Inference Acceleration papers, 2023–2026

Key findings

• Inference Acceleration went from 54 papers in 2023 to 91 in 2026, roughly 1.7x in three years.
• NeurIPS publishes the most Inference Acceleration work: 90 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Deep learning · large language models: papers tagged with both rose from 1 in 2023 to 9 in 2026.
• Among the 5 topics under Efficiency and Systems, it ranks #5 by 2026 paper count; the fastest grower in the group, Hardware-Aware ML, is up 4.4x versus 1.7x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026A Method-Class Divide in Sub-4-Bit Quantization:\\Iterative vs.\ Single-Pass Sensitivity to Data Composition
• ICML 2026Consistency Deep Equilibrium Models
• ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
• CVPR 2026GeoRK2 Geometry-Guided Runge-Kutta Integration for Diffusion Transformer Acceleration
• NeurIPS 2025PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
• ICML 2025RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
• ICLR 2025Progressive distillation induces an implicit curriculum
• CVPR 2025Adapting Dense Matching for Homography Estimation with Grid-based Acceleration
• NeurIPS 2024Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
• ICML 2024Diversified Batch Selection for Training Acceleration
• ICLR 2024Embarrassingly Simple Dataset Distillation
• CVPR 2024Data-Free Quantization via Pseudo-label Filtering
• NeurIPS 2023Continuous-time Analysis of Anchor Acceleration
• ICML 2023Auxiliary Modality Learning with Generalized Curriculum Distillation
• ICLR 2023Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
• CVPR 2023NIPQ: Noise Proxy-Based Integrated Pseudo-Quantization
• NeurIPS 2026AcceleGrad#: Adaptive Geometry-Aware Acceleration
• ICML 2026PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU Inference
• ICLR 2026NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
• CVPR 2026SODA Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer

All Inference Acceleration papers

90 papers, page 2 of 2

51. NeurIPS 2024Adaptive Depth Networks with Skippable Sub-Paths
52. NeurIPS 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
53. NeurIPS 2024BiDM: Pushing the Limit of Quantization for Diffusion Models
54. NeurIPS 2024Constant Acceleration Flow
55. NeurIPS 2024CRONOS: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
56. NeurIPS 2024DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
57. NeurIPS 2024Fast Best-of-N Decoding via Speculative Rejection
58. NeurIPS 2024Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
59. NeurIPS 2024GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
60. NeurIPS 2024KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
61. NeurIPS 2024Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
62. NeurIPS 2024Nesterov acceleration despite very noisy gradients
63. NeurIPS 2024OneBit: Towards Extremely Low-bit Large Language Models
64. NeurIPS 2024Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
65. NeurIPS 2024ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
66. NeurIPS 2024ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
67. NeurIPS 2024Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
68. NeurIPS 2024UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
69. NeurIPS 2024Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
70. NeurIPS 2024VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
71. NeurIPS 2023Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
72. NeurIPS 2023Conformalized matrix completion
73. NeurIPS 2023Continuous-time Analysis of Anchor Acceleration
74. NeurIPS 2023Counterfactually Comparing Abstaining Classifiers
75. NeurIPS 2023Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
76. NeurIPS 2023Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee
77. NeurIPS 2023First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities
78. NeurIPS 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
79. NeurIPS 2023Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds
80. NeurIPS 2023Knowledge Distillation for High Dimensional Search Index
81. NeurIPS 2023Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference
82. NeurIPS 2023Pseudo-Likelihood Inference
83. NeurIPS 2023QuIP: 2-Bit Quantization of Large Language Models With Guarantees
84. NeurIPS 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
85. NeurIPS 2023Speculative Decoding with Big Little Decoder
86. NeurIPS 2023Students Parrot Their Teachers: Membership Inference on Model Distillation
87. NeurIPS 2023SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration
88. NeurIPS 2023Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value
89. NeurIPS 2023Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data
90. NeurIPS 2023WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

FAQ

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

259 in total: 54 in 2023, 50 in 2024, 64 in 2025, 91 in 2026.

How many Inference Acceleration papers are at NeurIPS 2026?

NeurIPS 2026 has 33 Inference Acceleration papers, versus 15 the year before.

How many Inference Acceleration papers are at ICLR 2026?

ICLR 2026 has 17 Inference Acceleration papers, versus 18 the year before.

How many Inference Acceleration papers are at ICML 2026?

ICML 2026 has 26 Inference Acceleration papers, versus 22 the year before.

How many Inference Acceleration papers are at CVPR 2026?

CVPR 2026 has 15 Inference Acceleration papers, versus 9 the year before.

Which conference publishes the most Inference Acceleration papers?

NeurIPS, with 90 papers from 2023 to 2026.