Imagen de Portada

From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Yiming, Han, Junlin, Bai, Tianyi, Tong, Shengbang, Kokkinos, Filippos, Torr, Philip
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning Multimedia
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training
por: Han, Junlin, et al.
Publicado: (2025)

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models
por: Han, Junlin, et al.
Publicado: (2024)

Visual Semantic Description Generation with MLLMs for Image-Text Matching
por: Chen, Junyu, et al.
Publicado: (2025)

Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
por: Han, Junlin, et al.
Publicado: (2024)

SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
por: Tu, Jinzhe, et al.
Publicado: (2026)

Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation
por: Wu, Xun, et al.
Publicado: (2024)

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
por: Cai, Qi, et al.
Publicado: (2026)

PixelThink: Towards Efficient Chain-of-Pixel Reasoning
por: Wang, Song, et al.
Publicado: (2025)

VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification
por: Meng, Jiahao, et al.
Publicado: (2026)

Disparity-based Stereo Image Compression with Aligned Cross-View Priors
por: Zhai, Yongqi, et al.
Publicado: (2022)

Noisy-Correspondence Learning for Text-to-Image Person Re-identification
por: Qin, Yang, et al.
Publicado: (2023)

Spatial-Aware Efficient Projector for MLLMs via Multi-Layer Feature Aggregation
por: Qian, Shun, et al.
Publicado: (2024)

Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision
por: Yin, Kangsheng, et al.
Publicado: (2025)

Anisotropic Modality Align
por: Yu, Xiaomin, et al.
Publicado: (2026)

Magic3DSketch: Create Colorful 3D Models From Sketch-Based 3D Modeling Guided by Text and Language-Image Pre-Training
por: Zang, Ying, et al.
Publicado: (2024)

Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention
por: Song, Shezheng, et al.
Publicado: (2026)

Continual Panoptic Perception: Towards Multi-modal Incremental Interpretation of Remote Sensing Images
por: Yuan, Bo, et al.
Publicado: (2024)

CIV-DG: Conditional Instrumental Variables for Domain Generalization in Medical Imaging
por: Bai, Shaojin, et al.
Publicado: (2026)

Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
por: Chen, Yangneng, et al.
Publicado: (2026)

Synthetic Perception: Can Generated Images Unlock Latent Visual Prior for Text-Centric Reasoning?
por: Huang, Yuesheng, et al.
Publicado: (2025)

PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning
por: Xiao, Yicheng, et al.
Publicado: (2025)

CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception
por: Li, Liupeng, et al.
Publicado: (2026)

A Tri-Dynamic Preprocessing Framework for UGC Video Compression
por: Zhao, Fei, et al.
Publicado: (2025)

A Preprocessing Framework for Video Machine Vision under Compression
por: Zhao, Fei, et al.
Publicado: (2025)

ComAlign: Compositional Alignment in Vision-Language Models
por: Abdollah, Ali, et al.
Publicado: (2024)

Scalable Image Coding for Humans and Machines Using Feature Fusion Network
por: Shindo, Takahiro, et al.
Publicado: (2024)

EditHF-1M: A Million-Scale Rich Human Preference Feedback for Image Editing
por: Xu, Zitong, et al.
Publicado: (2026)

X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs
por: Swetha, Sirnam, et al.
Publicado: (2024)

G-Refine: A General Quality Refiner for Text-to-Image Generation
por: Li, Chunyi, et al.
Publicado: (2024)

Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment
por: Zhang, Tong, et al.
Publicado: (2025)

Generative Preprocessing for Image Compression with Pre-trained Diffusion Models
por: Guo, Mengxi, et al.
Publicado: (2025)

UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
por: Wang, Xiang, et al.
Publicado: (2025)

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
por: Han, ZhaoYang, et al.
Publicado: (2025)

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
por: Zhong, Zhisheng, et al.
Publicado: (2024)

DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment
por: Li, Xinyue, et al.
Publicado: (2026)

Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
por: Mo, Wentao, et al.
Publicado: (2025)

GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models
por: Zhu, Xingyu, et al.
Publicado: (2026)

A Benchmark for Ultra-High-Resolution Remote Sensing MLLMs
por: Dang, Yunkai, et al.
Publicado: (2025)

Phi-Ground Tech Report: Advancing Perception in GUI Grounding
por: Zhang, Miaosen, et al.
Publicado: (2025)

CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model
por: Luo, Yuxuan, et al.
Publicado: (2025)