Imagen de Portada

Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nguyen, Tuc, Le, Thai
Formato:	Preprint
Publicado:	2024
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers
por: Nguyen, Tuc, et al.
Publicado: (2024)

ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning
por: Nguyen, Tuc, et al.
Publicado: (2026)

Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification
por: Nguyen, Tuc, et al.
Publicado: (2025)

NoMatterXAI: Generating "No Matter What" Alterfactual Examples for Explaining Black-Box Text Classification Models
por: Nguyen, Tuc, et al.
Publicado: (2024)

ShareChat: A Dataset of Chatbot Conversations in the Wild
por: Yan, Yueru, et al.
Publicado: (2025)

Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations
por: Dong, Zican, et al.
Publicado: (2025)

Fast and Effective Weight Update for Pruned Large Language Models
por: Boža, Vladimír
Publicado: (2024)

Topological Data Analysis Applications in Natural Language Processing: A Survey
por: Uchendu, Adaku, et al.
Publicado: (2024)

All-in-One Tuning and Structural Pruning for Domain-Specific LLMs
por: Lu, Lei, et al.
Publicado: (2024)

EditLens: Quantifying the Extent of AI Editing in Text
por: Thai, Katherine, et al.
Publicado: (2025)

MoKA: Mixture of Kronecker Adapters
por: Sadeghi, Mohammadreza, et al.
Publicado: (2025)

Flexible and Effective Mixing of Large Language Models into a Mixture of Domain Experts
por: Lee, Rhui Dih, et al.
Publicado: (2024)

Cluster-Driven Expert Pruning for Mixture-of-Experts Large Language Models
por: Guo, Hongcheng, et al.
Publicado: (2025)

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models
por: Jiang, Songtao, et al.
Publicado: (2024)

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models
por: Siam, M. K. Khalidi, et al.
Publicado: (2026)

DetectAnyLLM: Towards Generalizable and Robust Detection of Machine-Generated Text Across Domains and Models
por: Fu, Jiachen, et al.
Publicado: (2025)

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs
por: Fu, Yao, et al.
Publicado: (2025)

MoDEM: Mixture of Domain Expert Models
por: Simonds, Toby, et al.
Publicado: (2024)

FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning
por: Bhattacharyya, Chaitali, et al.
Publicado: (2025)

signwriting-evaluation: Effective Sign Language Evaluation via SignWriting
por: Moryossef, Amit, et al.
Publicado: (2024)

Pruning and Distilling Mixture-of-Experts into Dense Language Models
por: Kim, Junhyuck, et al.
Publicado: (2026)

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies
por: Ma, Sibo, et al.
Publicado: (2025)

Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
por: Li, Chengzhengxu, et al.
Publicado: (2024)

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration
por: Wu, Guangxin, et al.
Publicado: (2026)

MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models
por: Cao, Jie, et al.
Publicado: (2025)

RAID: Refusal-Aware and Integrated Decoding for Jailbreaking LLMs
por: Nguyen, Tuan T., et al.
Publicado: (2025)

Towards Domain Specification of Embedding Models in Medicine
por: Khodadad, Mohammad, et al.
Publicado: (2025)

Pruning as a Domain-specific LLM Extractor
por: Zhang, Nan, et al.
Publicado: (2024)

The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints
por: Le, Thanh-Dung, et al.
Publicado: (2024)

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs
por: Chen, Hanting, et al.
Publicado: (2025)

MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models
por: Nguyen, Thai-Binh, et al.
Publicado: (2024)

MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
por: Liao, Yusheng, et al.
Publicado: (2024)

READ: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling
por: Nguyen, Thong, et al.
Publicado: (2023)

DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling
por: Quan, Shanghaoran
Publicado: (2024)

GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings
por: Tang, Yixuan, et al.
Publicado: (2025)

Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications
por: Zhezherau, Alexey, et al.
Publicado: (2024)

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions
por: Wang, Weiqi, et al.
Publicado: (2024)

DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning
por: Bai, Sikai, et al.
Publicado: (2025)

Lightweight Zero-shot Text-to-Speech with Mixture of Adapters
por: Fujita, Kenichi, et al.
Publicado: (2024)

CLIP-Adapter: Better Vision-Language Models with Feature Adapters
por: Gao, Peng, et al.
Publicado: (2021)