Copertina

Training-Free Pretrained Model Merging

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Xu, Zhengqi, Yuan, Ke, Wang, Huiqiong, Wang, Yong, Song, Mingli, Song, Jie
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?
di: Xie, Yuechen, et al.
Pubblicazione: (2025)

Sampling-Aware Quantization for Diffusion Models
di: Zeng, Qian, et al.
Pubblicazione: (2025)

LG-CAV: Train Any Concept Activation Vector with Language Guidance
di: Huang, Qihan, et al.
Pubblicazione: (2024)

Deep Feature Response Discriminative Calibration
di: Xu, Wenxiang, et al.
Pubblicazione: (2024)

On the Concept Trustworthiness in Concept Bottleneck Models
di: Huang, Qihan, et al.
Pubblicazione: (2024)

Evolutionary Negative Module Pruning for Better LoRA Merging
di: Cao, Anda, et al.
Pubblicazione: (2026)

Diffusion Model Quantization: A Review
di: Zeng, Qian, et al.
Pubblicazione: (2025)

Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models
di: Wang, Xuanhan, et al.
Pubblicazione: (2025)

RS3DBench: A Comprehensive Benchmark for 3D Spatial Perception in Remote Sensing
di: Wang, Jiayu, et al.
Pubblicazione: (2025)

Training-Free Model Merging for Multi-target Domain Adaptation
di: Li, Wenyi, et al.
Pubblicazione: (2024)

Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey
di: Wang, Gaoang, et al.
Pubblicazione: (2022)

D$^2$-DPM: Dual Denoising for Quantized Diffusion Probabilistic Models
di: Zeng, Qian, et al.
Pubblicazione: (2025)

Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation
di: Li, Ping, et al.
Pubblicazione: (2023)

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
di: Huang, Qihan, et al.
Pubblicazione: (2025)

Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning
di: Li, Ping, et al.
Pubblicazione: (2024)

Sample-level Adaptive Knowledge Distillation for Action Recognition
di: Li, Ping, et al.
Pubblicazione: (2025)

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
di: Wang, Haiping, et al.
Pubblicazione: (2023)

CogVLM: Visual Expert for Pretrained Language Models
di: Wang, Weihan, et al.
Pubblicazione: (2023)

Dataset Ownership Verification for Pre-trained Masked Models
di: Xie, Yuechen, et al.
Pubblicazione: (2025)

Physical Autoregressive Model for Robotic Manipulation without Action Pretraining
di: Song, Zijian, et al.
Pubblicazione: (2025)

MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation
di: Yang, Yanwu, et al.
Pubblicazione: (2025)

Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference
di: Gao, Yuan, et al.
Pubblicazione: (2024)

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
di: Song, Tianhui, et al.
Pubblicazione: (2025)

Training-Free Large Model Priors for Multiple-in-One Image Restoration
di: He, Xuanhua, et al.
Pubblicazione: (2024)

FREE-Merging: Fourier Transform for Efficient Model Merging
di: Zheng, Shenghe, et al.
Pubblicazione: (2024)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
di: Hu, Taihang, et al.
Pubblicazione: (2024)

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
di: Huang, Qihan, et al.
Pubblicazione: (2024)

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks
di: Hu, Jiacong, et al.
Pubblicazione: (2022)

Rethinking Token Reduction for Large Vision-Language Models
di: Wang, Yi, et al.
Pubblicazione: (2026)

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls
di: Xu, Qianxun, et al.
Pubblicazione: (2026)

Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
di: Chang, Gengjia, et al.
Pubblicazione: (2026)

Training-Free Image Editing with Visual Context Integration and Concept Alignment
di: Song, Rui, et al.
Pubblicazione: (2026)

$D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation
di: Wang, Ruizhi, et al.
Pubblicazione: (2026)

FreeRet: MLLMs as Training-Free Retrievers
di: Zhu, Yuhan, et al.
Pubblicazione: (2025)

SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
di: Utintu, Chaitat, et al.
Pubblicazione: (2024)

Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2025)

BachVid: Training-Free Video Generation with Consistent Background and Character
di: Yan, Han, et al.
Pubblicazione: (2025)

Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
di: Han, Chaolei, et al.
Pubblicazione: (2025)

On the Evaluation Consistency of Attribution-based Explanations
di: Duan, Jiarui, et al.
Pubblicazione: (2024)

LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
di: Wang, Xinyu, et al.
Pubblicazione: (2026)