Imagen de Portada

Geometric Decoupling: Diagnosing the Structural Instability of Latent

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liang, Yuanbang, Chen, Zhengwen, Lai, Yu-Kun
Formato:	Preprint
Publicado:	2026
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

GMapLatent: Geometric Mapping in Latent Space
por: Zeng, Wei, et al.
Publicado: (2025)

ReLE: A Scalable System and Structured Benchmark for Diagnosing Capability Anisotropy in Chinese LLMs
por: Fang, Rui, et al.
Publicado: (2026)

Native and Compact Structured Latents for 3D Generation
por: Xiang, Jianfeng, et al.
Publicado: (2025)

Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
por: Ma, Yanbiao, et al.
Publicado: (2025)

MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion
por: Shin, Minjung, et al.
Publicado: (2025)

Latent Action Control for Reasoning-Guided Unified Image Generation
por: Zhai, Fuxiang, et al.
Publicado: (2026)

DO-Bench: An Attributable Benchmark for Diagnosing Object Hallucination in Vision-Language Models
por: Wang, JiYang, et al.
Publicado: (2026)

CDSA-Net:Collaborative Decoupling of Vascular Structure and Background for High-Fidelity Coronary Digital Subtraction Angiography
por: Li, Si, et al.
Publicado: (2026)

Decoupling Endpoint and Semantic Transition Learning for Zero-Shot Composed Image Retrieval
por: Liu, Mingyu, et al.
Publicado: (2026)

SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstruction
por: Sun, Dai, et al.
Publicado: (2025)

DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
por: Chen, Junyu, et al.
Publicado: (2025)

GraphGSOcc: Semantic-Geometric Graph Transformer with Dynamic-Static Decoupling for 3D Gaussian Splatting-based Occupancy Prediction
por: Song, Ke, et al.
Publicado: (2025)

Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models
por: Peng, Xingkai, et al.
Publicado: (2025)

AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
por: Liu, Tao, et al.
Publicado: (2024)

Scale Decoupled Distillation
por: Luo, Shicai Wei Chunbo Luo Yang
Publicado: (2024)

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance
por: Zeng, Ziyun, et al.
Publicado: (2026)

Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoising
por: Li, Huaqiu, et al.
Publicado: (2025)

From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentation
por: Wang, Tao, et al.
Publicado: (2025)

Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
por: Wang, Junjie, et al.
Publicado: (2025)

Decoupled Data Augmentation for Improving Image Classification
por: Chen, Ruoxin, et al.
Publicado: (2024)

Structured Click Control in Transformer-based Interactive Segmentation
por: Xu, Long, et al.
Publicado: (2024)

MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering
por: Xi, Suyang, et al.
Publicado: (2026)

Monet: Reasoning in Latent Visual Space Beyond Images and Language
por: Wang, Qixun, et al.
Publicado: (2025)

Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
por: Lai, Yixuan, et al.
Publicado: (2026)

Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos
por: Liu, Bowen, et al.
Publicado: (2026)

Geometry OR Tracker: Universal Geometric Operating Room Tracking
por: Shao, Yihua, et al.
Publicado: (2026)

GeoPE:A Unified Geometric Positional Embedding for Structured Tensors
por: Yao, Yupu, et al.
Publicado: (2025)

HiDe: Rethinking The Zoom-IN method in High Resolution MLLMs via Hierarchical Decoupling
por: Liu, Xianjie, et al.
Publicado: (2025)

Adversarially Domain-adaptive Latent Diffusion for Unsupervised Semantic Segmentation
por: Yu, Jongmin, et al.
Publicado: (2024)

DDT: Decoupled Diffusion Transformer
por: Wang, Shuai, et al.
Publicado: (2025)

Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens
por: Yang, Zeyuan, et al.
Publicado: (2025)

DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
por: Chen, Yi, et al.
Publicado: (2026)

Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
por: Nzoyem, Roussel Desmond, et al.
Publicado: (2026)

VITAL: Visual-Semantic Dual Supervision for Enhanced and Interpretable Latent Reasoning in Medical MLLMs
por: Li, Qiaoru, et al.
Publicado: (2026)

Seeking Consensus: Geometric-Semantic On-the-Fly Recalibration for Open-Vocabulary Remote Sensing Semantic Segmentation
por: Wang, Guanchun, et al.
Publicado: (2026)

Vision-Enhanced Time Series Forecasting via Latent Diffusion Models
por: Ruan, Weilin, et al.
Publicado: (2025)

Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
por: Guo, Garvin, et al.
Publicado: (2026)

AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization
por: Yu, Binhe, et al.
Publicado: (2025)

SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning
por: Qi, Biqing, et al.
Publicado: (2024)

Runge-Kutta Approximation and Decoupled Attention for Rectified Flow Inversion and Semantic Editing
por: Chen, Weiming, et al.
Publicado: (2025)