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 98 篇，第 2 / 2 页

51. NeurIPS 2025MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling
52. NeurIPS 2025Multipole Attention for Efficient Long Context Reasoning
53. NeurIPS 2025MultiScale Contextual Bandits for Long Term Objectives
54. NeurIPS 2025NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables
55. NeurIPS 2025Omni-DNA: A Genomic Model Supporting Sequence Understanding, Long-context, and Textual Annotation
56. NeurIPS 2025Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse Attention
57. NeurIPS 2025PaceLLM: Brain-Inspired Large Language Models for Long-Context Understanding
58. NeurIPS 2025PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA
59. NeurIPS 2025Pre-trained Large Language Models Learn to Predict Hidden Markov Models In-context
60. NeurIPS 2025Predicting Functional Brain Connectivity with Context-Aware Deep Neural Networks
61. NeurIPS 2025Principled Long-Tailed Generative Modeling via Diffusion Models
62. NeurIPS 2025R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
63. NeurIPS 2025ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents
64. NeurIPS 2025RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval
65. NeurIPS 2025Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
66. NeurIPS 2025Revisiting Glorot Initialization for Long-Range Linear Recurrences
67. NeurIPS 2025Robust Ego-Exo Correspondence with Long-Term Memory
68. NeurIPS 2025Rope to Nope and Back Again: A New Hybrid Attention Strategy
69. NeurIPS 2025SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater
70. NeurIPS 2025Scalable In-context Ranking with Generative Models
71. NeurIPS 2025Scale-invariant attention
72. NeurIPS 2025SeerAttention: Self-distilled Attention Gating for Efficient Long-context Prefilling
73. NeurIPS 2025Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
74. NeurIPS 2025Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling
75. NeurIPS 2025SkyLadder: Better and Faster Pretraining via Context Window Scheduling
76. NeurIPS 2025StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
77. NeurIPS 2025StateSpaceDiffuser: Bringing Long Context to Diffusion World Models
78. NeurIPS 2025Streaming Attention Approximation via Discrepancy Theory
79. NeurIPS 2025Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context
80. NeurIPS 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames
81. NeurIPS 2025Theoretical Insights into In-context Learning with Unlabeled Data
82. NeurIPS 2025Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
83. NeurIPS 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
84. NeurIPS 2025Titans: Learning to Memorize at Test Time
85. NeurIPS 2025Towards Predicting Any Human Trajectory In Context
86. NeurIPS 2025Towards Provable Emergence of In-Context Reinforcement Learning
87. NeurIPS 2025Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
88. NeurIPS 2025True Zero-Shot Inference of Dynamical Systems Preserving Long-Term Statistics
89. NeurIPS 2025UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
90. NeurIPS 2025Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
91. NeurIPS 2025Unleashing Hour-Scale Video Training for Long Video-Language Understanding
92. NeurIPS 2025Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks
93. NeurIPS 2025Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation
94. NeurIPS 2025Vision-centric Token Compression in Large Language Model
95. NeurIPS 2025Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
96. NeurIPS 2025WaLRUS: Wavelets for Long range Representation Using State Space Methods
97. NeurIPS 2025WorldMem: Long-term Consistent World Simulation with Memory
98. NeurIPS 2025ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention

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。