SOTAVerified

Task Arithmetic

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 26–50 of 61 papers

TitleStatusHype
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach—0
Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach—0
Task Arithmetic Through The Lens Of One-Shot Federated Learning—0
Multi-Task Model Merging via Adaptive Weight DisentanglementCode0
Task Singular Vectors: Reducing Task Interference in Model MergingCode2
Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics—0
ATM: Improving Model Merging by Alternating Tuning and Merging—0
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging—0
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse—0
NegMerge: Consensual Weight Negation for Strong Machine UnlearningCode1
What Matters for Model Merging at Scale?—0
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge IntegrationCode0
Task Arithmetic for Language Expansion in Speech Translation—0
Localize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticCode1
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task ArithmeticCode1
Knowledge Composition using Task Vectors with Learned Anisotropic ScalingCode1
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion—0
MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic—0
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition—0
HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task—0
Localizing Task Information for Improved Model Merging and CompressionCode2
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models—0
No Train but Gain: Language Arithmetic for training-free Language Adapters enhancementCode0
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model MergingCode1
Ethos: Rectifying Language Models in Orthogonal Parameter Space—0
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.