开放域问答论文趋势 2023–2026

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。

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 36 篇，第 1 / 1 页

1. ICLR 2026Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
2. ICLR 2026Estimating Worst-Case Frontier Risks of Open-Weight LLMs
3. ICLR 2026Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
4. ICLR 2026Helix: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving
5. ICLR 2026LeRobot: An Open-Source Library for End-to-End Robot Learning
6. ICLR 2026PRISM: Progressive Robust Learning for Open-World Continual Category Discovery
7. ICLR 2026SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
8. ICLR 2025ACES: Automatic Cohort Extraction System for Event-Stream Datasets
9. ICLR 2025Do Deep Neural Network Solutions Form a Star Domain?
10. ICLR 2025FreDF: Learning to Forecast in the Frequency Domain
11. ICLR 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
12. ICLR 2025OLMoE: Open Mixture-of-Experts Language Models
13. ICLR 2025On the Performance Analysis of Momentum Method: A Frequency Domain Perspective
14. ICLR 2025OpenHands: An Open Platform for AI Software Developers as Generalist Agents
15. ICLR 2025OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
16. ICLR 2025Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
17. ICLR 2025Re-evaluating Open-ended Evaluation of Large Language Models
18. ICLR 2025Towards Domain Adaptive Neural Contextual Bandits
19. ICLR 2025YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus
20. ICLR 2024BatteryML: An Open-source Platform for Machine Learning on Battery Degradation
21. ICLR 2024Domain constraints improve risk prediction when outcome data is missing
22. ICLR 2024DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
23. ICLR 2024EasyTPP: Towards Open Benchmarking Temporal Point Processes
24. ICLR 2024Improving Domain Generalization with Domain Relations
25. ICLR 2024Minimum width for universal approximation using ReLU networks on compact domain
26. ICLR 2024OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
27. ICLR 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs
28. ICLR 2024Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
29. ICLR 2023Domain Generalization via Heckman-type Selection Models
30. ICLR 2023Generate rather than Retrieve: Large Language Models are Strong Context Generators
31. ICLR 2023GLM-130B: An Open Bilingual Pre-trained Model
32. ICLR 2023Learning Domain-Agnostic Representation for Disease Diagnosis
33. ICLR 2023Learning Object-Language Alignments for Open-Vocabulary Object Detection
34. ICLR 2023Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions
35. ICLR 2023SIMPLE: Specialized Model-Sample Matching for Domain Generalization
36. ICLR 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition

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。