mlsanityData to 14 Oct 2026

Maximizing Asynchronicity in Event-based Neural Networks

arXiv 2505.11165 ↗First posted 16 May 2025cs.LG cs.AI cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Event cameras deliver visual data with high temporal resolution, low latency, and minimal redundancy, yet their asynchronous, sparse sequential nature challenges standard tensor-based machine learning (ML). While the recent asynchronous-to-synchronous (A2S) paradigm aims to bridge this gap by asynchronously encoding events into learned features for ML pipelines, existing A2S approaches often sacrifice expressivity and generalizability compared to dense, synchronous methods. This paper introduces EVA (EVent Asynchronous feature learning), a novel A2S framework to generate highly expressive and generalizable event-by-event features. Inspired by the analogy between events and language, EVA uniquely adapts advances from language modeling in linear attention and self-supervised learning for its construction. In demonstration, EVA outperforms prior A2S methods on recognition tasks (DVS128-Gesture and N-Cars), and represents the first A2S framework to successfully master demanding detection tasks, achieving a 0.477 mAP on the Gen1 dataset. These results underscore EVA's potential for advancing real-time event-based vision applications.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 45 of its 64 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

45 of 64 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  7. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  8. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
  9. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  10. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  11. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  12. 2019Event-based Vision: A Surveycited by 1,016
33 more
  1. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
  2. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 740
  3. 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 613
  4. 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 514
  5. 2019High Speed and High Dynamic Range Video with an Event Cameracited by 345
  6. 2015Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccadescited by 314
  7. 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
  8. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
  9. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 159
  10. 2024Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrencecited by 159
  11. 2017Parallelizing Linear Recurrent Neural Nets Over Sequence Lengthcited by 127
  12. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  13. 2020A Large Scale Event-based Detection Dataset for Automotivecited by 109
  14. 2020Event-based Asynchronous Sparse Convolutional Networkscited by 104
  15. 2024State Space Models for Event Camerascited by 75
  16. 2021Time-Ordered Recent Event (TORE) Volumes for Event Camerascited by 73
  17. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  18. 2018EventNet: Asynchronous Recursive Event Processingcited by 58
  19. 2018Asynchronous Convolutional Networks for Object Detection in Neuromorphic Camerascited by 57
  20. 2023From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detectioncited by 52
  21. 2020Temporal Binary Representation for Event-Based Action Recognitioncited by 51
  22. 2023Graph-based Asynchronous Event Processing for Rapid Object Recognitioncited by 51
  23. 2023Event Camera Data Pre-trainingcited by 50
  24. 2023Hierarchical Neural Memory Network for Low Latency Event Processingcited by 47
  25. 2022Masked Event Modeling: Self-Supervised Pretraining for Event Camerascited by 41
  26. 2024Scalable Event-by-event Processing of Neuromorphic Sensory Signals With Deep State-Space Modelscited by 31
  27. 2023Event Camera Data Dense Pre-trainingcited by 21
  28. 2024Microsaccade-inspired Event Camera for Roboticscited by 17
  29. 2024S7: Selective and Simplified State Space Layers for Sequence Modelingcited by 17
  30. 2024ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Datacited by 8
  31. 2024EvRepSL: Event-Stream Representation via Self-Supervised Learning for Event-Based Visioncited by 8
  32. 2024GG-SSMs: Graph-Generating State Space Modelscited by 3
  33. 2025Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Spacecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detectioncited by 0
  2. 2026Neural Events: Discrete Asynchronous Autoencoders for Event-Based Visioncited by 0