Copertina

SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Yifan, Zhang, Zhen, Swaminathan, Rupak Vignesh, Liu, Jing, Susanj, Nathan, Zhang, Zheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computation and Language Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
di: Solgi, Ryan, et al.
Pubblicazione: (2025)

Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
di: Solgi, Ryan, et al.
Pubblicazione: (2025)

Wanda++: Pruning Large Language Models via Regional Gradients
di: Yang, Yifan, et al.
Pubblicazione: (2025)

LLaMA based Punctuation Restoration With Forward Pass Only Decoding
di: Pang, Yutong, et al.
Pubblicazione: (2024)

MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models
di: Zhang, Zhen, et al.
Pubblicazione: (2025)

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
di: Wan, Guancheng, et al.
Pubblicazione: (2025)

Fine-Tuning Language Models with Just Forward Passes
di: Malladi, Sadhika, et al.
Pubblicazione: (2023)

Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes
di: Christ, Bryan R., et al.
Pubblicazione: (2024)

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting
di: Watts, Ishaan, et al.
Pubblicazione: (2026)

Zeroth-Order Sharpness-Aware Learning with Exponential Tilting
di: Gong, Xuchen, et al.
Pubblicazione: (2025)

TRAM: Bridging Trust Regions and Sharpness Aware Minimization
di: Sherborne, Tom, et al.
Pubblicazione: (2023)

SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning
di: Pandey, Prabhat, et al.
Pubblicazione: (2025)

Understanding GUI Agent Localization Biases through Logit Sharpness
di: Tao, Xingjian, et al.
Pubblicazione: (2025)

CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass
di: Zhang, Bowen, et al.
Pubblicazione: (2025)

Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
di: Fang, Xianya, et al.
Pubblicazione: (2026)

TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models
di: Adhikari, Rabin, et al.
Pubblicazione: (2024)

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
di: Hong, Xiangyu, et al.
Pubblicazione: (2025)

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
di: Fan, Chongyu, et al.
Pubblicazione: (2025)

IAPT: Instruction-Aware Prompt Tuning for Large Language Models
di: Zhu, Wei, et al.
Pubblicazione: (2024)

Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models
di: Xu, Qinwu, et al.
Pubblicazione: (2026)

Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts
di: Hong, Haodong, et al.
Pubblicazione: (2024)

Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Pass
di: Popovič, Nicholas, et al.
Pubblicazione: (2025)

For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs
di: Deng, Wenlong, et al.
Pubblicazione: (2025)

Patch-Prompt Aligned Bayesian Prompt Tuning for Vision-Language Models
di: Liu, Xinyang, et al.
Pubblicazione: (2023)

Conflict-Resolving and Sharpness-Aware Minimization for Generalized Knowledge Editing with Multiple Updates
di: Nguyen, Duy, et al.
Pubblicazione: (2026)

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks
di: Lyu, Yuanjie, et al.
Pubblicazione: (2025)

Historical Test-time Prompt Tuning for Vision Foundation Models
di: Zhang, Jingyi, et al.
Pubblicazione: (2024)

Optimizing Soft Prompt Tuning via Structural Evolution
di: Huang, Zhenzhen, et al.
Pubblicazione: (2026)

FAAST: Forward-Only Associative Learning via Closed-Form Fast Weights for Test-Time Supervised Adaptation
di: Bao, Guangsheng, et al.
Pubblicazione: (2026)

Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning
di: Fang, Yangui, et al.
Pubblicazione: (2025)

Governance-Aware Hybrid Fine-Tuning for Multilingual Large Language Models
di: Qi, Haomin, et al.
Pubblicazione: (2025)

Iterative Forward Tuning Boosts In-Context Learning in Language Models
di: Yang, Jiaxi, et al.
Pubblicazione: (2023)

VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
di: Kamoi, Ryo, et al.
Pubblicazione: (2024)

Sharpness-Aware Minimization in Genetic Programming
di: Bakurov, Illya, et al.
Pubblicazione: (2024)

Few-Shot Query Intent Detection via Relation-Aware Prompt Learning
di: Zhang, Liang, et al.
Pubblicazione: (2025)

ColorBlindnessEval: Can Vision-Language Models Pass Color Blindness Tests?
di: Ling, Zijian, et al.
Pubblicazione: (2025)

AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning
di: Yang, Yifan, et al.
Pubblicazione: (2024)

Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
di: Liu, Yong, et al.
Pubblicazione: (2024)

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
di: Jie, Shibo, et al.
Pubblicazione: (2024)

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
di: Singla, Somanshu, et al.
Pubblicazione: (2024)