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 176 篇，第 4 / 4 页

151. NeurIPS 2024LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
152. NeurIPS 2024Make Your LLM Fully Utilize the Context
153. NeurIPS 2024MambaLRP: Explaining Selective State Space Sequence Models
154. NeurIPS 2024Many-Shot In-Context Learning
155. NeurIPS 2024Many-shot Jailbreaking
156. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
157. NeurIPS 2024MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
158. NeurIPS 2024Mini-Sequence Transformers: Optimizing Intermediate Memory for Long Sequences Training
159. NeurIPS 2024Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
160. NeurIPS 2024MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
161. NeurIPS 2024Needle In A Multimodal Haystack
162. NeurIPS 2024Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
163. NeurIPS 2024One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
164. NeurIPS 2024Opponent Modeling with In-context Search
165. NeurIPS 2024Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
166. NeurIPS 2024Probing the Decision Boundaries of In-context Learning in Large Language Models
167. NeurIPS 2024Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
168. NeurIPS 2024Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
169. NeurIPS 2024Selective Attention: Enhancing Transformer through Principled Context Control
170. NeurIPS 2024StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
171. NeurIPS 2024Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
172. NeurIPS 2024The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
173. NeurIPS 2024The GAN is dead; long live the GAN! A Modern GAN Baseline
174. NeurIPS 2024Transformers are Minimax Optimal Nonparametric In-Context Learners
175. NeurIPS 2024Universal In-Context Approximation By Prompting Fully Recurrent Models
176. NeurIPS 2024xLSTM: Extended Long Short-Term Memory

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。