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 87 篇，第 1 / 2 页

1. ICLR 2025$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models
2. ICLR 2025A Causal Lens for Learning Long-term Fair Policies
3. ICLR 2025A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
4. ICLR 2025A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention
5. ICLR 2025BenTo: Benchmark Reduction with In-Context Transferability
6. ICLR 2025Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
7. ICLR 2025Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
8. ICLR 2025Can In-context Learning Really Generalize to Out-of-distribution Tasks?
9. ICLR 2025Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?
10. ICLR 2025ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
11. ICLR 2025Competition Dynamics Shape Algorithmic Phases of In-Context Learning
12. ICLR 2025Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data
13. ICLR 2025Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
14. ICLR 2025CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning
15. ICLR 2025DeciMamba: Exploring the Length Extrapolation Potential of Mamba
16. ICLR 2025Density estimation with LLMs: a geometric investigation of in-context learning trajectories
17. ICLR 2025Differential learning kinetics govern the transition from memorization to generalization during in-context learning
18. ICLR 2025Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
19. ICLR 2025DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
20. ICLR 2025FlashMask: Efficient and Rich Mask Extension of FlashAttention
21. ICLR 2025FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
22. ICLR 2025Forgetting Transformer: Softmax Attention with a Forget Gate
23. ICLR 2025From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data
24. ICLR 2025Gated Delta Networks: Improving Mamba2 with Delta Rule
25. ICLR 2025GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range Dependencies in Graphs
26. ICLR 2025HELMET: How to Evaluate Long-context Models Effectively and Thoroughly
27. ICLR 2025Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data
28. ICLR 2025HOPE for a Robust Parameterization of Long-memory State Space Models
29. ICLR 2025Human-inspired Episodic Memory for Infinite Context LLMs
30. ICLR 2025ICLR: In-Context Learning of Representations
31. ICLR 2025Implicit In-context Learning
32. ICLR 2025In-context Time Series Predictor
33. ICLR 2025Inference Scaling for Long-Context Retrieval Augmented Generation
34. ICLR 2025Is In-Context Learning Sufficient for Instruction Following in LLMs?
35. ICLR 2025Learning Long Range Dependencies on Graphs via Random Walks
36. ICLR 2025Learning Randomized Algorithms with Transformers
37. ICLR 2025Long Context Compression with Activation Beacon
38. ICLR 2025Long-Context Linear System Identification
39. ICLR 2025Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
40. ICLR 2025Long-tailed Adversarial Training with Self-Distillation
41. ICLR 2025Long-time asymptotics of noisy SVGD outside the population limit
42. ICLR 2025LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs
43. ICLR 2025LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement
44. ICLR 2025LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization
45. ICLR 2025LongVILA: Scaling Long-Context Visual Language Models for Long Videos
46. ICLR 2025LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
47. ICLR 2025MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
48. ICLR 2025MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
49. ICLR 2025MELODI: Exploring Memory Compression for Long Contexts
50. ICLR 2025Metalic: Meta-Learning In-Context with Protein 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。