Cover Image

Learning to See Before Seeing: Demystifying LLM Visual Priors from Language Pre-training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Han, Junlin, Tong, Shengbang, Fan, David, Ren, Yufan, Sinha, Koustuv, Torr, Philip, Kokkinos, Filippos
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Multimedia
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images
by: Chen, Yiming, et al.
Published: (2025)

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

SeeingSounds: Learning Audio-to-Visual Alignment via Text
by: Carnemolla, Simone, et al.
Published: (2025)

Efficient Object-centric Representation Learning with Pre-trained Geometric Prior
by: Khac, Phúc H. Le, et al.
Published: (2024)

Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models
by: Caffagni, Davide, et al.
Published: (2025)

Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learning
by: Wang, Youze, et al.
Published: (2023)

See or Guess: Counterfactually Regularized Image Captioning
by: Cao, Qian, et al.
Published: (2024)

Seeing Text in the Dark: Algorithm and Benchmark
by: Xu, Chengpei, et al.
Published: (2024)

VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models
by: Ren, Yufan, et al.
Published: (2025)

Seeing Culture: A Benchmark for Visual Reasoning and Grounding
by: Satar, Burak, et al.
Published: (2025)

It Hears, It Sees too: Multi-Modal LLM for Depression Detection By Integrating Visual Understanding into Audio Language Models
by: Zhao, Xiangyu, et al.
Published: (2025)

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

Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition
by: Liu, Rui, et al.
Published: (2025)

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

COPA: Efficient Vision-Language Pre-training Through Collaborative Object- and Patch-Text Alignment
by: Jiang, Chaoya, et al.
Published: (2023)

Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction
by: Wang, Dali, et al.
Published: (2026)

Physics-Aware Novel-View Acoustic Synthesis with Vision-Language Priors and 3D Acoustic Environment Modeling
by: Fan, Congyi, et al.
Published: (2026)

Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
by: Tan, Weiting, et al.
Published: (2025)

Seeing World Dynamics in a Nutshell
by: Shen, Qiuhong, et al.
Published: (2025)

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents
by: Zhang, Yimeng, et al.
Published: (2025)

Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners
by: Xing, Yazhou, et al.
Published: (2024)

Multimodal Pre-training Framework for Sequential Recommendation via Contrastive Learning
by: Zhang, Lingzi, et al.
Published: (2023)

Reinforcing Pre-trained Models Using Counterfactual Images
by: Li, Xiang, et al.
Published: (2024)

Speech-to-See: End-to-End Speech-Driven Open-Set Object Detection
by: Lu, Wenhuan, et al.
Published: (2025)

Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
by: Chen, Junjie, et al.
Published: (2025)

A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification
by: Calbucura, Nicolas, et al.
Published: (2025)

RA-BLIP: Multimodal Adaptive Retrieval-Augmented Bootstrapping Language-Image Pre-training
by: Ding, Muhe, et al.
Published: (2024)

Seeing Through Deception: Uncovering Misleading Creator Intent in Multimodal News with Vision-Language Models
by: Wu, Jiaying, et al.
Published: (2025)

Scaling up Multimodal Pre-training for Sign Language Understanding
by: Zhou, Wengang, et al.
Published: (2024)

Learning Switchable Priors for Neural Image Compression
by: Zhang, Haotian, et al.
Published: (2025)

Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator
by: Kang, Minjae, et al.
Published: (2025)

Towards Unified Representation of Multi-Modal Pre-training for 3D Understanding via Differentiable Rendering
by: Fei, Ben, et al.
Published: (2024)

Seeing Isn't Believing: Addressing the Societal Impact of Deepfakes in Low-Tech Environments
by: Wasi, Azmine Toushik, et al.
Published: (2025)

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

Seeing, Hearing, and Knowing Together: Multimodal Strategies in Deepfake Videos Detection
by: Chen, Chen, et al.
Published: (2026)

Seeing What You Say: Expressive Image Generation from Speech
by: Lee, Jiyoung, et al.
Published: (2025)

"I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments
by: Zhang, Ziyi, et al.
Published: (2025)

SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing
by: Chen, Mingfei, et al.
Published: (2025)

CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
by: Sun, Shuyang, et al.
Published: (2023)

VSpeechLM: A Visual Speech Language Model for Visual Text-to-Speech Task
by: Wang, Yuyue, et al.
Published: (2025)