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 255 篇，第 1 / 6 页

1. CVPR 2025BIMBA: Selective-Scan Compression for Long-Range Video Question Answering
2. CVPR 2025Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs
3. CVPR 2025Context-Enhanced Memory-Refined Transformer for Online Action Detection
4. CVPR 2025Distilling Long-tailed Datasets
5. CVPR 2025Fractal Calibration for Long-tailed Object Detection
6. CVPR 2025From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
7. CVPR 2025GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding
8. CVPR 2025HOIGPT: Learning Long-Sequence Hand-Object Interaction with Language Models
9. CVPR 2025Learning from Neighbors: Category Extrapolation for Long-Tail Learning
10. CVPR 2025LOCORE: Image Re-ranking with Long-Context Sequence Modeling
11. CVPR 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
12. CVPR 2025Mimic In-Context Learning for Multimodal Tasks
13. CVPR 2025Neural Video Compression with Context Modulation
14. CVPR 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
15. CVPR 2025Precise Event Spotting in Sports Videos: Solving Long-Range Dependency and Class Imbalance
16. CVPR 2025TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
17. CVPR 2025Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images
18. ICLR 2025$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
19. ICLR 2025A Causal Lens for Learning Long-term Fair Policies
20. ICLR 2025A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
21. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
22. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
23. ICLR 2025Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
24. ICLR 2025Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
25. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
26. ICLR 2025Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
27. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
28. ICLR 2025Competition Dynamics Shape Algorithmic Phases of In-Context Learning
29. ICLR 2025Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data
30. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
31. ICLR 2025CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning
32. ICLR 2025DeciMamba: Exploring the Length Extrapolation Potential of Mamba
33. ICLR 2025Density estimation with LLMs: a geometric investigation of in-context learning trajectories
34. ICLR 2025Differential learning kinetics govern the transition from memorization to generalization during in-context learning
35. ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
36. ICLR 2025DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
37. ICLR 2025FlashMask: Efficient and Rich Mask Extension of FlashAttention
38. ICLR 2025FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
39. ICLR 2025Forgetting Transformer: Softmax Attention with a Forget Gate
40. ICLR 2025From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
41. ICLR 2025Gated Delta Networks: Improving Mamba2 with Delta Rule
42. ICLR 2025GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in Graphs
43. ICLR 2025HELMET: How to Evaluate Long-context Models Effectively and Thoroughly
44. ICLR 2025Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
45. ICLR 2025HOPE for a Robust Parameterization of Long-memory State Space Models
46. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
47. ICLR 2025ICLR: In-Context Learning of Representations
48. ICLR 2025Implicit In-context Learning
49. ICLR 2025In-context Time Series Predictor
50. ICLR 2025Inference Scaling for Long-Context Retrieval Augmented Generation

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。