Sparse Learning

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models ACL 2026 Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling CVPR 2026 ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization CVPR 2026 IAFMNet: Information-Aware Feature Modulation for Efficient Super-Resolution CVPR 2026 Improving Sparse Autoencoder with Dynamic Attention CVPR 2026 OneSparse: A Unified Framework for Sparse Activation Layers in Vision Models CVPR 2026 Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalization UAI 2026 Test-time Sparsity for Extreme Fast Action Diffusion CVPR 2026 UltraSparseBERT: 99% Conditionally Sparse Language Modelling ACL 2024 Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training NeurIPS 2023 The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers ICLR 2023 Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable ICLR 2022 Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning ICLR 2022 Dual Lottery Ticket Hypothesis ICLR 2022 Dynamic Forward and Backward Sparse Training (DFBST): Accelerated Deep Learning through Completely Sparse Training Schedule ACML 2022 Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks NeurIPS 2022 On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning ICLR 2022 ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity ICLR 2022 Efficient Neural Network Training via Forward and Backward Propagation Sparsification NeurIPS 2021 Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration NeurIPS 2021 Sparse Training via Boosting Pruning Plasticity with Neuroregeneration NeurIPS 2021 Winning the Lottery with Continuous Sparsification NeurIPS 2020 Evaluating Lottery Tickets Under Distributional Shifts EMNLP 2019 From Keyframes to Key Objects: Video Summarization by Representative Object Proposal Selection CVPR 2016 Approximating Sparse PCA from Incomplete Data NeurIPS 2015