流式推理论文趋势 2023–2026
在线流处理
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 90 篇被归入该主题的论文。
主要结论
- 流式推理论文从 2023 年的 13 篇增长到 2026 年的 41 篇，三年间扩大到约 3.2 倍。
- NeurIPS 是发流式推理论文最多的会议，2023–2026 年共 35 篇，占四个会议总量的 39%。
- 交叉方向里涨得最快的是三维视觉：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 10 篇。
- 在「边缘与物联网」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的传感融合是 3.8 倍，流式推理是 3.2 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 5 | 3 | 4 | 1 | 13 |
| 2024 | 7 | 1 | 6 | 5 | 19 |
| 2025 | 8 | 2 | 4 | 3 | 17 |
| 2026 | 15 | 1 | 10 | 15 | 41 |
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 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
- ICML 2026Estimating Correlation Clustering Cost in Node-Arrival Stream
- ICLR 2026Near-Optimal Online Deployment and Routing for Streaming LLMs
- CVPR 2026Color When It Counts Grayscale-Guided Online Triggering for Always-On Streaming
- NeurIPS 2025Learning-Augmented Streaming Algorithms for Correlation Clustering
- ICML 2025Deep Streaming View Clustering
- ICLR 2025Learning-Augmented Frequent Directions
- CVPR 2025Learning from Streaming Video with Orthogonal Gradients
- NeurIPS 2024Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
- ICML 2024Fast White-Box Adversarial Streaming Without a Random Oracle
- ICLR 2024Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
- CVPR 2024Streaming Dense Video Captioning
- NeurIPS 2023Streaming PCA for Markovian Data
- ICML 2023Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
- ICLR 2023Continual Transformers: Redundancy-Free Attention for Online Inference
- CVPR 2023System-Status-Aware Adaptive Network for Online Streaming Video Understanding
- NeurIPS 2026QueryStop: Dynamic Stop Signals for Efficient Streaming Inference
- ICML 2026SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts
- CVPR 2026Event Stream Filtering via Probability Flux Estimation
- NeurIPS 2025Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion
全部流式推理论文
共 24 篇，第 1 / 1 页
- CVPR 20263D Gaussian Splatting from Unposed Spike Stream
- CVPR 2026Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
- CVPR 2026Color When It Counts Grayscale-Guided Online Triggering for Always-On Streaming
- CVPR 2026DetAny4D Detect Anything 4D Temporally in a Streaming RGB Video
- CVPR 2026Dynamic Momentum Recalibration in Online Gradient Learning
- CVPR 2026Event Stream Filtering via Probability Flux Estimation
- CVPR 2026LASER Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
- CVPR 2026Learning to See through Illumination Extremes with Event Streaming in
- CVPR 2026LongStream Long-Sequence Streaming Autoregressive Visual Geometry
- CVPR 2026STAC Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
- CVPR 2026Streaming Video Instruction Tuning
- CVPR 2026StreamingTOM Streaming Token Compression for Efficient Video Understanding
- CVPR 2026StreamVLO Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
- CVPR 2026Towards Streaming Referring Video Segmentation via Large Language Model
- CVPR 2026WeaveTime Streaming from Earlier Frames into Emergent Memory in VideoLLMs
- CVPR 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting
- CVPR 2025Learning from Streaming Video with Orthogonal Gradients
- CVPR 2025VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network
- CVPR 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos
- CVPR 2024Low-Latency Neural Stereo Streaming
- CVPR 2024SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream
- CVPR 2024Streaming Dense Video Captioning
- CVPR 2024VideoLLM-online: Online Video Large Language Model for Streaming Video
- CVPR 2023System-Status-Aware Adaptive Network for Online Streaming Video Understanding
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 查流式推理在 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": "streaming-inference"}
常见问题
- 2023–2026 年四大会议一共有多少篇流式推理论文？
- 共 90 篇，按年份分别是 2023 年 13 篇、2024 年 19 篇、2025 年 17 篇、2026 年 41 篇。
- NeurIPS 2026 有多少篇流式推理论文？
- NeurIPS 2026 有 15 篇流式推理论文，上一届是 8 篇。
- ICLR 2026 有多少篇流式推理论文？
- ICLR 2026 有 1 篇流式推理论文，上一届是 2 篇。
- ICML 2026 有多少篇流式推理论文？
- ICML 2026 有 10 篇流式推理论文，上一届是 4 篇。
- CVPR 2026 有多少篇流式推理论文？
- CVPR 2026 有 15 篇流式推理论文，上一届是 3 篇。
- 哪个会议的流式推理论文最多？
- NeurIPS，2023–2026 年共 35 篇。