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 838 篇，第 14 / 17 页

651. ICLR 2024PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
652. ICLR 2024RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
653. ICLR 2024Retrieval meets Long Context Large Language Models
654. ICLR 2024RingAttention with Blockwise Transformers for Near-Infinite Context
655. ICLR 2024Robustifying State-space Models for Long Sequences via Approximate Diagonalization
656. ICLR 2024Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
657. ICLR 2024The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
658. ICLR 2024Towards Offline Opponent Modeling with In-context Learning
659. ICLR 2024Transformer-VQ: Linear-Time Transformers via Vector Quantization
660. ICLR 2024YaRN: Efficient Context Window Extension of Large Language Models
661. ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
662. ICML 2024An Information-Theoretic Analysis of In-Context Learning
663. ICML 2024Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT
664. ICML 2024Bifurcated Attention for Single-Context Large-Batch Sampling
665. ICML 2024Breaking through the learning plateaus of in-context learning in Transformer
666. ICML 2024Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling
667. ICML 2024Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks
668. ICML 2024Chasing Convex Functions with Long-term Constraints
669. ICML 2024Conditional Language Learning with Context
670. ICML 2024Data Engineering for Scaling Language Models to 128K Context
671. ICML 2024Dual Operating Modes of In-Context Learning
672. ICML 2024Efficient World Models with Context-Aware Tokenization
673. ICML 2024ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models
674. ICML 2024Emergence of In-Context Reinforcement Learning from Noise Distillation
675. ICML 2024Evaluating Quantized Large Language Models
676. ICML 2024Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers
677. ICML 2024Fast Peer Adaptation with Context-aware Exploration
678. ICML 2024Feedback Loops With Language Models Drive In-Context Reward Hacking
679. ICML 2024Generalization to New Sequential Decision Making Tasks with In-Context Learning
680. ICML 2024GistScore: Learning Better Representations for In-Context Example Selection with Gist Bottlenecks
681. ICML 2024Harnessing Hierarchical Label Distribution Variations in Test Agnostic Long-tail Recognition
682. ICML 2024How do Transformers Perform In-Context Autoregressive Learning ?
683. ICML 2024In-context Convergence of Transformers
684. ICML 2024In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
685. ICML 2024In-Context Language Learning: Architectures and Algorithms
686. ICML 2024In-Context Learning Agents Are Asymmetric Belief Updaters
687. ICML 2024In-context Learning on Function Classes Unveiled for Transformers
688. ICML 2024In-Context Principle Learning from Mistakes
689. ICML 2024In-Context Unlearning: Language Models as Few-Shot Unlearners
690. ICML 2024In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
691. ICML 2024Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
692. ICML 2024Language Models as Science Tutors
693. ICML 2024Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition
694. ICML 2024Linguistic Calibration of Long-Form Generations
695. ICML 2024LLM Maybe LongLM: SelfExtend LLM Context Window Without Tuning
696. ICML 2024LoCoCo: Dropping In Convolutions for Long Context Compression
697. ICML 2024Long Range Propagation on Continuous-Time Dynamic Graphs
698. ICML 2024Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts
699. ICML 2024LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
700. ICML 2024Loss Shaping Constraints for Long-Term Time Series Forecasting

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。