开放域问答论文趋势 2023–2026
开放问答
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 244 篇被归入该主题的论文。
主要结论
- 开放域问答论文从 2023 年的 52 篇增长到 2026 年的 62 篇，三年间扩大到约 1.2 倍。
- CVPR 是发开放域问答论文最多的会议，2023–2026 年共 113 篇，占四个会议总量的 46%。
- 交叉方向里涨得最快的是驾驶仿真：同时属于两个主题的论文从 2023 年的 2 篇增至 2026 年的 9 篇。
- 在「信息检索」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的交叉编码重排是 3.0 倍，开放域问答是 1.2 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 14 | 8 | 5 | 25 | 52 |
| 2024 | 15 | 9 | 14 | 23 | 61 |
| 2025 | 21 | 12 | 2 | 34 | 69 |
| 2026 | 19 | 7 | 5 | 31 | 62 |
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 2026Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
- ICML 2026HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning
- ICLR 2026PRISM: Progressive Robust Learning for Open-World Continual Category Discovery
- CVPR 2026Enhancing Part-Level Point Grounding for Any Open-Source MLLMs
- NeurIPS 2025Continuous Domain Generalization
- ICML 2025COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
- ICLR 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
- CVPR 2025Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization
- NeurIPS 2024GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
- ICML 2024DOGE: Domain Reweighting with Generalization Estimation
- ICLR 2024Domain constraints improve risk prediction when outcome data is missing
- CVPR 2024Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain
- NeurIPS 2023ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram
- ICML 2023Internet Explorer: Targeted Representation Learning on the Open Web
- ICLR 2023Domain Generalization via Heckman-type Selection Models
- CVPR 2023AutoLabel: CLIP-Based Framework for Open-Set Video Domain Adaptation
- NeurIPS 2026CompleteRXN: Toward Completing Open Chemical Reaction Databases
- ICML 2026Names Don’t Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning
- ICLR 2026LeRobot: An Open-Source Library for End-to-End Robot Learning
- CVPR 2026From Indoor to Open World Revealing the Spatial Reasoning Gap
全部开放域问答论文
共 19 篇，第 1 / 1 页
- NeurIPS 2026A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
- NeurIPS 2026Better Language Models Require Better Domain-Specific Inductive Biases
- NeurIPS 2026Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
- NeurIPS 2026Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
- NeurIPS 2026CompleteRXN: Toward Completing Open Chemical Reaction Databases
- NeurIPS 2026Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains
- NeurIPS 2026Efficient Multi-Source Prompt Adaptation for Cross-Domain Open-Vocabulary Learning
- NeurIPS 2026EgoSurgHands: An Egocentric 3D Hand Pose Dataset & Benchmark for Open-Surgery Training
- NeurIPS 2026FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
- NeurIPS 2026LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection
- NeurIPS 2026Open Vocabulary Domain Unlearning
- NeurIPS 2026PRISM: Priority-Guided Scanning in the Wavelet Domain for UAV Maritime Small Object Detection
- NeurIPS 2026Query as a Resource: Activity-Cost Guided Remote Sensing Domain-Incremental Object Detection
- NeurIPS 2026Re:Cognize - A Framework For Open-Set Comic Character Re-Identification
- NeurIPS 2026ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
- NeurIPS 2026SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
- NeurIPS 2026The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
- NeurIPS 2026Too Smart to Teach: The Articulability Ceiling in Language Models
- NeurIPS 2026Witness Overlap: Directional Provenance Inside Open-Weight Model Families
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查开放域问答在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "open-domain-qa"}
常见问题
- 2023–2026 年四大会议一共有多少篇开放域问答论文？
- 共 244 篇，按年份分别是 2023 年 52 篇、2024 年 61 篇、2025 年 69 篇、2026 年 62 篇。
- NeurIPS 2026 有多少篇开放域问答论文？
- NeurIPS 2026 有 19 篇开放域问答论文，上一届是 21 篇。
- ICLR 2026 有多少篇开放域问答论文？
- ICLR 2026 有 7 篇开放域问答论文，上一届是 12 篇。
- ICML 2026 有多少篇开放域问答论文？
- ICML 2026 有 5 篇开放域问答论文，上一届是 2 篇。
- CVPR 2026 有多少篇开放域问答论文？
- CVPR 2026 有 31 篇开放域问答论文，上一届是 34 篇。
- 哪个会议的开放域问答论文最多？
- CVPR，2023–2026 年共 113 篇。