Glyph: Scaling Context Windows via Visual-Text Compression

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Jiale, Liu, Yusen, Zhang, Xinyu, Fei, Yulin, Hong, Wenyi, Lyu, Ruiliang, Wang, Weihan, Su, Zhe, Gu, Xiaotao, Liu, Xiao, Bai, Yushi, Tang, Jie, Wang, Hongning, Huang, Minlie
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
por: Cheng, Jiale, et al.
Publicado: (2025)

LongSafety: Evaluating Long-Context Safety of Large Language Models
por: Lu, Yida, et al.
Publicado: (2025)

UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization
por: Yang, Zhen, et al.
Publicado: (2025)

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
por: Gui, Jiayi, et al.
Publicado: (2024)

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
por: Cheng, Jiale, et al.
Publicado: (2024)

SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
por: Cheng, Jiale, et al.
Publicado: (2024)

GlyphMastero: A Glyph Encoder for High-Fidelity Scene Text Editing
por: Wang, Tong, et al.
Publicado: (2025)

GlyphWeaver: Unlocking Glyph Design Creativity with Uniform Glyph DSL and AI
por: Liu, Can, et al.
Publicado: (2025)

HPSS: Heuristic Prompting Strategy Search for LLM Evaluators
por: Wen, Bosi, et al.
Publicado: (2025)

Language Model Decoding as Direct Metrics Optimization
por: Ji, Haozhe, et al.
Publicado: (2023)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
por: Cheng, Jiale, et al.
Publicado: (2023)

GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text Rendering
por: Shuai, Xincheng, et al.
Publicado: (2026)

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning
por: Qi, Ji, et al.
Publicado: (2024)

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis
por: Wang, Yuanrui, et al.
Publicado: (2025)

Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering
por: Liu, Zeyu, et al.
Publicado: (2024)

HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing
por: Feng, Andrew Zhuoer, et al.
Publicado: (2026)

LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model
por: Liu, Hongen, et al.
Publicado: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
por: Zhang, Zhexin, et al.
Publicado: (2023)

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
por: Hong, Wenyi, et al.
Publicado: (2025)

Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
por: Wen, Jiaxin, et al.
Publicado: (2024)

SWAA: Sliding Window Attention Adaptation for Efficient and Quality Preserving Long Context Processing
por: Yu, Yijiong, et al.
Publicado: (2025)

Recurrent Context Compression: Efficiently Expanding the Context Window of LLM
por: Huang, Chensen, et al.
Publicado: (2024)

Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering
por: Liu, Zeyu, et al.
Publicado: (2024)

Context Cascade Compression: Exploring the Upper Limits of Text Compression
por: Liu, Fanfan, et al.
Publicado: (2025)

FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection
por: Zhang, Ruiqiang, et al.
Publicado: (2026)

Data Selection via Optimal Control for Language Models
por: Gu, Yuxian, et al.
Publicado: (2024)

FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
por: Kai, Jushi, et al.
Publicado: (2025)

MARVisT: Authoring Glyph-based Visualization in Mobile Augmented Reality
por: Zhu-Tian, Chen, et al.
Publicado: (2023)

Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training
por: Li, Wenbo, et al.
Publicado: (2024)

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
por: Zhao, Hongbo, et al.
Publicado: (2025)

AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
por: Guan, Jian, et al.
Publicado: (2024)

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
por: Zheng, Wendi, et al.
Publicado: (2024)

Glyph-Based Multiscale Visualization of Turbulent Multi-Physics Statistics
por: Cowe, Arisa, et al.
Publicado: (2025)

LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
por: Xie, Roy, et al.
Publicado: (2026)

TextMaster: A Unified Framework for Realistic Text Editing via Glyph-Style Dual-Control
por: Yan, Zhenyu, et al.
Publicado: (2024)

Think Socially via Cognitive Reasoning
por: Zhou, Jinfeng, et al.
Publicado: (2025)

Point Cloud Compression with Implicit Neural Representations: A Unified Framework
por: Ruan, Hongning, et al.
Publicado: (2024)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
por: Feng, Andrew Zhuoer, et al.
Publicado: (2026)

A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation
por: Zhao, Yi, et al.
Publicado: (2026)

Learning Task Decomposition to Assist Humans in Competitive Programming
por: Wen, Jiaxin, et al.
Publicado: (2024)