One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging
Fuente:
arXiv
Saved in:
| Main Authors: | Luo, Yingfeng, Lin, Dingyang, Wang, Junxin, Xu, Ziqiang, Chang, Kaiyan, Zheng, Tong, Li, Bei, Ma, Anxiang, Xiao, Tong, Yu, Zhengtao, Zhu, Jingbo |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
by: Luo, Yingfeng, et al.
Published: (2025)
by: Luo, Yingfeng, et al.
Published: (2025)
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
by: Luo, Yingfeng, et al.
Published: (2026)
by: Luo, Yingfeng, et al.
Published: (2026)
Efficient Prompting Methods for Large Language Models: A Survey
by: Chang, Kaiyan, et al.
Published: (2024)
by: Chang, Kaiyan, et al.
Published: (2024)
APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
by: Chang, Kaiyan, et al.
Published: (2026)
by: Chang, Kaiyan, et al.
Published: (2026)
Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
by: Shan, Weiqiao, et al.
Published: (2024)
by: Shan, Weiqiao, et al.
Published: (2024)
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
by: Luo, Yingfeng, et al.
Published: (2025)
by: Luo, Yingfeng, et al.
Published: (2025)
One Size Does Not Fit All: Architecture-Aware Adaptive Batch Scheduling with DEBA
by: Belias, François, et al.
Published: (2025)
by: Belias, François, et al.
Published: (2025)
Leak Detection Strategies: One Size Does Not Fit All
by: Jane M. Arrington
Published: (2026)
by: Jane M. Arrington
Published: (2026)
Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
by: Hofman, Paul, et al.
Published: (2025)
by: Hofman, Paul, et al.
Published: (2025)
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
by: Chang, Kaiyan, et al.
Published: (2025)
by: Chang, Kaiyan, et al.
Published: (2025)
EIT: Enhanced Interactive Transformer
by: Zheng, Tong, et al.
Published: (2022)
by: Zheng, Tong, et al.
Published: (2022)
One Size Does NOT Fit All: On the Importance of Physical Representations for Datalog Evaluation
by: Rassau, Nick, et al.
Published: (2026)
by: Rassau, Nick, et al.
Published: (2026)
Dosing Biologic Drugs for Patients With Obesity: One Size Does Not Fit All
by: Stephen J. Balevic, et al.
Published: (2026)
by: Stephen J. Balevic, et al.
Published: (2026)
Rethinking Stroke Prevention in Atrial Fibrillation: One Size Does not Fit All
by: Panteleimon E. Papakonstantinou, et al.
Published: (2025)
by: Panteleimon E. Papakonstantinou, et al.
Published: (2025)
Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models
by: Mu, Yongyu, et al.
Published: (2025)
by: Mu, Yongyu, et al.
Published: (2025)
One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
by: Lu, Liming, et al.
Published: (2026)
by: Lu, Liming, et al.
Published: (2026)
How To Establish a Parliamentary Research Service: Does One Size Fit All?
by: Verrier, June R.
Published: (2000)
by: Verrier, June R.
Published: (2000)
The One Size Does Not Fit All Approach: Case Studies in Modeling Embedded Librarianship
by: Edford, Rachel L., et al.
Published: (2022)
by: Edford, Rachel L., et al.
Published: (2022)
One Size Does Not Fit All: Planting Calendar as an Adaptation Strategy in the Mekong Delta
by: Le Phuong‐Dung, et al.
Published: (2025)
by: Le Phuong‐Dung, et al.
Published: (2025)
When One Size Does not Fit All—Artificial Intelligence in Australian Rural Health
by: Lewis Hains, et al.
Published: (2025)
by: Lewis Hains, et al.
Published: (2025)
Hybrid Alignment Training for Large Language Models
by: Wang, Chenglong, et al.
Published: (2024)
by: Wang, Chenglong, et al.
Published: (2024)
Theorem Provers: One Size Fits All?
by: Oates, Harrison, et al.
