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

259 papers, page 1 of 6

1. CVPR 2026Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
2. CVPR 2026D2Cache Second-Order Delta Caching for Higher Video Diffusion Acceleration
3. CVPR 2026Denoising as Path Planning Training-Free Acceleration of Diffusion Models with
4. CVPR 2026Fast3Dcache Training-free 3D Geometry Synthesis Acceleration
5. CVPR 2026Flow Map Distillation Without Data
6. CVPR 2026GeoRK2 Geometry-Guided Runge-Kutta Integration for Diffusion Transformer Acceleration
7. CVPR 2026Just-in-Time Training-Free Spatial Acceleration for Diffusion Transformers
8. CVPR 2026LESA Learnable Stage-Aware Predictors for Diffusion Model Acceleration
9. CVPR 2026Masked Auto-Regressive Variational Acceleration Fast Inference Makes Practical Reinforcement Learning
10. CVPR 2026ResCa Residual Caching for Diffusion Transformers Acceleration
11. CVPR 2026S2D Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations
12. CVPR 2026Seele A Unified Acceleration Framework for Real-Time Gaussian Splatting on
13. CVPR 2026SODA Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer
14. CVPR 2026TAP A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration
15. CVPR 2026TC-Pade Trajectory-Consistent Pade Approximation for Diffusion Acceleration
16. ICLR 2026BBQ: Boosting Quantization Entropy with Bell Box Quantization
17. ICLR 2026Corner Gradient Descent
18. ICLR 2026Dataset Distillation as Pushforward Optimal Quantization
19. ICLR 2026DiCache: Let Diffusion Model Determine Its Own Cache
20. ICLR 2026Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
21. ICLR 2026Distributionally Robust Linear Regression with Block Lewis Weights
22. ICLR 2026Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
23. ICLR 2026Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
24. ICLR 2026GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
25. ICLR 2026NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
26. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
27. ICLR 2026RAPID$^3$: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
28. ICLR 2026Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data
29. ICLR 2026SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
30. ICLR 2026Towards a Universally Transferable Acceleration Method for Density Functional Theory
31. ICLR 2026TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
32. ICLR 2026Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
33. ICML 2026ASTRA: Communication-Efficient Acceleration for Multi-Device Transformer Inference
34. ICML 2026Attn-QAT: 4-Bit Attention With Quantization-Aware Training
35. ICML 2026Budget-Constrained Step-Level Diffusion Caching
36. ICML 2026CoCoQuant: Breaking the Bandwidth Wall via Co-Optimized Communication and Computation Quantization
37. ICML 2026Consistency Deep Equilibrium Models
38. ICML 2026DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding
39. ICML 2026FAFO: Lossy KV Cache Compression for Lossless Inference Acceleration via Draftless Fumble Decoding
40. ICML 2026FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
41. ICML 2026Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
42. ICML 2026Improving Classifier-Free Guidance of Flow Matching via Manifold Projection
43. ICML 2026Inference of Online Newton Methods with Nesterov's Accelerated Sketching
44. ICML 2026LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration
45. ICML 2026Lie-Algebraic Acceleration of Neural Koopman Dynamics
46. ICML 2026MAnchors: Memorization-Based Acceleration of Anchors via Rule Reuse and Transformation
47. ICML 2026MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model Serving
48. ICML 2026Matrix-Free GPU Semidefinite Programming for Quantum Ordered Search at the k=6 Frontier
49. ICML 2026PsumQuant: In-line Post-training Partial Sum Quantizer for Energy Efficient NPU Inference
50. ICML 2026Pushing the Limits of Block Rotations in Post-Training Quantization

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.