Model Merging

SLIM: Let LLM Learn More and Forget Less with Soft LoRA and Identity Mixture NAACL 2025 SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs ICLR 2025 Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition EMNLP 2025 Small Models Struggle to Learn from Strong Reasoners ACL 2025 Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMs EMNLP 2025 STAR: Spectral Truncation and Rescale for Model Merging NAACL 2025 SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models EMNLP 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 Superficial Self-Improved Reasoners Benefit from Model Merging EMNLP 2025 Superpose Task-specific Features for Model Merging EMNLP 2025 Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation ICLR 2025 TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks ACL 2025 Task Singular Vectors: Reducing Task Interference in Model Merging CVPR 2025 Task Vector Quantization for Memory-Efficient Model Merging ICCV 2025 TBA at BEA 2025 Shared Task: Transfer-Learning from DARE-TIES Merged Models for the Pedagogical Ability Assessment of LLM-Powered Math Tutors ACL 2025 TeamHateMate at BLP Task1: Divide and Conquer: A Two-Stage Cascaded Framework with K-Fold Ensembling for Multi-Label Bangla Hate Speech Classification AACL 2025 Temporal Alignment of Time Sensitive Facts with Activation Engineering EMNLP 2025 Temporal Information Retrieval via Time-Specifier Model Merging ACL 2025 The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs EMNLP 2025 To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging EMNLP 2025 Towards High-Fidelity Head Blending with Chroma Keying for Industrial Applications WACV 2025 Towards Performance Consistency in Multi-Level Model Collaboration ICCV 2025 Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text ACL 2025 Tracking Universal Features Through Fine-Tuning and Model Merging NAACL 2025 Training-free LLM Merging for Multi-task Learning ACL 2025