Imagen de Portada

PixelThink: Towards Efficient Chain-of-Pixel Reasoning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Song, Fang, Gongfan, Kong, Lingdong, Li, Xiangtai, Xu, Jianyun, Yang, Sheng, Li, Qiang, Zhu, Jianke, Wang, Xinchao
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Multimedia
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Diversity-Guided MLP Reduction for Efficient Large Vision Transformers
por: Shen, Chengchao, et al.
Publicado: (2025)

PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
por: Wang, Song, et al.
Publicado: (2025)

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
por: Meng, Jiahao, et al.
Publicado: (2025)

Context and Pixel Aware Large Language Model for Video Quality Assessment
por: Wen, Wen, 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)

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

Food Portion Estimation: From Pixels to Calories
por: Vinod, Gautham, et al.
Publicado: (2026)

EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
por: Chow, Wei, et al.
Publicado: (2025)

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query
por: Chow, Wei, et al.
Publicado: (2025)

ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps
por: Feng, Sicheng, et al.
Publicado: (2025)

OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation
por: Gan, Qijun, et al.
Publicado: (2025)

Event Camera Demosaicing via Swin Transformer and Pixel-focus Loss
por: Lu, Yunfan, et al.
Publicado: (2024)

CoPRS: Learning Positional Prior from Chain-of-Thought for Reasoning Segmentation
por: Lu, Zhenyu, et al.
Publicado: (2025)

PixelatedScatter: Arbitrary-level Visual Abstraction for Large-scale Multiclass Scatterplots
por: Guo, Ziheng, et al.
Publicado: (2025)

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

Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking
por: Xu, Zhengfei, et al.
Publicado: (2024)

PianoMotion10M: Dataset and Benchmark for Hand Motion Generation in Piano Performance
por: Gan, Qijun, et al.
Publicado: (2024)

FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally
por: Shen, Qiuhong, et al.
Publicado: (2024)

Harmonizing Pixels and Melodies: Maestro-Guided Film Score Generation and Composition Style Transfer
por: Qi, F., et al.
Publicado: (2024)

Grounded Chain-of-Thought for Multimodal Large Language Models
por: Wu, Qiong, et al.
Publicado: (2025)

D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos
por: Zhang, Wenkang, et al.
Publicado: (2025)

Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
por: Zhang, Dongxu, et al.
Publicado: (2026)

EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering
por: Zhou, Sheng, et al.
Publicado: (2025)

StableMoFusion: Towards Robust and Efficient Diffusion-based Motion Generation Framework
por: Huang, Yiheng, et al.
Publicado: (2024)

PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-Resolution
por: Mishra, Aradhana, et al.
Publicado: (2025)

Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning
por: Li, Shenshen, et al.
Publicado: (2025)

ReactDiff: Latent Diffusion for Facial Reaction Generation
por: Li, Jiaming, et al.
Publicado: (2025)

SpecFLASH: A Latent-Guided Semi-autoregressive Speculative Decoding Framework for Efficient Multimodal Generation
por: Wang, Zihua, et al.
Publicado: (2025)

ExpLLM: Towards Chain of Thought for Facial Expression Recognition
por: Lan, Xing, et al.
Publicado: (2024)

Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling
por: Wang, Zhihua, et al.
Publicado: (2025)

Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search
por: Yang, Shuyu, et al.
Publicado: (2024)

Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
por: Huang, Youhan, et al.
Publicado: (2026)

Generating Attribute-Aware Human Motions from Textual Prompt
por: Wang, Xinghan, et al.
Publicado: (2025)

CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery
por: Chen, Tung-I, et al.
Publicado: (2026)

ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
por: Cheng, Zihang, et al.
Publicado: (2026)

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks
por: Wu, Jianyu, et al.
Publicado: (2025)

MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation
por: Shi, Haoyuan, et al.
Publicado: (2026)

FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process
por: Bu, Yuyan, et al.
Publicado: (2024)

SCI-Reason: A Dataset with Chain-of-Thought Rationales for Complex Multimodal Reasoning in Academic Areas
por: Ma, Chenghao, et al.
Publicado: (2025)

MAO: Efficient Model-Agnostic Optimization of Prompt Tuning for Vision-Language Models
por: Li, Haoyang, et al.
Publicado: (2025)