流式推理论文趋势 2023–2026

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。

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 90 篇，第 1 / 2 页

1. CVPR 20263D Gaussian Splatting from Unposed Spike Stream
2. CVPR 2026Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
3. CVPR 2026Color When It Counts Grayscale-Guided Online Triggering for Always-On Streaming
4. CVPR 2026DetAny4D Detect Anything 4D Temporally in a Streaming RGB Video
5. CVPR 2026Dynamic Momentum Recalibration in Online Gradient Learning
6. CVPR 2026Event Stream Filtering via Probability Flux Estimation
7. CVPR 2026LASER Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstruction
8. CVPR 2026Learning to See through Illumination Extremes with Event Streaming in
9. CVPR 2026LongStream Long-Sequence Streaming Autoregressive Visual Geometry
10. CVPR 2026STAC Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction
11. CVPR 2026Streaming Video Instruction Tuning
12. CVPR 2026StreamingTOM Streaming Token Compression for Efficient Video Understanding
13. CVPR 2026StreamVLO Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
14. CVPR 2026Towards Streaming Referring Video Segmentation via Large Language Model
15. CVPR 2026WeaveTime Streaming from Earlier Frames into Emergent Memory in VideoLLMs
16. ICLR 2026Near-Optimal Online Deployment and Routing for Streaming LLMs
17. ICML 2026Estimating Correlation Clustering Cost in Node-Arrival Stream
18. ICML 2026Incremental Transformer Neural Processes
19. ICML 2026Intentional Updates for Streaming Reinforcement Learning
20. ICML 2026NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels
21. ICML 2026Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits
22. ICML 2026ProactiveLLM: Learning Active Interaction for Streaming Large Language Models
23. ICML 2026SFedPO: Streaming Federated Learning with a Prediction Oracle under Temporal Shifts
24. ICML 2026Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning
25. ICML 2026Streaming Covariate Balancing via Discrepancy-Based Feature Coresets
26. ICML 2026Streaming Sliced Optimal Transport
27. NeurIPS 2026Dynamics of the Transformer Residual Stream: Coupling Spectral Geometry to Network Topology
28. NeurIPS 2026FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry
29. NeurIPS 2026GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction
30. NeurIPS 2026HIST3R: Rectified State Decomposition from History for Streaming 3D Reconstruction
31. NeurIPS 2026IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
32. NeurIPS 2026Inference and Uncertainty Quantification for Streaming $r$-PCA
33. NeurIPS 2026MIST: Reliable Streaming Decision Trees for Online Class-Incremental Learning via McDiarmid Bound
34. NeurIPS 2026Online Directional Regression for Streaming Sufficient Dimension Reduction
35. NeurIPS 2026PF-SGS: Pose-Free Streaming 3D Gaussian Splatting for Large-Scale Scene Reconstruction
36. NeurIPS 2026QueryStop: Dynamic Stop Signals for Efficient Streaming Inference
37. NeurIPS 2026SoccerNarrate: Event-Grounded Streaming Soccer Commentary with Macro-Window Preference Alignment
38. NeurIPS 2026Stable3R: Streaming 3D Reconstruction with Stable Geometric References
39. NeurIPS 2026Streaming Interventions: Can Video LLMs Correct Mistakes as They Occur?
40. NeurIPS 2026StreamPhy: Streaming Inference of High-Dimensional Physical Dynamics via State Space Models
41. NeurIPS 2026What Should a Streaming Video Model Remember?
42. CVPR 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting
43. CVPR 2025Learning from Streaming Video with Orthogonal Gradients
44. CVPR 2025VISTREAM: Improving Computation Efficiency of Visual Streaming Perception via Law-of-Charge-Conservation Inspired Spiking Neural Network
45. ICLR 2025Learning-Augmented Frequent Directions
46. ICLR 2025Streaming Algorithms For $\ell_p$ Flows and $\ell_p$ Regression
47. ICML 2025A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing
48. ICML 2025Deep Streaming View Clustering
49. ICML 2025SEAD: Unsupervised Ensemble of Streaming Anomaly Detectors
50. ICML 2025SHE: Streaming-media Hashing Retrieval

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。