Papers with Code 아카이브
Task Arithmetic
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
A task vector specifies a direction in the weight space of a pre-trained model, such that movement in that direction improves performance on the task. We build task vectors by subtracting the weights of a pre-trained model from the weights of the same model after fine-tuning on a task. We show that these task vectors can be modified and combined together through arithmetic operations such as negation and addition, and the behavior of the resulting model is steered accordingly.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task
Localizing Task Information for Improved Model Merging and Compression
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging
Ethos: Rectifying Language Models in Orthogonal Parameter Space
Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic
Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion
Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization
Task Arithmetic with LoRA for Continual Learning
Model Merging by Uncertainty-Based Gradient Matching
Parameter Efficient Multi-task Model Fusion with Partial Linearization
AdaMerging: Adaptive Model Merging for Multi-Task Learning
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
An Empirical Study of Multimodal Model Merging
Editing Models with Task Arithmetic
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.