Copertina

Model Reprogramming Outperforms Fine-tuning on Out-of-distribution Data in Text-Image Encoders

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Geng, Andrew, Chen, Pin-Yu
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection
di: Shen, Han, et al.
Pubblicazione: (2024)

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing
di: Kim, Hyunjae, et al.
Pubblicazione: (2024)

Fundamental Safety-Capability Trade-offs in Fine-tuning Large Language Models
di: Chen, Pin-Yu, et al.
Pubblicazione: (2025)

DreamBlend: Advancing Personalized Fine-tuning of Text-to-Image Diffusion Models
di: Ram, Shwetha, et al.
Pubblicazione: (2024)

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
di: Kim, Kyuyoung, et al.
Pubblicazione: (2024)

A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models
di: Miao, Yanting, et al.
Pubblicazione: (2025)

Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models
di: Hsu, Chia-Yi, et al.
Pubblicazione: (2024)

Representation Learning of Daily Movement Data Using Text Encoders
di: Capstick, Alexander, et al.
Pubblicazione: (2024)

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
di: Hsiung, Lei, et al.
Pubblicazione: (2025)

Efficient Model Development through Fine-tuning Transfer
di: Lin, Pin-Jie, et al.
Pubblicazione: (2025)

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
di: Chowdhury, Mohammed Nowaz Rabbani, et al.
Pubblicazione: (2024)

Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
di: Lee, Yu-Ang, et al.
Pubblicazione: (2026)

Match & Choose: Model Selection Framework for Fine-tuning Text-to-Image Diffusion Models
di: Lewandowski, Basile, et al.
Pubblicazione: (2025)

Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction
di: Ye, Zesheng, et al.
Pubblicazione: (2025)

When Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective
di: Tsao, Hsi-Ai, et al.
Pubblicazione: (2024)

Efficiently Estimating Data Efficiency for Language Model Fine-tuning
di: Je, Gyung Hyun, et al.
Pubblicazione: (2025)

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
di: Zeng, Cong, et al.
Pubblicazione: (2025)

Model Reprogramming Demystified: A Neural Tangent Kernel Perspective
di: Chung, Ming-Yu, et al.
Pubblicazione: (2025)

ToonOut: Fine-tuned Background-Removal for Anime Characters
di: Muratori, Matteo, et al.
Pubblicazione: (2025)

When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning
di: Deng, Mengyi, et al.
Pubblicazione: (2025)

A Simple and Effective Reinforcement Learning Method for Text-to-Image Diffusion Fine-tuning
di: Gupta, Shashank, et al.
Pubblicazione: (2025)

Efficient Adjoint Matching for Fine-tuning Diffusion Models
di: Shin, Jeongwoo, et al.
Pubblicazione: (2026)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
di: Chen, Yukun, et al.
Pubblicazione: (2025)

Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
di: Jin, Ming, et al.
Pubblicazione: (2023)

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
di: Zhou, Huichi, et al.
Pubblicazione: (2025)

Sparse Gradient Compression for Fine-Tuning Large Language Models
di: Yang, David H., et al.
Pubblicazione: (2025)

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
di: Chen, Sirui, et al.
Pubblicazione: (2026)

Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams
di: Garcia, Cristiano Mesquita, et al.
Pubblicazione: (2024)

The Importance of Online Data: Understanding Preference Fine-tuning via Coverage
di: Song, Yuda, et al.
Pubblicazione: (2024)

Mixture Data for Training Cannot Ensure Out-of-distribution Generalization
di: Zhang, Songming, et al.
Pubblicazione: (2023)

BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification
di: Wang, Yi-Siang, et al.
Pubblicazione: (2026)

Out-of-distribution materials property prediction using adversarial learning based fine-tuning
di: Li, Qinyang, et al.
Pubblicazione: (2024)

Can Muon Fine-tune Adam-Pretrained Models?
di: Qu, Xingyu, et al.
Pubblicazione: (2026)

Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
di: Ma, Huan, et al.
Pubblicazione: (2023)

Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers
di: Breejen, Felix den, et al.
Pubblicazione: (2024)

Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
di: Zhang, Jiale, et al.
Pubblicazione: (2025)

Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks
di: Wang, Danny, et al.
Pubblicazione: (2025)

Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees
di: Rahiminasab, Zahra, et al.
Pubblicazione: (2025)

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
di: Yuan, Haonan, et al.
Pubblicazione: (2025)

On the Loss of Context-awareness in General Instruction Fine-tuning
di: Wang, Yihan, et al.
Pubblicazione: (2024)