← Back to all news
arXiv Machine Learning

Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment

The paper introduces Difference‑Quotient Clustering (DQC) to address mean‑collapse in multimodal regression. DQC partitions data by minimizing intra‑cluster output‑vs‑input discrepancy, assigning each sample to the cluster with the lowest maximum contradiction ratio. The resulting cluster labels train a logits generator and conditional network, achieving lower minimum squared error on synthetic benchmarks compared to random labeling and mean‑collapse baselines.

Related stories

arXiv Machine Learning
Jun 10

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

arXiv:2606. 11190v1 Announce Type: new Abstract: Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality.

By Ilay Kamai, Hugues Van Assel, Aviv Regev, Hagai B. Perets, Randall Balestriero
multimodalbenchmarkssafety
More like this →
Hugging Face Trending Papers
Jun 9

When to Align, When to Predict: A Phase Diagram for Multimodal Learning

Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each succeeds, when each fails, and when cross-modal training helps at all -- a gap that leaves practitioners, especially in scientific domains like biomedicine or astrophysics, with heterogeneous instruments and multiple levels of organization and measurement, unable to diagnose why standard methods underperform the best single modality. We develop a unified linear framework that addresses both questions.

multimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Jun 16

Unsupervised Learning for Missing Modalities in Multimodal Learning

arXiv:2606. 15743v1 Announce Type: new Abstract: This paper addresses the missing-modality challenge in multi-modal learning by introducing Unsupervised Learning for Missing Modalities in Multi-Modal Learning (UL4M4), a flexible framework that imputes missing feature embeddings in a task-independent manner before supervised prediction.

By Hassan Ismkhan, Hamid Bouchahcia
ragmultimodalbenchmarks
More like this →
arXiv Statistics ML
6d ago

Ensembles of Exactly Solved Subsamples for Clusterwise Regression: Trimming Without a Trimming Level

The paper proposes an ensemble method for clusterwise regression that uses exact solutions on many small random subsamples. Each subsample is solved to global optimality, extended to the full data via nearest-surface assignment, and the resulting partitions are combined by voting or selection. The method achieves high accuracy even with up to 20% gross outliers and can estimate the trimming level without prior knowledge, outperforming traditional trimmed alternation in worst‑case scenarios.

By Samir Orujov
More like this →
arXiv AI
Aug 25

Mitigating Sample-Level Imbalance via Probabilistic Separation for Adaptive Multimodal Fusion

The paper introduces a framework to tackle modality imbalance in multimodal learning by focusing on sample-level variations. It defines a Modality Gap metric to measure prediction discrepancies, models the resulting bimodal distribution with a Gaussian Mixture Model, and uses Bayesian probabilities for soft separation of balanced and imbalanced samples. A two‑stage training process—Warm‑up and Adaptive Training—reallocates loss weights based on the GMM, strengthening alignment for imbalanced samples while favoring fusion for balanced ones, and shows superior performance over existing baselines.

By Zhiwen Yu, Zhaocheng Liu, Xiaoqing Liu, Huanqiang Zeng, C. L. Philip Chen
fine-tuningmultimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Jul 9

Converge to Surprise: Evolutionary Self-supervised Image Clustering

arXiv:2607. 06887v1 Announce Type: new Abstract: Most self-supervised image clustering models, actually almost all deep learning approaches, are based on gradient descent: In order to calculate the loss, every optimization step requires a clearly defined target, whether a contrastive split, a masked patch or entity, an EMA-teacher output, a pseudo-label, or a differentiable information-theoretic functional.

By Canlin Zhang, Xiuwen Liu
benchmarks
More like this →