Sparsity Acceleration papers, 2023–2026

Key findings

• Sparsity Acceleration went from 54 papers in 2023 to 89 in 2026, roughly 1.6x in three years.
• NeurIPS publishes the most Sparsity Acceleration work: 80 papers from 2023 to 2026, 31% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 0 in 2023 to 13 in 2026.
• Among the 5 topics under Hardware and Compilers, it ranks #1 by 2026 paper count; the fastest grower in the group, Edge Inference, is up 4.0x versus 1.6x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026AC/DC on a Budget -- Alternating Sparse Phases
• ICML 2026An Evidential Route to Asymptotic Bayes Optimality under Sparsity
• ICLR 2026Hilbert-Guided Sparse Local Attention
• CVPR 2026Improving Sparse Autoencoder with Dynamic Attention
• NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
• ICML 2025COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
• ICLR 2025Beyond Worst-Case Dimensionality Reduction for Sparse Vectors
• CVPR 2025ICP: Immediate Compensation Pruning for Mid-to-high Sparsity
• NeurIPS 2024ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
• ICML 2024Accelerating Transformer Pre-training with 2:4 Sparsity
• ICLR 2024Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
• CVPR 2024Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement
• NeurIPS 2023Dynamic Sparsity Is Channel-Level Sparsity Learner
• ICML 2023Conformalization of Sparse Generalized Linear Models
• ICLR 2023Bit-Pruning: A Sparse Multiplication-Less Dot-Product
• CVPR 2023Adaptive Channel Sparsity for Federated Learning Under System Heterogeneity
• NeurIPS 2026Beyond Masked Sparsity: SNACK Enables Truly Sparse Neural Networks on GPU
• ICML 2026FlashSketch: Sketch-Kernel Co-Design for Fast Sparse Sketching on GPUs
• ICLR 2026Identifiability Challenges in Sparse Linear Ordinary Differential Equations
• CVPR 2026Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction

All Sparsity Acceleration papers

260 papers, page 3 of 6

101. ICLR 2025Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
102. ICLR 2025R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference
103. ICLR 2025ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing
104. ICLR 2025RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs
105. ICLR 2025Schur's Positive-Definite Network: Deep Learning in the SPD cone with structure
106. ICLR 2025Semantic Aware Representation Learning for Lifelong Learning
107. ICLR 2025Training-Free Activation Sparsity in Large Language Models
108. ICLR 2025Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
109. ICLR 2025VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration
110. ICLR 2025Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity
111. ICML 2025Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
112. ICML 2025AdaSplash: Adaptive Sparse Flash Attention
113. ICML 2025BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training
114. ICML 2025Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders
115. ICML 2025COGNATE: Acceleration of Sparse Tensor Programs on Emerging Hardware using Transfer Learning
116. ICML 2025CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models
117. ICML 2025Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective
118. ICML 2025Dynamic Sparse Training of Diagonally Sparse Networks
119. ICML 2025Fast Inference with Kronecker-Sparse Matrices
120. ICML 2025FlashTP: Fused, Sparsity-Aware Tensor Product for Machine Learning Interatomic Potentials
121. ICML 2025Grokking Beyond the Euclidean Norm of Model Parameters
122. ICML 2025Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
123. ICML 2025Metadata Conditioning Accelerates Language Model Pre-training
124. ICML 2025Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
125. ICML 2025Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models
126. ICML 2025Position: A Theory of Deep Learning Must Include Compositional Sparsity
127. ICML 2025PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS
128. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
129. ICML 2025Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
130. ICML 2025Sparsing Law: Towards Large Language Models with Greater Activation Sparsity
131. ICML 2025When Dynamic Data Selection Meets Data Augmentation: Achieving Enhanced Training Acceleration
132. ICML 2025XAttention: Block Sparse Attention with Antidiagonal Scoring
133. NeurIPS 2025Bilevel Network Learning via Hierarchically Structured Sparsity
134. NeurIPS 2025Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
135. NeurIPS 2025CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs
136. NeurIPS 2025Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization
137. NeurIPS 2025DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
138. NeurIPS 2025Exploiting Dynamic Sparsity in Einsum
139. NeurIPS 2025Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks
140. NeurIPS 2025Masked Gated Linear Unit
141. NeurIPS 2025MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE
142. NeurIPS 2025MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference
143. NeurIPS 2025PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
144. NeurIPS 2025Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
145. NeurIPS 2025Price of Parsimony: Complexity of Fourier Sparsity Testing
146. NeurIPS 2025Sign-In to the Lottery: Reparameterizing Sparse Training
147. NeurIPS 2025Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention
148. NeurIPS 2025Stochastic Shortest Path with Sparse Adversarial Costs
149. NeurIPS 2025The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
150. NeurIPS 2025TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks

FAQ

How many Sparsity Acceleration papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

260 in total: 54 in 2023, 53 in 2024, 64 in 2025, 89 in 2026.

How many Sparsity Acceleration papers are at NeurIPS 2026?

NeurIPS 2026 has 29 Sparsity Acceleration papers, versus 21 the year before.

How many Sparsity Acceleration papers are at ICLR 2026?

ICLR 2026 has 24 Sparsity Acceleration papers, versus 16 the year before.

How many Sparsity Acceleration papers are at ICML 2026?

ICML 2026 has 24 Sparsity Acceleration papers, versus 22 the year before.

How many Sparsity Acceleration papers are at CVPR 2026?

CVPR 2026 has 12 Sparsity Acceleration papers, versus 5 the year before.

Which conference publishes the most Sparsity Acceleration papers?

NeurIPS, with 80 papers from 2023 to 2026.