偏见缓解论文趋势 2023–2026

主要结论

• 偏见缓解论文从 2023 年的 50 篇增长到 2026 年的 76 篇，三年间扩大到约 1.5 倍。
• ICLR 是发偏见缓解论文最多的会议，2023–2026 年共 85 篇，占四个会议总量的 30%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 15 篇。
• 在「因果与公平」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的因果发现是 2.4 倍，偏见缓解是 1.5 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 2026Controlling for Omitted Variable Bias in Deep Neural Networks
• ICML 2026BESplit: Bias-Compensated Split Federated Learning with Evidential Aggregation
• ICLR 2026Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
• CVPR 2026BAMI Training-Free Bias Mitigation in GUI Grounding
• NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
• ICML 2025Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies
• ICLR 2025ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition
• CVPR 2025Data Distributional Properties As Inductive Bias for Systematic Generalization
• NeurIPS 2024Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
• ICML 2024Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
• ICLR 2024A 2-Dimensional State Space Layer for Spatial Inductive Bias
• CVPR 2024Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
• NeurIPS 2023Fast Model DeBias with Machine Unlearning
• ICML 2023FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction
• ICLR 2023Bias Propagation in Federated Learning
• CVPR 2023Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
• NeurIPS 2026Empirical Bayes Rebiasing
• ICML 2026DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation
• ICLR 2026BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses
• CVPR 2026Bias at the End of the Score

全部偏见缓解论文

共 42 篇，第 1 / 1 页

1. CVPR 2026BAMI Training-Free Bias Mitigation in GUI Grounding
2. CVPR 2026BD-Merging Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
3. CVPR 2026Bias at the End of the Score
4. CVPR 2026Bias Is a Subspace Not a Coordinate A Geometric Rethinking
5. CVPR 2026Cross-Modal Attention Calibration for LVLM Hallucination Mitigation
6. CVPR 2026DSO Direct Steering Optimization for Bias Mitigation
7. CVPR 2026Elucidating the SNR-t Bias of Diffusion Probabilistic Models
8. CVPR 2026Envision Attend Then Respond Counterfactual Hallucination Mitigation in Large Vision-Language
9. CVPR 2026Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis
10. CVPR 2026MixFlow Training Alleviating Exposure Bias with Slowed Interpolation Mixture
11. CVPR 2026Multimodal Semantic Bias Mitigation for Diverse Text-To-3D Generation
12. CVPR 2026Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters
13. CVPR 2026Rank-Guided Pseudo-Bias Learning for Robust Black-Box Adaptation
14. CVPR 2025ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large Language Models
15. CVPR 2025D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.
16. CVPR 2025Data Distributional Properties As Inductive Bias for Systematic Generalization
17. CVPR 2025Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
18. CVPR 2025FreqDebias: Towards Generalizable Deepfake Detection via Consistency-Driven Frequency Debiasing
19. CVPR 2025Joint Vision-Language Social Bias Removal for CLIP
20. CVPR 2025Perceptual Inductive Bias Is What You Need Before Contrastive Learning
21. CVPR 2024BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model
22. CVPR 2024Balancing Act: Distribution-Guided Debiasing in Diffusion Models
23. CVPR 2024Batch Normalization Alleviates the Spectral Bias in Coordinate Networks
24. CVPR 2024Diffeomorphic Template Registration for Atmospheric Turbulence Mitigation
25. CVPR 2024Enhancing Intrinsic Features for Debiasing via Investigating Class-Discerning Common Attributes in Bias-Contrastive Pair
26. CVPR 2024Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain
27. CVPR 2024FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions
28. CVPR 2024Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincare Ball
29. CVPR 2024Learn to Rectify the Bias of CLIP for Unsupervised Semantic Segmentation
30. CVPR 2024On the Content Bias in Frechet Video Distance
31. CVPR 2024Robust Emotion Recognition in Context Debiasing
32. CVPR 2024Spatio-Temporal Turbulence Mitigation: A Translational Perspective
33. CVPR 2024Would Deep Generative Models Amplify Bias in Future Models?
34. CVPR 2023Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
35. CVPR 2023Bias-Eliminating Augmentation Learning for Debiased Federated Learning
36. CVPR 2023BiasAdv: Bias-Adversarial Augmentation for Model Debiasing
37. CVPR 2023BiasBed - Rigorous Texture Bias Evaluation
38. CVPR 2023Generative Bias for Robust Visual Question Answering
39. CVPR 2023Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification
40. CVPR 2023Probabilistic Debiasing of Scene Graphs
41. CVPR 2023Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation
42. CVPR 2023Training Debiased Subnetworks With Contrastive Weight Pruning

常见问题

2023–2026 年四大会议一共有多少篇偏见缓解论文？

共 284 篇，按年份分别是 2023 年 50 篇、2024 年 73 篇、2025 年 85 篇、2026 年 76 篇。

NeurIPS 2026 有多少篇偏见缓解论文？

NeurIPS 2026 有 14 篇偏见缓解论文，上一届是 38 篇。

ICLR 2026 有多少篇偏见缓解论文？

ICLR 2026 有 24 篇偏见缓解论文，上一届是 23 篇。

ICML 2026 有多少篇偏见缓解论文？

ICML 2026 有 24 篇偏见缓解论文，上一届是 17 篇。

CVPR 2026 有多少篇偏见缓解论文？

CVPR 2026 有 14 篇偏见缓解论文，上一届是 7 篇。

哪个会议的偏见缓解论文最多？

ICLR，2023–2026 年共 85 篇。