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 43 篇，第 1 / 1 页

1. ICLR 2024A Benchmark for Learning to Translate a New Language from One Grammar Book
2. ICLR 2024AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
3. ICLR 2024AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
4. ICLR 2024BooookScore: A systematic exploration of book-length summarization in the era of LLMs
5. ICLR 2024CausalLM is not optimal for in-context learning
6. ICLR 2024CLEX: Continuous Length Extrapolation for Large Language Models
7. ICLR 2024Compressed Context Memory for Online Language Model Interaction
8. ICLR 2024Context is Environment
9. ICLR 2024Context-Aware Meta-Learning
10. ICLR 2024Equivariant Matrix Function Neural Networks
11. ICLR 2024FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
12. ICLR 2024FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
13. ICLR 2024Function Vectors in Large Language Models
14. ICLR 2024Functional Interpolation for Relative Positions improves Long Context Transformers
15. ICLR 2024Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
16. ICLR 2024How do Language Models Bind Entities in Context?
17. ICLR 2024HyperAttention: Long-context Attention in Near-Linear Time
18. ICLR 2024IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
19. ICLR 2024IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
20. ICLR 2024In-context Autoencoder for Context Compression in a Large Language Model
21. ICLR 2024In-Context Learning Learns Label Relationships but Is Not Conventional Learning
22. ICLR 2024In-Context Learning through the Bayesian Prism
23. ICLR 2024In-Context Pretraining: Language Modeling Beyond Document Boundaries
24. ICLR 2024Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability
25. ICLR 2024Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
26. ICLR 2024Language Modeling Is Compression
27. ICLR 2024Long-tailed Diffusion Models with Oriented Calibration
28. ICLR 2024LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
29. ICLR 2024Looped Transformers are Better at Learning Learning Algorithms
30. ICLR 2024MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
31. ICLR 2024Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
32. ICLR 2024One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
33. ICLR 2024Periodicity Decoupling Framework for Long-term Series Forecasting
34. ICLR 2024PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
35. ICLR 2024RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
36. ICLR 2024Retrieval meets Long Context Large Language Models
37. ICLR 2024RingAttention with Blockwise Transformers for Near-Infinite Context
38. ICLR 2024Robustifying State-space Models for Long Sequences via Approximate Diagonalization
39. ICLR 2024Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
40. ICLR 2024The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
41. ICLR 2024Towards Offline Opponent Modeling with In-context Learning
42. ICLR 2024Transformer-VQ: Linear-Time Transformers via Vector Quantization
43. ICLR 2024YaRN: Efficient Context Window Extension of Large Language 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。