Skip to content
conftrace_

task vector

41 papers

Explore in graph

Co-occurring keywords · papers mentioning both

model merging (15) large language model (9) in-context learning (9) task arithmetic (4) transfer learning (4) attention head (3) vision-language model (3) parameter-efficient fine-tuning (3) language model (3) model editing (3)

Papers

Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation CVPR 2026 Behavior Knowledge Merge in Reinforced Agentic Models ACL 2026 DC-Merge: Improving Model Merging with Directional Consistency CVPR 2026 GDFA: Geometry-Driven Federated Unlearning with Directional Task Vector Alignment CVPR 2026 GLOBA: Rethinking Parameter Conflicts in Model Merging AAAI 2026 One Task Vector is not Enough: A Large-Scale Study for In-Context Learning ACL 2026 On the Additive Compositionality of Task Vectors in Vision–Language Models EACL 2026 Understanding and Enforcing Weight Disentanglement in Task Arithmetic CVPR 2026 VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation ACL 2026 Where and What Matters: Sensitivity-Aware Task Vectors for Many-Shot Multimodal In-Context Learning AAAI 2026 CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging ICML 2025 CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging ICML 2025 Composable Cross-prompt Essay Scoring by Merging Models EMNLP 2025 Dynamic Task Vector Grouping for Efficient Multi-Task Prompt Tuning ACL 2025 Efficient Model Editing with Task-Localized Sparse Fine-tuning ICLR 2025 ELICIT: LLM Augmentation Via External In-context Capability ICLR 2025 Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective ICML 2025 GIL-IIMAS UNAM at SemEval-2025 Task 4: LA-Min(E): LLM Unlearning Approaches Under Function Minimizing Evaluation Constraints SemEval 2025 Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge EMNLP 2025 Learning Task Representations from In-Context Learning ACL 2025 Less is More: Efficient Model Merging with Binary Task Switch CVPR 2025 LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging EMNLP 2025 Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent ICML 2025 NegMerge: Sign-Consensual Weight Merging for Machine Unlearning ICML 2025 Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer ACL 2025