Published: (2025)
by: Oates, Harrison, et al.
Published: (2025)
One Size Does Not Fit All: Investigating Efficacy of Perplexity in Detecting LLM-Generated Code
by: Xu, Jinwei, et al.
Published: (2024)
by: Xu, Jinwei, et al.
Published: (2024)
Timing of Peri‐Ictal MRI Abnormalities in Status Epilepticus – One Size Does Not Fit All
by: Pilar Bosque Varela, et al.
Published: (2025)
by: Pilar Bosque Varela, et al.
Published: (2025)
EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation
by: Niu, Miaohe, et al.
Published: (2026)
by: Niu, Miaohe, et al.
Published: (2026)
NDP: Next Distribution Prediction as a More Broad Target
by: Ruan, Junhao, et al.
Published: (2024)
by: Ruan, Junhao, et al.
Published: (2024)
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
by: Yu, Jianxiang, et al.
Published: (2026)
by: Yu, Jianxiang, et al.
Published: (2026)
Patent Ductus Arteriosus in Acute Kidney Injury in Preterm Neonates: One Size Does Not Fit All
by: Sascha Meyer, et al.
Published: (2025)
by: Sascha Meyer, et al.
Published: (2025)
One Size Does Not Fit All: Creating a Developmentally Appropriate Classification for Your Children's Collections
by: Kaplan, Tali Balas, et al.
Published: (2013)
by: Kaplan, Tali Balas, et al.
Published: (2013)
Evaluating the Impact of NCLB School Interventions in New York State: Does One Size Fit All?
by: Jaekyung Lee
Published: (2013)
by: Jaekyung Lee
Published: (2013)
One Size Doesn't Fit All: Age-Aware Gamification Mechanics for Multimedia Learning Environments
by: Kaißer, Sarah, et al.
Published: (2025)
by: Kaißer, Sarah, et al.
Published: (2025)
One Size Does Not Fit All: Exploring Variable Thresholds for Distance-Based Multi-Label Text Classification
by: Van Nooten, Jens, et al.
Published: (2025)
by: Van Nooten, Jens, et al.
Published: (2025)
One Size Does Not Fit All: Menopause Hormone Therapy Type and Route of Administration Influences Cognitive Health
by: Laura Gravelsins, et al.
Published: (2025)
by: Laura Gravelsins, et al.
Published: (2025)
CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
by: Yang, Zongzhen, et al.
Published: (2025)
by: Yang, Zongzhen, et al.
Published: (2025)
No One Size Fits All: QueryBandits for Hallucination Mitigation
by: Cho, Nicole, et al.
Published: (2026)
by: Cho, Nicole, et al.
Published: (2026)
One Size May Not Fit All: A Case Series
by: Anjali Daulat, et al.
Published: (2026)
by: Anjali Daulat, et al.
Published: (2026)
Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
by: Wang, Chenglong, et al.
Published: (2025)
by: Wang, Chenglong, et al.
Published: (2025)
MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
by: Wang, Jianjin, et al.
Published: (2025)
by: Wang, Jianjin, et al.
Published: (2025)
PartialFormer: Modeling Part Instead of Whole for Machine Translation
by: Zheng, Tong, et al.
Published: (2023)
by: Zheng, Tong, et al.
Published: (2023)
One Size Does Not Fit All: Idiographic Computational Models Reveal Individual Differences in Learning and Meta‐Learning Strategies
by: Theodros M. Haile, et al.
Published: (2024)
by: Theodros M. Haile, et al.
Published: (2024)
Similar Items
-
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
by: Luo, Yingfeng, et al.
Published: (2025) -
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
by: Luo, Yingfeng, et al.
Published: (2026) -
Efficient Prompting Methods for Large Language Models: A Survey
by: Chang, Kaiyan, et al.
Published: (2024) -
APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
by: Chang, Kaiyan, et al.
Published: (2026) -
Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
by: Shan, Weiqiao, et al.
Published: (2024)