端侧推理论文趋势 2023–2026
移动端部署
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 55 篇被归入该主题的论文。
主要结论
- 端侧推理论文从 2023 年的 7 篇增长到 2026 年的 28 篇，三年间扩大到约 4.0 倍。
- NeurIPS 是发端侧推理论文最多的会议，2023–2026 年共 21 篇，占四个会议总量的 38%。
- 交叉方向里涨得最快的是联邦边缘推理：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 15 篇。
- 在「硬件与编译」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的芯片设计 ML是 2.3 倍，端侧推理是 4.0 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 1 | 3 | 2 | 1 | 7 |
| 2024 | 3 | 0 | 0 | 3 | 6 |
| 2025 | 7 | 2 | 3 | 2 | 14 |
| 2026 | 10 | 3 | 9 | 6 | 28 |
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 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
- ICML 2026Faster Activation Functions at the Edge for Post-Training Speedups
- ICLR 2026Neural Graduated Assignment for Maximum Common Edge Subgraphs
- CVPR 2026E2-SCI Elastic Edge-Cloud Speculative Decoding via Credit Inertia
- NeurIPS 2025CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
- ICML 2025Edge-Colored Clustering in Hypergraphs: Beyond Minimizing Unsatisfied Edges
- ICLR 2025Grokking at the Edge of Numerical Stability
- CVPR 2025QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
- NeurIPS 2024Stepping on the Edge: Curvature Aware Learning Rate Tuners
- CVPR 20243D Neural Edge Reconstruction
- NeurIPS 2023From Trainable Negative Depth to Edge Heterophily in Graphs
- ICML 2023Second-order regression models exhibit progressive sharpening to the edge of stability
- ICLR 2023Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
- CVPR 2023The Treasure Beneath Multiple Annotations: An Uncertainty-Aware Edge Detector
- NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
- ICML 2026PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
- ICLR 2026Tequila: Deadzone-free Ternary Quantization for Large Language Models
- CVPR 2026Edge-Focused Super-Resolution for Omnidirectional Images with Spherical Geometric Augmentation
- NeurIPS 2025Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse
- ICML 2025Towards characterizing the value of edge embeddings in Graph Neural Networks
全部端侧推理论文
共 21 篇，第 1 / 1 页
- NeurIPS 2026Computer Use at the Edge of the Statistical Precipice
- NeurIPS 2026Does Sparse Connectivity Improve Generalization? Convolutional Networks Below the Edge of Stability
- NeurIPS 2026EAT: Eviction-Aware Training for Long-Context LLM Inference on Edge Devices
- NeurIPS 2026Edge of Stability Selectively Shapes Learning Across the Data Distribution
- NeurIPS 2026Edge of Stochastic Stability: Revisiting the Edge of Stability for SGD
- NeurIPS 2026Generalization at the Edge of Stability
- NeurIPS 2026Geometry-Constrained Kolmogorov–Arnold Networks: Learning Edge Geometry via Banach Duality
- NeurIPS 2026MedPsy: State‑of‑the‑Art Small Medical Language Models for Efficient Edge Deployment
- NeurIPS 2026MoE-SpAc: Efficient MoE Inference Based on Speculative Activation Utility in Heterogeneous Edge Scenario
- NeurIPS 2026SGD at the Edge of Stability: The Stochastic Sharpness Gap
- NeurIPS 2025CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction
- NeurIPS 2025CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
- NeurIPS 2025On the Edge of Memorization in Diffusion Models
- NeurIPS 2025Sim-LLM: Optimizing LLM Inference at the Edge through Inter-Task KV Reuse
- NeurIPS 2025Structure-Aware Spectral Sparsification via Uniform Edge Sampling
- NeurIPS 2025Transfer Learning on Edge Connecting Probability Estimation Under Graphon Model
- NeurIPS 2025Variational Learning Finds Flatter Solutions at the Edge of Stability
- NeurIPS 2024Finding Transformer Circuits With Edge Pruning
- NeurIPS 2024Stepping on the Edge: Curvature Aware Learning Rate Tuners
- NeurIPS 2024The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
- NeurIPS 2023From Trainable Negative Depth to Edge Heterophily in Graphs
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查端侧推理在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "edge-inference"}
常见问题
- 2023–2026 年四大会议一共有多少篇端侧推理论文？
- 共 55 篇，按年份分别是 2023 年 7 篇、2024 年 6 篇、2025 年 14 篇、2026 年 28 篇。
- NeurIPS 2026 有多少篇端侧推理论文？
- NeurIPS 2026 有 10 篇端侧推理论文，上一届是 7 篇。
- ICLR 2026 有多少篇端侧推理论文？
- ICLR 2026 有 3 篇端侧推理论文，上一届是 2 篇。
- ICML 2026 有多少篇端侧推理论文？
- ICML 2026 有 9 篇端侧推理论文，上一届是 3 篇。
- CVPR 2026 有多少篇端侧推理论文？
- CVPR 2026 有 6 篇端侧推理论文，上一届是 2 篇。
- 哪个会议的端侧推理论文最多？
- NeurIPS，2023–2026 年共 21 篇。