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 244 篇，第 3 / 5 页

101. ICLR 2025OLMoE: Open Mixture-of-Experts Language Models
102. ICLR 2025On the Performance Analysis of Momentum Method: A Frequency Domain Perspective
103. ICLR 2025OpenHands: An Open Platform for AI Software Developers as Generalist Agents
104. ICLR 2025OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
105. ICLR 2025Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
106. ICLR 2025Re-evaluating Open-ended Evaluation of Large Language Models
107. ICLR 2025Towards Domain Adaptive Neural Contextual Bandits
108. ICLR 2025YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus
109. ICML 2025COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation
110. ICML 2025Heterogeneous Label Shift: Theory and Algorithm
111. NeurIPS 2025A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
112. NeurIPS 2025AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
113. NeurIPS 2025Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
114. NeurIPS 2025Continuous Domain Generalization
115. NeurIPS 2025Diffusion Transformers as Open-World Spatiotemporal Foundation Models
116. NeurIPS 2025DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
117. NeurIPS 2025DOVTrack: Data-Efficient Open-Vocabulary Tracking
118. NeurIPS 2025FlexOLMo: Open Language Models for Flexible Data Use
119. NeurIPS 2025Gains: Fine-grained Federated Domain Adaptation in Open Set
120. NeurIPS 2025HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
121. NeurIPS 2025How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
122. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
123. NeurIPS 2025Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models
124. NeurIPS 2025Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation
125. NeurIPS 2025MergeBench: A Benchmark for Merging Domain-Specialized LLMs
126. NeurIPS 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
127. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
128. NeurIPS 2025Open-World Drone Active Tracking with Goal-Centered Rewards
129. NeurIPS 2025RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
130. NeurIPS 2025Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
131. NeurIPS 2025UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models
132. CVPR 2024A2XP: Towards Private Domain Generalization
133. CVPR 2024AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning
134. CVPR 2024CommonCanvas: Open Diffusion Models Trained on Creative-Commons Images
135. CVPR 2024Day-Night Cross-domain Vehicle Re-identification
136. CVPR 2024Domain Prompt Learning with Quaternion Networks
137. CVPR 2024Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain
138. CVPR 2024From Coarse to Fine-Grained Open-Set Recognition
139. CVPR 2024GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields
140. CVPR 2024Learning for Transductive Threshold Calibration in Open-World Recognition
141. CVPR 2024Open-Set Domain Adaptation for Semantic Segmentation
142. CVPR 2024Open-Vocabulary Segmentation with Semantic-Assisted Calibration
143. CVPR 2024Open-World Semantic Segmentation Including Class Similarity
144. CVPR 2024OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies
145. CVPR 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
146. CVPR 2024ProTeCt: Prompt Tuning for Taxonomic Open Set Classification
147. CVPR 2024Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos
148. CVPR 2024RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
149. CVPR 2024SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection
150. CVPR 2024Single Domain Generalization for Crowd Counting

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。