{"total":30,"rows":[{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2206.09117","title":"NISPA: Neuro-Inspired Stability-Plasticity Adaptation for Continual Learning in Sparse Networks","created":"2022-06-18","cited_by_count":39,"area":null},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30,"area":null},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2104.09949","title":"DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device","created":"2021-04-20","cited_by_count":18,"area":null},{"id":"2305.18353","title":"Emergent representations in networks trained with the Forward-Forward algorithm","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2309.06626","title":"Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity","created":"2023-09-12","cited_by_count":10,"area":null},{"id":"2411.13055","title":"Hardware Scaling Trends and Diminishing Returns in Large-Scale Distributed Training","created":"2024-11-20","cited_by_count":8,"area":null},{"id":"2305.17005","title":"Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2403.18587","title":"The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2407.20421","title":"Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification","created":"2024-07-29","cited_by_count":7,"area":null},{"id":"2208.13363","title":"Survey: Exploiting Data Redundancy for Optimization of Deep Learning","created":"2022-08-29","cited_by_count":6,"area":null},{"id":"2411.06346","title":"Activation Map Compression through Tensor Decomposition for Deep Learning","created":"2024-11-10","cited_by_count":6,"area":null},{"id":"2402.16184","title":"Deep Neural Network Initialization with Sparsity Inducing Activations","created":"2024-02-25","cited_by_count":5,"area":null},{"id":"2204.01460","title":"Optimizing the Consumption of Spiking Neural Networks with Activity Regularization","created":"2022-04-04","cited_by_count":4,"area":null},{"id":"2208.04187","title":"DIVISION: Memory Efficient Training via Dual Activation Precision","created":"2022-08-05","cited_by_count":4,"area":null},{"id":"2305.07522","title":"SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving","created":"2023-05-12","cited_by_count":4,"area":null},{"id":"2506.01352","title":"TAH-QUANT: Effective Activation Quantization in Pipeline Parallelism over Slow Network","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2104.08314","title":"High Performance Convolution Using Sparsity and Patterns for Inference in Deep Convolutional Neural Networks","created":"2021-04-16","cited_by_count":3,"area":null},{"id":"2506.13440","title":"Sparse Convolutional Recurrent Learning for Efficient Event-based Neuromorphic Object Detection","created":"2025-06-16","cited_by_count":3,"area":null},{"id":"2107.07305","title":"Training for temporal sparsity in deep neural networks, application in video processing","created":"2021-07-15","cited_by_count":2,"area":null},{"id":"2210.15170","title":"Improved Projection Learning for Lower Dimensional Feature Maps","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2211.16703","title":"An Efficient Split Fine-tuning Framework for Edge and Cloud Collaborative Learning","created":"2022-11-30","cited_by_count":1,"area":null},{"id":"2309.02855","title":"Bandwidth-efficient Inference for Neural Image Compression","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2301.00675","title":"FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks","created":"2022-12-29","cited_by_count":0,"area":null},{"id":"2405.19652","title":"Dual sparse training framework: inducing activation map sparsity via Transformed $\\ell1$ regularization","created":"2024-05-30","cited_by_count":0,"area":null},{"id":"2406.10528","title":"Memory Faults in Activation-sparse Quantized Deep Neural Networks: Analysis and Mitigation using Sharpness-aware Training","created":"2024-06-15","cited_by_count":0,"area":null},{"id":"2406.12569","title":"MOYU: A Theoretical Study on Massive Over-activation Yielded Uplifts in LLMs","created":"2024-06-18","cited_by_count":0,"area":null},{"id":"2510.20979","title":"Memory Constrained Dynamic Subnetwork Update for Transfer Learning","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2605.25612","title":"Towards the Connection between Activation Sparsity and Flat Minima","created":"2026-05-25","cited_by_count":0,"area":null}],"next_cursor":null}