Imagen de Portada

MANTA: Cross-Modal Semantic Alignment and Information-Theoretic Optimization for Long-form Multimodal Understanding

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhong, Ziqi, Tang, Daniel
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
por: Liang, Yupu, et al.
Publicado: (2025)

Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts
por: Zhu, Zhihao, et al.
Publicado: (2026)

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
por: Zhang, Xiaoyi, et al.
Publicado: (2025)

Cross-Modal Projection in Multimodal LLMs Doesn't Really Project Visual Attributes to Textual Space
por: Verma, Gaurav, et al.
Publicado: (2024)

APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention
por: Huang, Yuxiang, et al.
Publicado: (2026)

Cross-modal Information Flow in Multimodal Large Language Models
por: Zhang, Zhi, et al.
Publicado: (2024)

TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
por: Ren, Shuhuai, et al.
Publicado: (2023)

Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
por: Eslami, Sedigheh, et al.
Publicado: (2024)

Cross-Modal Adapter for Vision-Language Retrieval
por: Jiang, Haojun, et al.
Publicado: (2022)

Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities
por: Zhou, Ziwei, et al.
Publicado: (2025)

Robust Multimodal Large Language Models Against Modality Conflict
por: Zhang, Zongmeng, et al.
Publicado: (2025)

Semantic Matters: Multimodal Features for Affective Analysis
por: Hallmen, Tobias, et al.
Publicado: (2025)

VideoAgent: Long-form Video Understanding with Large Language Model as Agent
por: Wang, Xiaohan, et al.
Publicado: (2024)

Analyzing Fine-Grained Alignment and Enhancing Vision Understanding in Multimodal Language Models
por: Jiang, Jiachen, et al.
Publicado: (2025)

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
por: Xu, Zhiyu, et al.
Publicado: (2026)

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
por: Ye, Hanrong, et al.
Publicado: (2025)

MULTI: Multimodal Understanding Leaderboard with Text and Images
por: Zhu, Zichen, et al.
Publicado: (2024)

Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models
por: Xu, Shicheng, et al.
Publicado: (2024)

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding
por: Chen, Dongping, et al.
Publicado: (2024)

A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs
por: Broomfield, Julius, et al.
Publicado: (2025)

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better
por: Wang, Dianyi, et al.
Publicado: (2025)

Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding
por: Kim, Namho, et al.
Publicado: (2025)

Geometry-Aware Cross Modal Alignment for Light Field-LiDAR Semantic Segmentation
por: Luo, Jie, et al.
Publicado: (2025)

Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment
por: Zheng, Yuze, et al.
Publicado: (2024)

Internalized Reasoning for Long-Context Visual Document Understanding
por: Veselka, Austin
Publicado: (2026)

MLVU: Benchmarking Multi-task Long Video Understanding
por: Zhou, Junjie, et al.
Publicado: (2024)

Adaptive Greedy Frame Selection for Long Video Understanding
por: Huang, Yuning, et al.
Publicado: (2026)

Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence
por: Aufschläger, Robert, et al.
Publicado: (2025)

CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
por: Chen, Zeyu, et al.
Publicado: (2026)

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
por: Liu, Chenxi, et al.
Publicado: (2025)

The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models
por: Paruchuri, Akshay, et al.
Publicado: (2026)

Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs
por: Saxena, Rohit, et al.
Publicado: (2025)

On Pre-training of Multimodal Language Models Customized for Chart Understanding
por: Fan, Wan-Cyuan, et al.
Publicado: (2024)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
por: Wu, Chengyue, et al.
Publicado: (2024)

e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings
por: Chen, Haonan, et al.
Publicado: (2026)

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
por: Zhong, Yiwu, et al.
Publicado: (2024)

VideoExplorer: Think With Videos For Agentic Long-Video Understanding
por: Yuan, Huaying, et al.
Publicado: (2025)

ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding
por: Kondic, Jovana, et al.
Publicado: (2026)

MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization
por: Zhu, Chenyang, et al.
Publicado: (2026)

MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings
por: Chen, Haonan, et al.
Publicado: (2025)