arXiv AI
FairSSL: Fair Multimodal Self-Supervised Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 24
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv Machine Learning
Jul 27
Unbiased Open World Regularization for Fair Self-Supervised Learning
arXiv:2607. 22149v1 Announce Type: new Abstract: Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset.
arXiv Machine Learning
Jul 17
Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality
arXiv:2607. 14721v1 Announce Type: cross Abstract: Cross-modal learning, i.
Hugging Face Trending Papers
Jul 16
Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality
Cross-modal learning, i. e.
arXiv AI
Sep 16
Fairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions
The paper investigates intersectional biases in multimodal clinical predictions using Electronic Healthcare Records (EHR). It introduces datasets MIMIC-Eye1 and MIMIC-IV ED, applies unified text representations from pre‑trained clinical language models, and benchmarks bias mitigation at the intersectional subgroup level. Results show that subgroup‑specific mitigation is robust across datasets, subgroups, and embeddings, effectively addressing intersectional biases in multimodal settings.
arXiv Machine Learning
Sep 1
Diverse via bounded Agreement: Geometric Regularization for Multimodal Fusion
arXiv:2601.21670v4 Announce Type: replace-cross Abstract: Multimodal fusion is often treated as an optimization-balancing problem, where training signals are adjusted to prevent one modality from dom...