Multimodal Regression

Follow this topic Ask about this topic

Latest papers

9 papers0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label Assignment
Aug 26, 2026Huang WeiquanMultimodal Regression Multimodal Learning
Guangdong Polytechnic Normal University
Conformal Calibration for Multi-Modal Regression with Missing Modalities
Aug 7, 2026Ilia AziziGroup-Conditional Conformal Prediction Multimodal Regression
Department of Operations, HEC Lausanne, University of Lausanne, Switzerland · BegooAI, Switzerland
Efficient Analytic Uncertainty Quantification for Multi-Modal Regression
Jun 23, 2026Kun Jin, James Harrison, Jiawei Li +8Quantile Regression Uncertainty Quantification
1Google · 2Google DeepMind
Bounded-Compute Multimodal Regression for Product-Rating Prediction
May 26, 2026William Leach, Ru He, Sizhuo Ma +4Vision-Language Models VLM Adaptation
Snap Inc.
Rethinking Gradient Modulation in Multimodal Regression
May 26, 2026Haojie Yin, Chengcheng Feng, Tianyi Liu +2Multimodal Regression Multimodal Learning
Duke Kunshan University, China · Xi’an Jiaotong-Liverpool University, China · Soochow University
A Mutual Information Lower Bound for Multimodal Regression Active Learning
May 14, 2026Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris PerdikarisMixture Density Networks Active Learning
Graduate Group on Applied Mathematics & Computational Science · Department of Computer and Information Science University of Pennsylvania Philadelphia, PA 19104 · Department of Mechanical Engineering and Applied Mechanics University of Pennsylvania Philadelphia, PA 19104
EffiMiniVLM: A Compact Dual-Encoder Regression Framework
Apr 3, 2026Yin-Loon Khor, Yi-Jie Wong, Yan Chai HumMultimodal Regression Efficient VLM Training
Universiti Malaya, Kuala Lumpur 50603, Malaysia · Universiti Tunku Abdul Rahman, Selangor 43000, Malaysia
A Lightweight Vision-Language Fusion Framework for Predicting App Ratings from User Interfaces and Metadata
Feb 24, 2026Azrin Sultana, Firoz AhmedMultimodal Regression Multimodal Fusion
Department of Computer Science, American International University–Bangladesh
FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization and Contrastive Learning
Nov 30, 2025Haozhe WuMultimodal Federated Learning Non-IID Federated Learning
School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China

Aug 26, 2026J/K move · Enter open · S save

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

Huang Weiquan

Guangdong Polytechnic Normal University

Multimodal Regression Multimodal Learning

Open paper AskPDF arXiv

Multimodal regression suffers from the mean-collapse pathology: under squared loss, an unconstrained regressor converges to the conditional mean, which for K > 1 lies away from all modes. We attribute this failure to pairwise contradictions--samples with nearly identical inputs but distant outputs--and propose Difference-Quotient Clustering (DQC), which partitions data to minimize intra-cluster output-vs-input discrepancy. Each sample is assigned to the cluster that minimizes its maximum contradiction ratio; a logits generator and a conditional network are then trained on the resulting labels. Since the generating modality is unknown at test time, we evaluate via minimum squared error (minMSE) against all K true outputs. On synthetic benchmarks (K=5, 10), DQC achieves test minMSE 0.19 (K=5, nx=500), versus 0.09 for an oracle, 1.08 for random labels, and 1.33 for mean collapse. We observe two empirical regularities: larger intra-cluster contradictions require deeper networks, and oracle labels generalize from fewer samples than cluster-derived equivalents. The clustering is a hard, parallelizable O(n^2/2) front-end for coarse conditional assignment, reducing the burden of downstream generative refinement. A second-stage re-clustering on residual errors is outlined as future work.