arXiv AI
Dynamic Alignment and Calibration for Multimodal 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 14
PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
arXiv:2604. 22823v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities.
arXiv Machine Learning
Jul 2
Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning
arXiv:2505. 19614v2 Announce Type: replace Abstract: Multimodal learning has seen remarkable progress, particularly with large-scale pre-training across various modalities.
arXiv AI
Jun 8
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
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...
arXiv Machine Learning
Jun 2
Feature Alignment Determines Fusion Strategy: A Comparative Study of Cross-Attention and Concatenation in Multimodal Learning
arXiv:2606. 01207v1 Announce Type: cross Abstract: The choice between cross-attention and concatenation for multimodal fusion remains governed by practitioner intuition rather than principled understanding.
arXiv AI
Jul 16
Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision Mapping
arXiv:2508. 12466v2 Announce Type: replace-cross Abstract: Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data.