Copertina

Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Gao, Junqi, Zhang, Dazhi, Guo, Zhichang, Qi, Biqing, Ran, Yi, Zuo, Wangmeng
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness
di: Gao, Junqi, et al.
Pubblicazione: (2025)

Less is More: Efficient Model Merging with Binary Task Switch
di: Qi, Biqing, et al.
Pubblicazione: (2024)

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability
di: Gao, Junqi, et al.
Pubblicazione: (2024)

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration
di: Gao, Junqi, et al.
Pubblicazione: (2025)

Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
di: Ning, Jie, et al.
Pubblicazione: (2023)

An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
di: Li, Dong, et al.
Pubblicazione: (2024)

Task Vector Quantization for Memory-Efficient Model Merging
di: Kim, Youngeun, et al.
Pubblicazione: (2025)

Enhancing Adversarial Transferability via Information Bottleneck Constraints
di: Qi, Biqing, et al.
Pubblicazione: (2024)

MergeMoE: Efficient Compression of MoE Models via Expert Output Merging
di: Miao, Ruijie, et al.
Pubblicazione: (2025)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
di: Guo, Kuangpu, et al.
Pubblicazione: (2025)

Efficient Visual Transformer by Learnable Token Merging
di: Wang, Yancheng, et al.
Pubblicazione: (2024)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
di: Wang, Jiapeng, et al.
Pubblicazione: (2026)

SMR: State Memory Replay for Long Sequence Modeling
di: Qi, Biqing, et al.
Pubblicazione: (2024)

DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
di: Yoshida, Kotaro, et al.
Pubblicazione: (2025)

Exploring Adversarial Robustness of Deep State Space Models
di: Qi, Biqing, et al.
Pubblicazione: (2024)

Experimental Analysis of Large-scale Learnable Vector Storage Compression
di: Zhang, Hailin, et al.
Pubblicazione: (2023)

FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantization
di: Liu, Fangxin, et al.
Pubblicazione: (2025)

Task Singular Vectors: Reducing Task Interference in Model Merging
di: Gargiulo, Antonio Andrea, et al.
Pubblicazione: (2024)

Localizing Task Information for Improved Model Merging and Compression
di: Wang, Ke, et al.
Pubblicazione: (2024)

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
di: Qi, Biqing, et al.
Pubblicazione: (2024)

LPT++: Efficient Training on Mixture of Long-tailed Experts
di: Dong, Bowen, et al.
Pubblicazione: (2024)

Fast and Slow Gradient Approximation for Binary Neural Network Optimization
di: Chen, Xinquan, et al.
Pubblicazione: (2024)

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
di: Cheng, Runxi, et al.
Pubblicazione: (2025)

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
di: Li, Qizhang, et al.
Pubblicazione: (2024)

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
di: Li, Fangyuan, et al.
Pubblicazione: (2026)

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
di: Li, Lujun, et al.
Pubblicazione: (2025)

Vectorized Attention with Learnable Encoding for Quantum Transformer
di: Guo, Ziqing, et al.
Pubblicazione: (2025)

Interactive Continual Learning: Fast and Slow Thinking
di: Qi, Biqing, et al.
Pubblicazione: (2024)

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization
di: Lee, Jung Hyun, et al.
Pubblicazione: (2023)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
di: Yang, Enneng, et al.
Pubblicazione: (2023)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
di: He, Yifei, et al.
Pubblicazione: (2024)

AutoCompress: Critical Layer Isolation for Efficient Transformer Compression
di: Thorat, Archit
Pubblicazione: (2026)

Superpose Task-specific Features for Model Merging
di: Qiu, Haiquan, et al.
Pubblicazione: (2025)

Improved Generation of Adversarial Examples Against Safety-aligned LLMs
di: Li, Qizhang, et al.
Pubblicazione: (2024)

Multi-Task Model Merging via Adaptive Weight Disentanglement
di: Xiong, Feng, et al.
Pubblicazione: (2024)

Improving Transferability of Adversarial Examples via Bayesian Attacks
di: Li, Qizhang, et al.
Pubblicazione: (2023)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
di: Shen, Li, et al.
Pubblicazione: (2024)

Tiled Bit Networks: Sub-Bit Neural Network Compression Through Reuse of Learnable Binary Vectors
di: Gorbett, Matt, et al.
Pubblicazione: (2024)

SpecMol: A Spectroscopy-Grounded Foundation Model for Multi-Task Molecular Learning
di: Shen, Shuaike, et al.
Pubblicazione: (2025)

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
di: Zeng, Siqi, et al.
Pubblicazione: (2025)