Imagen de Portada

Intrinsic Dimension Correlation: uncovering nonlinear connections in multimodal representations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Basile, Lorenzo, Acevedo, Santiago, Bortolussi, Luca, Anselmi, Fabio, Rodriguez, Alex
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

ResiDual Transformer Alignment with Spectral Decomposition
por: Basile, Lorenzo, et al.
Publicado: (2024)

Head Pursuit: Probing Attention Specialization in Multimodal Transformers
por: Basile, Lorenzo, et al.
Publicado: (2025)

Explaining latent representations of generative models with large multimodal models
por: Zhu, Mengdan, et al.
Publicado: (2024)

Visual concept ranking uncovers medical shortcuts used by large multimodal models
por: Janizek, Joseph D., et al.
Publicado: (2026)

Blending adversarial training and representation-conditional purification via aggregation improves adversarial robustness
por: Ballarin, Emanuele, et al.
Publicado: (2023)

Closing the gap in multimodal medical representation alignment
por: Grassucci, Eleonora, et al.
Publicado: (2026)

Human-like object concept representations emerge naturally in multimodal large language models
por: Du, Changde, et al.
Publicado: (2024)

What to align in multimodal contrastive learning?
por: Dufumier, Benoit, et al.
Publicado: (2024)

Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion Models
por: Lewandowski, Basile, et al.
Publicado: (2025)

Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp
por: Hong, Rachel, et al.
Publicado: (2024)

Can multimodal representation learning by alignment preserve modality-specific information?
por: Thoreau, Romain, et al.
Publicado: (2025)

IRIS: Intrinsic Reward Image Synthesis
por: Chen, Yihang, et al.
Publicado: (2025)

Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension
por: Parolari, Luca, et al.
Publicado: (2024)

PerLA: Perceptive 3D Language Assistant
por: Mei, Guofeng, et al.
Publicado: (2024)

Linearly Separable Features in Shallow Nonlinear Networks: Width Scales Polynomially with Intrinsic Data Dimension
por: Xu, Alec S., et al.
Publicado: (2025)

Multi-Modal Hallucination Control by Visual Information Grounding
por: Favero, Alessandro, et al.
Publicado: (2024)

Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
por: Salzmann, Tim, et al.
Publicado: (2024)

COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
por: Xiao, Jinqi, et al.
Publicado: (2024)

Multimodal Inverse Attention Network with Intrinsic Discriminant Feature Exploitation for Fake News Detection
por: Zhang, Tianlin, et al.
Publicado: (2025)

A Vision Check-up for Language Models
por: Sharma, Pratyusha, et al.
Publicado: (2024)

MULTIAQUA: A multimodal maritime dataset and robust training strategies for multimodal semantic segmentation
por: Muhovič, Jon, et al.
Publicado: (2025)

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
por: Deitke, Matt, et al.
Publicado: (2024)

It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
por: Fahim, Abrar, et al.
Publicado: (2024)

Iris: Integrating Language into Diffusion-based Monocular Depth Estimation
por: Zeng, Ziyao, et al.
Publicado: (2024)

Next state prediction gives rise to entangled, yet compositional representations of objects
por: Saanum, Tankred, et al.
Publicado: (2024)

Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training
por: Saha, Rohan, et al.
Publicado: (2024)

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding
por: Zhou, Shijie, et al.
Publicado: (2025)

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications
por: Liang, Paul Pu, et al.
Publicado: (2023)

MPQ-Diff: Mixed Precision Quantization for Diffusion Models
por: Maruzzelli, Rocco Manz, et al.
Publicado: (2024)

The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models
por: Serra, Alessandro Pietro, et al.
Publicado: (2024)

An Intrinsic Vector Heat Network
por: Gao, Alexander, et al.
Publicado: (2024)

Task-conditioned probing of instruction-tuned multimodal LLMs: Region-specific brain alignment patterns under naturalistic stimuli
por: Oota, Subba Reddy, et al.
Publicado: (2025)

Characterizing the Predictive Impact of Modalities with Supervised Latent-Variable Modeling
por: Madaan, Divyam, et al.
Publicado: (2026)

Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition
por: Tang, Minxue, et al.
Publicado: (2026)

Debiasing Large Vision-Language Models by Ablating Protected Attribute Representations
por: Ratzlaff, Neale, et al.
Publicado: (2024)

Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers
por: Tas, Omer Sahin, et al.
Publicado: (2024)

MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Models
por: Ganesan, Mugilan, et al.
Publicado: (2025)

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models
por: Gan, Woody Haosheng, et al.
Publicado: (2025)

ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities
por: Ghosh, Adhiraj, et al.
Publicado: (2024)

Optimizing GPT for Video Understanding: Zero-Shot Performance and Prompt Engineering
por: Beliaev, Mark, et al.
Publicado: (2025)