Image de couverture de livre

Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Du, Zijian, Rybakov, Oleg
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Not All Pixels Are Equal: Pixel-wise Meta-Learning for Medical Segmentation with Noisy Labels
par: Mu, Chenyu, et autres
Publié: (2025)

Not All Tokens are Guided Equal: Improving Guidance in Visual Autoregressive Models
par: Nguyen, Ky Dan, et autres
Publié: (2025)

AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation
par: Deb, Prantik, et autres
Publié: (2026)

SLA2: Sparse-Linear Attention with Learnable Routing and QAT
par: Zhang, Jintao, et autres
Publié: (2026)

Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
par: Wang, Hongjun, et autres
Publié: (2025)

Empirical Recipes for Efficient and Compact Vision-Language Models
par: Huang, Jiabo, et autres
Publié: (2026)

Segment Any Anomaly without Training via Hybrid Prompt Regularization
par: Cao, Yunkang, et autres
Publié: (2023)

DL-QAT: Weight-Decomposed Low-Rank Quantization-Aware Training for Large Language Models
par: Ke, Wenjin, et autres
Publié: (2025)

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation
par: Gui, Guan, et autres
Publié: (2025)

Multi-modality Anomaly Segmentation on the Road
par: Gao, Heng, et autres
Publié: (2025)

Not All Splits Are Equal: Rethinking Attribute Generalization Across Unrelated Categories
par: Fircă, Liviu Nicolae, et autres
Publié: (2025)

A4-Unet: Deformable Multi-Scale Attention Network for Brain Tumor Segmentation
par: Wang, Ruoxin, et autres
Publié: (2024)

Video Understanding by Design: How Datasets Shape Architectures and Insights
par: Wang, Lei, et autres
Publié: (2025)

VLANeXt: Recipes for Building Strong VLA Models
par: Wu, Xiao-Ming, et autres
Publié: (2026)

Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly
par: Du, Hang, et autres
Publié: (2024)

ArchShapeNet:An Interpretable 3D-CNN Framework for Evaluating Architectural Shapes
par: Yin, Jun, et autres
Publié: (2025)

TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility
par: Motamed, Saman, et autres
Publié: (2025)

XAI-Enhanced Semantic Segmentation Models for Visual Quality Inspection
par: Clement, Tobias, et autres
Publié: (2024)

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation
par: Shenaj, Donald, et autres
Publié: (2026)

Ideal Registration? Segmentation is All You Need
par: Chen, Xiang, et autres
Publié: (2025)

Find Them All: Unveiling MLLMs for Versatile Person Re-identification
par: Li, Jinhao, et autres
Publié: (2025)

AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models
par: Qu, Zhen, et autres
Publié: (2026)

IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
par: Zheng, Haoyu, et autres
Publié: (2026)

Two Steps Are All You Need: Efficient 3D Point Cloud Anomaly Detection with Consistency Models
par: A, Pranav, et autres
Publié: (2026)

Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation
par: Ren, Zhiyao, et autres
Publié: (2025)

Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning
par: Chen, Ruizhe, et autres
Publié: (2025)

Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly
par: Du, Hang, et autres
Publié: (2024)

Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation
par: Lee, Mingyu, et autres
Publié: (2024)

Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation
par: Stangl, Kevin, et autres
Publié: (2024)

ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation
par: Li, Shengze, et autres
Publié: (2024)

MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
par: Gao, Bin-Bin
Publié: (2025)

Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation
par: Park, SoYoung, et autres
Publié: (2025)

Flexiffusion: Training-Free Segment-Wise Neural Architecture Search for Efficient Diffusion Models
par: Huang, Hongtao, et autres
Publié: (2025)

LoD Sketch Extraction from Architectural Models Using Generative AI: Dataset Construction for Multi-Level Architectural Design Generation
par: Du, Xusheng, et autres
Publié: (2026)

Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection
par: Mao, Guoxuan, et autres
Publié: (2025)

Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
par: Jia, Ziheng, et autres
Publié: (2025)

Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detection
par: Song, Shixuan, et autres
Publié: (2025)

All in One: Visual-Description-Guided Unified Point Cloud Segmentation
par: Han, Zongyan, et autres
Publié: (2025)

Restoration Adaptation for Semantic Segmentation on Low Quality Images
par: Guan, Kai, et autres
Publié: (2026)

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
par: Liu, Jiawei, et autres
Publié: (2025)