Imagen de Portada

Tackling the Abstraction and Reasoning Corpus with Vision Transformers: the Importance of 2D Representation, Positions, and Objects

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Wenhao, Xu, Yudong, Sanner, Scott, Khalil, Elias Boutros
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representations
por: Xu, Yudong, et al.
Publicado: (2023)

A 2D Semantic-Aware Position Encoding for Vision Transformers
por: Chen, Xi, et al.
Publicado: (2025)

Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
por: Aniraj, Ananthu, et al.
Publicado: (2025)

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers
por: Xu, Xuwei, et al.
Publicado: (2025)

GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation
por: Xu, Xuwei, et al.
Publicado: (2023)

Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction
por: Xu, Yudong W., et al.
Publicado: (2025)

C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning
por: Ye, Guanting, et al.
Publicado: (2026)

Weierstrass Positional Encoding for Vision Transformers
por: Xin, Zhihang, et al.
Publicado: (2026)

Representation Learning with Adaptive Superpixel Coding
por: Khalil, Mahmoud, et al.
Publicado: (2025)

Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
por: Xu, Qi, et al.
Publicado: (2025)

Human-Like Coarse Object Representations in Vision Models
por: Gizdov, Andrey, et al.
Publicado: (2026)

ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task
por: Khalil, Ahmad, et al.
Publicado: (2025)

CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
por: Pothiraj, Atin, et al.
Publicado: (2025)

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection
por: Yu, Jiangyong, et al.
Publicado: (2025)

Representation Separation for Semantic Segmentation with Vision Transformers
por: Hong, Yuanduo, et al.
Publicado: (2022)

Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection
por: Kumar, Yogesh, et al.
Publicado: (2025)

On Extending Semantic Abstraction for Efficient Search of Hidden Objects
por: Pais, Tasha, et al.
Publicado: (2025)

OCTrack: Benchmarking the Open-Corpus Multi-Object Tracking
por: Qian, Zekun, et al.
Publicado: (2024)

Synthesizing 3D Abstractions by Inverting Procedural Buildings with Transformers
por: Dax, Maximilian, et al.
Publicado: (2025)

MM-IQ: Benchmarking Human-Like Abstraction and Reasoning in Multimodal Models
por: Cai, Huanqia, et al.
Publicado: (2025)

LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers
por: Chowdhury, Md Abtahi Majeed, et al.
Publicado: (2025)

Mitigating Bias with Words: Inducing Demographic Ambiguity in Face Recognition Templates by Text Encoding
por: Chettaoui, Tahar, et al.
Publicado: (2025)

Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
por: Lepori, Michael A., et al.
Publicado: (2024)

Keypoint Abstraction using Large Models for Object-Relative Imitation Learning
por: Fang, Xiaolin, et al.
Publicado: (2024)

Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
por: Sinha, Rohit, et al.
Publicado: (2026)

Quantum Inverse Contextual Vision Transformers (Q-ICVT): A New Frontier in 3D Object Detection for AVs
por: Dharavath, Sanjay Bhargav, et al.
Publicado: (2024)

The Progression of Transformers from Language to Vision to MOT: A Literature Review on Multi-Object Tracking with Transformers
por: Kamboj, Abhi
Publicado: (2024)

AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer
por: Dam, Tanmoy, et al.
Publicado: (2024)

CityCube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments
por: Xu, Haotian, et al.
Publicado: (2026)

CRD: Collaborative Representation Distance for Practical Anomaly Detection
por: Han, Chao, et al.
Publicado: (2023)

COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking
por: Zhang, Chunhui, et al.
Publicado: (2025)

SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer
por: Li, Wenxi, et al.
Publicado: (2025)

Surformer v1: Transformer-Based Surface Classification Using Tactile and Vision Features
por: Kansana, Manish, et al.
Publicado: (2025)

CoRE: Concept-Reasoning Expansion for Continual Brain Lesion Segmentation
por: Chen, Qianqian, et al.
Publicado: (2026)

Cross-Axis Transformer with 3D Rotary Positional Embeddings
por: Erickson, Lily
Publicado: (2023)

Extending 6D Object Pose Estimators for Stereo Vision
por: Pöllabauer, Thomas, et al.
Publicado: (2024)

Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers
por: Gandhi, Sanket, et al.
Publicado: (2024)

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging
por: Shams, Montasir, et al.
Publicado: (2025)

Symbolic Rule Extraction from Attention-Guided Sparse Representations in Vision Transformers
por: Padalkar, Parth, et al.
Publicado: (2025)

IFViT: Interpretable Fixed-Length Representation for Fingerprint Matching via Vision Transformer
por: Qiu, Yuhang, et al.
Publicado: (2024)