Cover Image

From Pixels to Words -- Towards Native Vision-Language Primitives at Scale

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Diao, Haiwen, Li, Mingxuan, Wu, Silei, Dai, Linjun, Wang, Xiaohua, Deng, Hanming, Lu, Lewei, Lin, Dahua, Liu, Ziwei
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

From Pixels to Words -- Towards Native One-Vision Models at Scale
by: Diao, Haiwen, et al.
Published: (2026)

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding
by: Fan, Weichen, et al.
Published: (2025)

ACPO: Counteracting Likelihood Displacement in Vision-Language Alignment with Asymmetric Constraints
by: Huang, Kaili, et al.
Published: (2026)

Visual Jigsaw Post-Training Improves MLLMs
by: Wu, Penghao, et al.
Published: (2025)

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints
by: Tian, Changyao, et al.
Published: (2025)

From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models
by: Li, Rongjie, et al.
Published: (2024)

Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM
by: Wu, Penghao, et al.
Published: (2025)

DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
by: Xie, Haozhe, et al.
Published: (2026)

Unveiling Encoder-Free Vision-Language Models
by: Diao, Haiwen, et al.
Published: (2024)

DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
by: Cui, Erfei, et al.
Published: (2023)

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
by: Diao, Haiwen, et al.
Published: (2025)

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
by: Chen, Zhaoxi, et al.
Published: (2024)

KARST: Multi-Kernel Kronecker Adaptation with Re-Scaling Transmission for Visual Classification
by: Zhu, Yue, et al.
Published: (2025)

SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
by: Chng, Yong Xien, et al.
Published: (2025)

From Pixels to Primitives: Scene Change Detection in 3D Gaussian Splatting
by: Galappaththige, Chamuditha Jayanga, et al.
Published: (2026)

PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
by: Liang, Wenqi, et al.
Published: (2025)

VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?
by: Liu, Qing'an, et al.
Published: (2026)

End-to-End Vision Tokenizer Tuning
by: Wang, Wenxuan, et al.
Published: (2025)

VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
by: Wu, Jiannan, et al.
Published: (2024)

EVA: Efficient Reinforcement Learning for End-to-End Video Agent
by: Zhang, Yaolun, et al.
Published: (2026)

HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding
by: Tao, Chenxin, et al.
Published: (2024)

Deep Boosting Learning: A Brand-new Cooperative Approach for Image-Text Matching
by: Diao, Haiwen, et al.
Published: (2024)

SS4D: Native 4D Generative Model via Structured Spacetime Latents
by: Li, Zhibing, et al.
Published: (2025)

From Dead Pixels to Editable Slides: Infographic Reconstruction into Native Google Slides via Vision-Language Region Understanding
by: Gonzalez, Leonardo
Published: (2026)

ELV-Halluc: Benchmarking Semantic Aggregation Hallucinations in Long Video Understanding
by: Lu, Hao, et al.
Published: (2025)

Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Models
by: He, Zoe Wanying, et al.
Published: (2025)

Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection
by: Wang, Jiahao, et al.
Published: (2024)

Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives
by: Hanson, Alex, et al.
Published: (2024)

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
by: Wu, Penghao, et al.
Published: (2025)

Towards Fine-Grained Recognition with Large Visual Language Models: Benchmark and Optimization Strategies
by: Pang, Cong, et al.
Published: (2025)

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
by: Li, Xiaotong, et al.
Published: (2024)

Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
by: Bao, Muyi, et al.
Published: (2026)

Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing
by: Li, Jinsong, et al.
Published: (2026)

Scaling Spatial Intelligence with Multimodal Foundation Models
by: Cai, Zhongang, et al.
Published: (2025)

From Simple to Professional: A Combinatorial Controllable Image Captioning Agent
by: Wang, Xinran, et al.
Published: (2024)

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
by: Lin, Yihan, et al.
Published: (2026)

From Pixels to Words: Leveraging Explainability in Face Recognition through Interactive Natural Language Processing
by: DeAndres-Tame, Ivan, et al.
Published: (2024)

SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding
by: Li, Hao, et al.
Published: (2024)

InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
by: Chen, Zhe, et al.
Published: (2023)

From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs
by: Kiruluta, Andrew, et al.
Published: (2025)