optimization paradigm that progressively equips our model with the capacity to interpret event-based scenes. To handle the voluminous temporal information inherent in long event streams, we leverage text-guided cross-modal queries for feature reduction, augmented by hierarchical clustering and similarity computation to distill the most representative event features. Moreover, we curate and construct a large-scale event-text aligned dataset to train our model, achieving tighter alignment of event features within the LLM embedding space. We also develop a comprehensive benchmark covering a diverse set of tasks -- reasoning, captioning, classification, temporal localization and moment retrieval. Experimental results demonstrate that LET-US outperforms prior state-of-the-art MLLMs in both descriptive accuracy and semantic comprehension on long-duration event streams. All datasets, codes, and models will be publicly available.