conftrace_

model merging

234 papers

Explore in graph

Co-occurring keywords

large language model (13587) transfer learning (5449) multi-task learning (2575) knowledge distillation (3725) model compression (3302) language model (4599) low-rank adaptation (560) parameter-efficient fine-tuning (736) domain adaptation (4595) task vector (25)

Papers

FedMerge: Federated Model Merging for Personalization AAAI 2026
K-Merge: Online Continual Merging of Adapters for On-device Large Language Models ACL 2026
BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation EACL 2026
Breaking the Aggregation Bottleneck in Federated Recommendation: A Personalized Model Merging Approach AAAI 2026
RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior AAAI 2026
Can Continual Pretraining Bridge the Performance Gap between General-purpose and Specialized Language Models in the Medical Domain? ACL 2026
Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models WACV 2026
H3Fusion: Helpful, Harmless, Honest Fusion of Aligned LLMs EACL 2026
Hala Technical Report Building Arabic-Centric Instruction & Translation Models at Scale EACL 2026
Breaking Task Boundaries: A Unified Model for 3D Medical Image Fusion and Segmentation Guided by Manifold Perspective AAAI 2026
RecCocktail: A Generalizable and Efficient Framework for LLM-Based Recommendation AAAI 2026
Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging AAAI 2026
Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging AAAI 2026
MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation AAAI 2026
MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images WACV 2026
Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification WACV 2026
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts EACL 2026
Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models EACL 2026
Luth: Efficient French Specialization for Small Language Models and Cross-Lingual Transfer EACL 2026
Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging EACL 2026
Building a Turkish Large Language Model via Continual Pre-Training and Parameter-Efficient Adaptation EACL 2026
DivMerge: A divergence-based model merging method for multi-tasking EACL 2026
GLOBA: Rethinking Parameter Conflicts in Model Merging AAAI 2026
From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging AAAI 2026
Revisiting Model Interpolation for Efficient Reasoning ACL 2026