Cover Image

On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lyu, Siyi, Liu, Quan, Yan, Feng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computational Complexity
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

On Computational Limits of FlowAR Models: Expressivity and Efficiency
by: Cao, Yang, et al.
Published: (2025)

On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis
by: Ke, Yekun, et al.
Published: (2025)

Automatic Channel Pruning for Multi-Head Attention
by: Lee, Eunho, et al.
Published: (2024)

fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
by: Ohm, Tillmann, et al.
Published: (2024)

Limits of Spatial Imagery Reasoning in Frontier LLM Models
by: Hayashi, Sergio Y., et al.
Published: (2026)

AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
by: Liu, Dongrui, et al.
Published: (2026)

OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning
by: Thwal, Chu Myaet, et al.
Published: (2024)

SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images
by: Liu, Zishan, et al.
Published: (2026)

Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learning
by: Zhao, Botong., et al.
Published: (2025)

On the Limits of Token Reduction for Efficient Unified Vision Language Training
by: Chen, Siyi, et al.
Published: (2026)

CoV: Chain-of-View Prompting for Spatial Reasoning
by: Zhao, Haoyu, et al.
Published: (2026)

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis
by: Ni, Zanlin, et al.
Published: (2024)

EarthSpatialBench: Benchmarking Spatial Reasoning Capabilities of Multimodal LLMs on Earth Imagery
by: Xu, Zelin, et al.
Published: (2026)

Aerial Vision-Language Navigation with a Unified Framework for Spatial, Temporal and Embodied Reasoning
by: Xu, Huilin, et al.
Published: (2025)

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition
by: Hu, Youbing, et al.
Published: (2024)

MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
by: Pan, Zhenyu, et al.
Published: (2025)

Uncovering the Text Embedding in Text-to-Image Diffusion Models
by: Yu, Hu, et al.
Published: (2024)

Texture Image Synthesis Using Spatial GAN Based on Vision Transformers
by: Salari, Elahe, et al.
Published: (2025)

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes
by: Liu, Tianhui, et al.
Published: (2026)

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
by: Wu, Junfei, et al.
Published: (2025)

Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps
by: Gao, Xiangjun, et al.
Published: (2026)

BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models
by: Tang, Jianting, et al.
Published: (2025)

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
by: Li, Hongxing, et al.
Published: (2025)

Algorithm Research of ELMo Word Embedding and Deep Learning Multimodal Transformer in Image Description
by: Cheng, Xiaohan, et al.
Published: (2024)

Exploring Non-Local Spatial-Angular Correlations with a Hybrid Mamba-Transformer Framework for Light Field Super-Resolution
by: Liu, Haosong, et al.
Published: (2025)

DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation
by: Phung, Hao, et al.
Published: (2024)

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning
by: Guo, Xingang, et al.
Published: (2025)

SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis
by: Feng, Bin, et al.
Published: (2025)

UrbanGraphEmbeddings: Learning and Evaluating Spatially Grounded Multimodal Embeddings for Urban Science
by: Zhang, Jie, et al.
Published: (2026)

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
by: Chen, Zhangquan, et al.
Published: (2025)

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
by: Duan, Chengqi, et al.
Published: (2025)

Multimodal Mathematical Reasoning Embedded in Aerial Vehicle Imagery: Benchmarking, Analysis, and Exploration
by: Zhou, Yue, et al.
Published: (2025)

VERDI: VLM-Embedded Reasoning for Autonomous Driving
by: Feng, Bowen, et al.
Published: (2025)

Attention in Space: Functional Roles of VLM Heads for Spatial Reasoning
by: Ma, Xueqi, et al.
Published: (2026)

Sub-token ViT Embedding via Stochastic Resonance Transformers
by: Lao, Dong, et al.
Published: (2023)

Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation
by: Chen, Weiming, et al.
Published: (2026)

Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
by: Kim, Seungwook, et al.
Published: (2026)

UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding
by: Feng, Jie, et al.
Published: (2025)

Make Geometry Matter for Spatial Reasoning
by: Zhang, Shihua, et al.
Published: (2026)

Geometrically-Constrained Agent for Spatial Reasoning
by: Chen, Zeren, et al.
Published: (2025)