arXiv Computer Vision August 28, 2026 By Vaishnavi Nagabhushana, Kartikay Agrawal, Ayon Borthakur

Parameter Efficient Continual Learning for Sparse Event-Based Transformers

Read the original on arXiv Computer Vision →

The paper introduces sLoTh, a parameter‑efficient continual learning framework for sparse event‑based vision transformers. sLoTh freezes the backbone and limits plasticity to low‑rank attention updates (seLoRA) and shared neuronal threshold modulation, updating less than 1% of parameters without replay buffers. Experiments on CIFAR‑100, Tiny‑ImageNet, ImageNet‑100, and ImageNet‑R show competitive rehearsal‑free performance across up to 100 tasks while achieving roughly 6.5× lower energy consumption than dense vision transformers.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers

2d ago

Parameter Efficient Continual Learning for Sparse Event-Based Transformers

Robotic and edge intelligence systems operate in dynamic environments where data arrives continuously, requiring models to adapt while preserving previously learned knowledge under strict memory and e...

llms robotics fine-tuning

Hugging Face Trending Papers

Jun 1

Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization

Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learnable prompts at the input level. However, existing VP methods typically employ dense pixel-level prompts, which often suffer from redundant perturbations, limited generalization and energy inefficiency.

llms benchmarks

arXiv AI

Jun 3

PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models

arXiv:2606. 03598v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved remarkable success in language-conditioned robotic manipulation.

By Ziyang Chen, Shaoguang Wang, Weiyu Guo, Qianyi Cai, He Zhang, Pengteng Li, Yiren Zhao, Yandong Guo

agents robotics multimodal

arXiv Machine Learning

Aug 12

GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging

arXiv:2509. 13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models.

By Irene Testa, Luigi Quarantiello, Eric Nuertey Coleman, Samrat Mukherjee, Julio Hurtado, Vincenzo Lomonaco

fine-tuning benchmarks

arXiv Machine Learning

Jul 30

Gated Adaptation for Continual Learning in Human Activity Recognition

arXiv:2603. 10046v2 Announce Type: replace Abstract: Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR).

By Reza Rahimi Azghan, Gautham Krishna Gudur, Mohit Malu, Edison Thomaz, Giulia Pedrielli, Pavan Turaga, Hassan Ghasemzadeh

arXiv AI

Jul 14

Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models

arXiv:2607. 09785v1 Announce Type: cross Abstract: Traditionally, continual learning has assumed access to labeled data, yet many real-world applications -- such as lifelong robotics -- require models to adapt continuously from unlabeled streams.

By Sergi Masip, Alicja Dobrzeniecka, Jonathan Swinnen, Joachim Collin, Bart{\l}omiej Twardowski, Szymon {\L}ukasik, Tinne Tuytelaars

robotics efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

Parameter Efficient Continual Learning for Sparse Event-Based Transformers

Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization

PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models

GLAM: Efficient Continual Learning at Scale via Grouped LoRA Adapter Merging

Gated Adaptation for Continual Learning in Human Activity Recognition

Lifelong Representations: A Survey on Continual Self-Supervised Learning for Vision Models