长上下文论文趋势 2023–2026

主要结论

• 长上下文论文从 2023 年的 66 篇增长到 2026 年的 341 篇，三年间扩大到约 5.2 倍。
• NeurIPS 是发长上下文论文最多的会议，2023–2026 年共 298 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是AI 智能体：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 45 篇。
• 在「长上下文与记忆」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的检索记忆是 6.6 倍，长上下文是 5.2 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 2026Accelerating Long-Context LLM Prefill via Layer-wise Progressive Token Pruning in Local Deployment
• ICML 2026AdaSplash-2: Faster Differentiable Sparse Attention
• ICLR 2026An evolutionary perspective on modes of learning in Transformers
• CVPR 2026AR2-4FV Anchored Referring and Re-identification for Long-Term Grounding in Fixed-View
• NeurIPS 2025A Controllable Examination for Long-Context Language Models
• ICML 2025CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration
• ICLR 2025$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
• CVPR 2025BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
• NeurIPS 2024[Re] CUDA: Curriculum of Data Augmentation for Long‐tailed Recognition
• ICML 2024Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
• ICLR 2024CLEX: Continuous Length Extrapolation for Large Language Models
• CVPR 2024GigaTraj: Predicting Long-term Trajectories of Hundreds of Pedestrians in Gigapixel Complex Scenes
• NeurIPS 2023A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation
• ICML 2023CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
• ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
• CVPR 2023AutoAD: Movie Description in Context
• NeurIPS 2026AdaCal: Adaptive Calibration for Robust Sparse Attention in Long-Context LLMs
• ICML 2026Artificial Hippocampus Networks for Efficient Long-Context Modeling
• ICLR 2026AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism
• CVPR 2026AstraNav-Memory Contexts Compression for Long Memory

全部长上下文论文

共 66 篇，第 1 / 2 页

1. CVPR 2023AutoAD: Movie Description in Context
2. CVPR 2023Balancing Logit Variation for Long-Tailed Semantic Segmentation
3. CVPR 2023Context De-Confounded Emotion Recognition
4. CVPR 2023Curvature-Balanced Feature Manifold Learning for Long-Tailed Classification
5. CVPR 2023Images Speak in Images: A Generalist Painter for In-Context Visual Learning
6. CVPR 2023Leveraging Temporal Context in Low Representational Power Regimes
7. CVPR 2023Long-Term Visual Localization With Mobile Sensors
8. CVPR 2023LSTFE-Net:Long Short-Term Feature Enhancement Network for Video Small Object Detection
9. CVPR 2023MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition
10. CVPR 2023No One Left Behind: Improving the Worst Categories in Long-Tailed Learning
11. CVPR 2023Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective
12. CVPR 2023Selective Structured State-Spaces for Long-Form Video Understanding
13. CVPR 2023Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers
14. CVPR 2023Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need
15. CVPR 2023Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark
16. ICLR 2023$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
17. ICLR 2023Artificial Neuronal Ensembles with Learned Context Dependent Gating
18. ICLR 2023CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
19. ICLR 2023Decoupled Training for Long-Tailed Classification With Stochastic Representations
20. ICLR 2023Delving into Semantic Scale Imbalance
21. ICLR 2023Evaluating Long-Term Memory in 3D Mazes
22. ICLR 2023Generate rather than Retrieve: Large Language Models are Strong Context Generators
23. ICLR 2023In-context Reinforcement Learning with Algorithm Distillation
24. ICLR 2023Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models
25. ICLR 2023Long Range Language Modeling via Gated State Spaces
26. ICLR 2023Long-Tailed Learning Requires Feature Learning
27. ICLR 2023Long-Tailed Partial Label Learning via Dynamic Rebalancing
28. ICLR 2023MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting
29. ICLR 2023On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning.
30. ICLR 2023Simplified State Space Layers for Sequence Modeling
31. ICLR 2023Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors
32. ICLR 2023What learning algorithm is in-context learning? Investigations with linear models
33. ICLR 2023What Makes Convolutional Models Great on Long Sequence Modeling?
34. ICML 2023A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
35. ICML 2023CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
36. ICML 2023Context Consistency Regularization for Label Sparsity in Time Series
37. ICML 2023Controlled Differential Equations on Long Sequences via Non-standard Wavelets
38. ICML 2023DevFormer: A Symmetric Transformer for Context-Aware Device Placement
39. ICML 2023FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
40. ICML 2023Global Context Vision Transformers
41. ICML 2023Large Language Models Struggle to Learn Long-Tail Knowledge
42. ICML 2023Long Horizon Temperature Scaling
43. ICML 2023Long-Term Rhythmic Video Soundtracker
44. ICML 2023LongCoder: A Long-Range Pre-trained Language Model for Code Completion
45. ICML 2023Resurrecting Recurrent Neural Networks for Long Sequences
46. ICML 2023Robust Situational Reinforcement Learning in Face of Context Disturbances
47. ICML 2023Simple Hardware-Efficient Long Convolutions for Sequence Modeling
48. ICML 2023Transformers Learn In-Context by Gradient Descent
49. NeurIPS 2023A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation
50. NeurIPS 2023Blockwise Parallel Transformers for Large Context Models

常见问题

2023–2026 年四大会议一共有多少篇长上下文论文？

共 838 篇，按年份分别是 2023 年 66 篇、2024 年 176 篇、2025 年 255 篇、2026 年 341 篇。

NeurIPS 2026 有多少篇长上下文论文？

NeurIPS 2026 有 130 篇长上下文论文，上一届是 98 篇。

ICLR 2026 有多少篇长上下文论文？

ICLR 2026 有 82 篇长上下文论文，上一届是 87 篇。

ICML 2026 有多少篇长上下文论文？

ICML 2026 有 98 篇长上下文论文，上一届是 53 篇。

CVPR 2026 有多少篇长上下文论文？

CVPR 2026 有 31 篇长上下文论文，上一届是 17 篇。

哪个会议的长上下文论文最多？

NeurIPS，2023–2026 年共 298 篇。