Imagen de Portada

SynQ: Accurate Zero-shot Quantization by Synthesis-aware Fine-tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Minjun, Kim, Jongjin, Kang, U
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LampQ: Towards Accurate Layer-wise Mixed Precision Quantization for Vision Transformers
por: Kim, Minjun, et al.
Publicado: (2025)

Zero-shot Quantization: A Comprehensive Survey
por: Kim, Minjun, et al.
Publicado: (2025)

StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
por: Kim, Younghyun, et al.
Publicado: (2025)

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
por: Li, Juncheng, et al.
Publicado: (2023)

Robust Fine-tuning of Zero-shot Models via Variance Reduction
por: Zhu, Beier, et al.
Publicado: (2024)

Efficient and Versatile Robust Fine-Tuning of Zero-shot Models
por: Kim, Sungyeon, et al.
Publicado: (2024)

Visual Diversity and Region-aware Prompt Learning for Zero-shot HOI Detection
por: Yang, Chanhyeong, et al.
Publicado: (2025)

SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning
por: Kim, Si-Woo, et al.
Publicado: (2025)

Task-Specific Zero-shot Quantization-Aware Training for Object Detection
por: Li, Changhao, et al.
Publicado: (2025)

Semantic-aware Adversarial Fine-tuning for CLIP
por: Zhang, Jiacheng, et al.
Publicado: (2026)

Zero-shot Text-guided Infinite Image Synthesis with LLM guidance
por: Kwon, Soyeong, et al.
Publicado: (2024)

HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer
por: Kim, Minjun, et al.
Publicado: (2026)

VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting
por: Kang, Seunggu, et al.
Publicado: (2023)

Cross-View Completion Models are Zero-shot Correspondence Estimators
por: An, Honggyu, et al.
Publicado: (2024)

GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection
por: Kim, Donghyeong, et al.
Publicado: (2025)

GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis
por: Kang, Minjun, et al.
Publicado: (2026)

Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection
por: Lee, Hyogun, et al.
Publicado: (2025)

Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
por: Chen, Yujie, et al.
Publicado: (2025)

Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes
por: Kim, Yehna, et al.
Publicado: (2025)

EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing
por: Yang, Xiangpeng, et al.
Publicado: (2024)

InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation
por: Kim, Chanran, et al.
Publicado: (2024)

Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
por: Feng, Weilun, et al.
Publicado: (2025)

Language-only Efficient Training of Zero-shot Composed Image Retrieval
por: Gu, Geonmo, et al.
Publicado: (2023)

Sharpness-Aware Data Generation for Zero-shot Quantization
por: Hoang-Anh, Dung, et al.
Publicado: (2025)

PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning
por: Wang, Yankai, et al.
Publicado: (2026)

SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning
por: Dai, Zhewei, et al.
Publicado: (2024)

Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognition
por: Zhu, Anqi, et al.
Publicado: (2024)

Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
por: Liu, Weihuang, et al.
Publicado: (2024)

ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
por: Zhao, Tianchen, et al.
Publicado: (2024)

Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection
por: Zhu, Jiawen, et al.
Publicado: (2024)

Fine-gained Zero-shot Video Sampling
por: Chen, Dengsheng, et al.
Publicado: (2024)

Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers
por: Chen, Lei, et al.
Publicado: (2024)

GenQ: Quantization in Low Data Regimes with Generative Synthetic Data
por: Li, Yuhang, et al.
Publicado: (2023)

Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval
por: Lyou, Eunyi, et al.
Publicado: (2024)

Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignment
por: Kim, Namu, et al.
Publicado: (2025)

Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition
por: Do, Jeonghyeok, et al.
Publicado: (2024)

CoVFT: Context-aware Visual Fine-tuning for Multimodal Large Language Models
por: Zhou, Nan, et al.
Publicado: (2026)

AnimeAdapter: Fine-grained and Consistent Zero-shot Anime Character Generation
por: Han, Yixuan
Publicado: (2026)

Q-SAM2: Accurate Quantization for Segment Anything Model 2
por: Farronato, Nicola, et al.
Publicado: (2025)

VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
por: Liu, Xuyang, et al.
Publicado: (2023)