Imagen de Portada

Large Language Models are Universal Reasoners for Visual Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ren, Sucheng, Chen, Chen, Wang, Zhenbang, Song, Liangchen, Zhu, Xiangxin, Yuille, Alan, Chen, Liang-Chieh, Lu, Jiasen
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Autoregressive Video Generation beyond Next Frames Prediction
por: Ren, Sucheng, et al.
Publicado: (2025)

Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation
por: Ren, Sucheng, et al.
Publicado: (2025)

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers
por: Ren, Sucheng, et al.
Publicado: (2025)

Frequency-Aware Flow Matching for High-Quality Image Generation
por: Ren, Sucheng, et al.
Publicado: (2026)

FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
por: Ren, Sucheng, et al.
Publicado: (2024)

Rejuvenating image-GPT as Strong Visual Representation Learners
por: Ren, Sucheng, et al.
Publicado: (2023)

ViMix-14M: A Curated Multi-Source Video-Text Dataset with Long-Form, High-Quality Captions and Crawl-Free Access
por: Yang, Timing, et al.
Publicado: (2025)

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning
por: Ren, Sucheng, et al.
Publicado: (2024)

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation
por: Ren, Sucheng, et al.
Publicado: (2024)

ViTamin: Designing Scalable Vision Models in the Vision-Language Era
por: Chen, Jieneng, et al.
Publicado: (2024)

SPFormer: Enhancing Vision Transformer with Superpixel Representation
por: Mei, Jieru, et al.
Publicado: (2024)

ReVision: Refining Video Diffusion with Explicit 3D Motion Modeling
por: Liu, Qihao, et al.
Publicado: (2025)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
por: Liu, Haoyu, et al.
Publicado: (2026)

ViT-5: Vision Transformers for The Mid-2020s
por: Wang, Feng, et al.
Publicado: (2026)

Efficient Large Multi-modal Models via Visual Context Compression
por: Chen, Jieneng, et al.
Publicado: (2024)

ExoViP: Step-by-step Verification and Exploration with Exoskeleton Modules for Compositional Visual Reasoning
por: Wang, Yuxuan, et al.
Publicado: (2024)

Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
por: Ren, Sucheng, et al.
Publicado: (2024)

AToken: A Unified Tokenizer for Vision
por: Lu, Jiasen, et al.
Publicado: (2025)

GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models
por: Guan, Yaohan, et al.
Publicado: (2026)

Mamba-R: Vision Mamba ALSO Needs Registers
por: Wang, Feng, et al.
Publicado: (2024)

Generative World Explorer
por: Lu, Taiming, et al.
Publicado: (2024)

HResFormer: Hybrid Residual Transformer for Volumetric Medical Image Segmentation
por: Ren, Sucheng, et al.
Publicado: (2024)

CAR-Flow: Condition-Aware Reparameterization Aligns Source and Target for Better Flow Matching
por: Chen, Chen, et al.
Publicado: (2025)

Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models
por: Wang, Xingrui, et al.
Publicado: (2025)

Quality Sentinel: Estimating Label Quality and Errors in Medical Segmentation Datasets
por: Chen, Yixiong, et al.
Publicado: (2024)

WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark
por: Lin, Wang, et al.
Publicado: (2026)

RNN as Linear Transformer: A Closer Investigation into Representational Potentials of Visual Mamba Models
por: Yang, Timing, et al.
Publicado: (2025)

Large-Scale Label Quality Assessment for Medical Segmentation via a Vision-Language Judge and Synthetic Data
por: Chen, Yixiong, et al.
Publicado: (2026)

VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models
por: Xu, Weiye, et al.
Publicado: (2025)

Play to Generalize: Learning to Reason Through Game Play
por: Xie, Yunfei, et al.
Publicado: (2025)

A Simple Video Segmenter by Tracking Objects Along Axial Trajectories
por: He, Ju, et al.
Publicado: (2023)

SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference
por: Wang, Feng, et al.
Publicado: (2023)

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency
por: Wang, Feng, et al.
Publicado: (2024)

Thinking with Spatial Code for Physical-World Video Reasoning
por: Chen, Jieneng, et al.
Publicado: (2026)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
por: Zhu, Wenxin, et al.
Publicado: (2025)

Randomized Autoregressive Visual Generation
por: Yu, Qihang, et al.
Publicado: (2024)

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models
por: Ma, Wufei, et al.
Publicado: (2025)

Vision-Language-Vision Auto-Encoder: Scalable Knowledge Distillation from Diffusion Models
por: Zhang, Tiezheng, et al.
Publicado: (2025)

Deeply Supervised Flow-Based Generative Models
por: Shin, Inkyu, et al.
Publicado: (2025)

Perceptual Taxonomy: Evaluating and Guiding Hierarchical Scene Reasoning in Vision-Language Models
por: Lee, Jonathan, et al.
Publicado: (2025)