推理加速论文趋势 2023–2026

主要结论

• 推理加速论文从 2023 年的 54 篇增长到 2026 年的 91 篇，三年间扩大到约 1.7 倍。
• NeurIPS 是发推理加速论文最多的会议，2023–2026 年共 90 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是深度学习 · large language models：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 9 篇。
• 在「效率与系统」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的硬件协同是 4.4 倍，推理加速是 1.7 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部推理加速论文

共 48 篇，第 1 / 1 页

1. ICLR 2026BBQ: Boosting Quantization Entropy with Bell Box Quantization
2. ICLR 2026Corner Gradient Descent
3. ICLR 2026Dataset Distillation as Pushforward Optimal Quantization
4. ICLR 2026DiCache: Let Diffusion Model Determine Its Own Cache
5. ICLR 2026Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
6. ICLR 2026Distributionally Robust Linear Regression with Block Lewis Weights
7. ICLR 2026Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
8. ICLR 2026Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
9. ICLR 2026GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
10. ICLR 2026NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference
11. ICLR 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Framework
12. ICLR 2026RAPID$^3$: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
13. ICLR 2026Score Distillation Beyond Acceleration: Generative Modeling from Corrupted Data
14. ICLR 2026SGD with Adaptive Preconditioning: Unified Analysis and Momentum Acceleration
15. ICLR 2026Towards a Universally Transferable Acceleration Method for Density Functional Theory
16. ICLR 2026TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate
17. ICLR 2026Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
18. ICLR 2025Effective Interplay between Sparsity and Quantization: From Theory to Practice
19. ICLR 2025Elucidating the Preconditioning in Consistency Distillation
20. ICLR 2025Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity
21. ICLR 2025Model Equality Testing: Which Model is this API Serving?
22. ICLR 2025Nesterov acceleration in benignly non-convex landscapes
23. ICLR 2025One Step Diffusion via Shortcut Models
24. ICLR 2025Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
25. ICLR 2025PALMBENCH: A COMPREHENSIVE BENCHMARK OF COMPRESSED LARGE LANGUAGE MODELS ON MOBILE PLATFORMS
26. ICLR 2025PEARL: Parallel Speculative Decoding with Adaptive Draft Length
27. ICLR 2025PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores
28. ICLR 2025Progressive distillation induces an implicit curriculum
29. ICLR 2025Quamba: A Post-Training Quantization Recipe for Selective State Space Models
30. ICLR 2025Restructuring Vector Quantization with the Rotation Trick
31. ICLR 2025RTop-K: Ultra-Fast Row-Wise Top-K Selection for Neural Network Acceleration on GPUs
32. ICLR 2025SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
33. ICLR 2025Scaling FP8 training to trillion-token LLMs
34. ICLR 2025SGD with memory: fundamental properties and stochastic acceleration
35. ICLR 2025SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models
36. ICLR 2024Embarrassingly Simple Dataset Distillation
37. ICLR 2024InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
38. ICLR 2023Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats
39. ICLR 2023Bit-Pruning: A Sparse Multiplication-Less Dot-Product
40. ICLR 2023Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization
41. ICLR 2023EVC: Towards Real-Time Neural Image Compression with Mask Decay
42. ICLR 2023Masked Distillation with Receptive Tokens
43. ICLR 2023Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
44. ICLR 2023MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
45. ICLR 2023On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration
46. ICLR 2023PowerQuant: Automorphism Search for Non-Uniform Quantization
47. ICLR 2023Scaffolding a Student to Instill Knowledge
48. ICLR 2023Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms

常见问题

2023–2026 年四大会议一共有多少篇推理加速论文？

共 259 篇，按年份分别是 2023 年 54 篇、2024 年 50 篇、2025 年 64 篇、2026 年 91 篇。

NeurIPS 2026 有多少篇推理加速论文？

NeurIPS 2026 有 33 篇推理加速论文，上一届是 15 篇。

ICLR 2026 有多少篇推理加速论文？

ICLR 2026 有 17 篇推理加速论文，上一届是 18 篇。

ICML 2026 有多少篇推理加速论文？

ICML 2026 有 26 篇推理加速论文，上一届是 22 篇。

CVPR 2026 有多少篇推理加速论文？

CVPR 2026 有 15 篇推理加速论文，上一届是 9 篇。

哪个会议的推理加速论文最多？

NeurIPS，2023–2026 年共 90 篇。