Open-Domain QA papers, 2023–2026

Key findings

• Open-Domain QA went from 52 papers in 2023 to 62 in 2026, roughly 1.2x in three years.
• CVPR publishes the most Open-Domain QA work: 113 papers from 2023 to 2026, 46% of the four-venue total.
• The fastest-growing overlap is with Simulation for Driving: papers tagged with both rose from 2 in 2023 to 9 in 2026.
• Among the 5 topics under Information Retrieval, it ranks #3 by 2026 paper count; the fastest grower in the group, Cross-Encoder Reranking, is up 3.0x versus 1.2x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Open-Domain QA papers

69 papers, page 1 of 2

1. NeurIPS 2026A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
2. NeurIPS 2026Better Language Models Require Better Domain-Specific Inductive Biases
3. NeurIPS 2026Beyond Average Flatness: Domain-wise Flatness for Domain Generalization
4. NeurIPS 2026Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
5. NeurIPS 2026CompleteRXN: Toward Completing Open Chemical Reaction Databases
6. NeurIPS 2026Domain-Conditioned Class Imbalance: Why Global Class Balance Fails Across Domains
7. NeurIPS 2026Efficient Multi-Source Prompt Adaptation for Cross-Domain Open-Vocabulary Learning
8. NeurIPS 2026EgoSurgHands: An Egocentric 3D Hand Pose Dataset & Benchmark for Open-Surgery Training
9. NeurIPS 2026FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale
10. NeurIPS 2026LDD-RFM: Learnable Domain Decomposition for Random Feature Models via Variable Projection
11. NeurIPS 2026Open Vocabulary Domain Unlearning
12. NeurIPS 2026PRISM: Priority-Guided Scanning in the Wavelet Domain for UAV Maritime Small Object Detection
13. NeurIPS 2026Query as a Resource: Activity-Cost Guided Remote Sensing Domain-Incremental Object Detection
14. NeurIPS 2026Re:Cognize - A Framework For Open-Set Comic Character Re-Identification
15. NeurIPS 2026ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork
16. NeurIPS 2026SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
17. NeurIPS 2026The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
18. NeurIPS 2026Too Smart to Teach: The Articulability Ceiling in Language Models
19. NeurIPS 2026Witness Overlap: Directional Provenance Inside Open-Weight Model Families
20. NeurIPS 2025A Generalized Label Shift Perspective for Cross-Domain Gaze Estimation
21. NeurIPS 2025AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise
22. NeurIPS 2025Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning
23. NeurIPS 2025Continuous Domain Generalization
24. NeurIPS 2025Diffusion Transformers as Open-World Spatiotemporal Foundation Models
25. NeurIPS 2025DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
26. NeurIPS 2025DOVTrack: Data-Efficient Open-Vocabulary Tracking
27. NeurIPS 2025FlexOLMo: Open Language Models for Flexible Data Use
28. NeurIPS 2025Gains: Fine-grained Federated Domain Adaptation in Open Set
29. NeurIPS 2025HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
30. NeurIPS 2025How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
31. NeurIPS 2025Intermediate Domain Alignment and Morphology Analogy for Patent-Product Image Retrieval
32. NeurIPS 2025Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models
33. NeurIPS 2025Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation
34. NeurIPS 2025MergeBench: A Benchmark for Merging Domain-Specialized LLMs
35. NeurIPS 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
36. NeurIPS 2025Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation
37. NeurIPS 2025Open-World Drone Active Tracking with Goal-Centered Rewards
38. NeurIPS 2025RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering
39. NeurIPS 2025Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
40. NeurIPS 2025UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models
41. NeurIPS 2024A Cross-Domain Benchmark for Active Learning
42. NeurIPS 2024ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
43. NeurIPS 2024Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
44. NeurIPS 2024CLUES: Collaborative Private-domain High-quality Data Selection for LLMs via Training Dynamics
45. NeurIPS 2024DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
46. NeurIPS 2024EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
47. NeurIPS 2024EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
48. NeurIPS 2024Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
49. NeurIPS 2024GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
50. NeurIPS 2024HelpSteer 2: Open-source dataset for training top-performing reward models

FAQ

How many Open-Domain QA papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

244 in total: 52 in 2023, 61 in 2024, 69 in 2025, 62 in 2026.

How many Open-Domain QA papers are at NeurIPS 2026?

NeurIPS 2026 has 19 Open-Domain QA papers, versus 21 the year before.

How many Open-Domain QA papers are at ICLR 2026?

ICLR 2026 has 7 Open-Domain QA papers, versus 12 the year before.

How many Open-Domain QA papers are at ICML 2026?

ICML 2026 has 5 Open-Domain QA papers, versus 2 the year before.

How many Open-Domain QA papers are at CVPR 2026?

CVPR 2026 has 31 Open-Domain QA papers, versus 34 the year before.

Which conference publishes the most Open-Domain QA papers?

CVPR, with 113 papers from 2023 to 2026.