Image de couverture de livre

Decomposing Task Vectors for Refined Model Editing

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Damirchi, Hamed, Abbasnejad, Ehsan, Zhang, Zhen, Shi, Javen
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

The Quest for Winning Tickets in Low-Rank Adapters
par: Damirchi, Hamed, et autres
Publié: (2025)

Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
par: Damirchi, Hamed, et autres
Publié: (2026)

Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction
par: Jiang, Wenkang, et autres
Publié: (2026)

Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling
par: Rodriguez-Opazo, Cristian, et autres
Publié: (2024)

What Makes a Representation Good for Single-Cell Perturbation Prediction?
par: Jiang, Wenkang, et autres
Publié: (2026)

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
par: Zhang, Frederic Z., et autres
Publié: (2024)

Rethinking State Disentanglement in Causal Reinforcement Learning
par: Cao, Haiyao, et autres
Publié: (2024)

Decomposing and Editing Predictions by Modeling Model Computation
par: Shah, Harshay, et autres
Publié: (2024)

BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
par: Vo, Viet Quoc, et autres
Publié: (2024)

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
par: Li, Hongkang, et autres
Publié: (2025)

Beyond Imitation: Recovering Dense Rewards from Demonstrations
par: Li, Jiangnan, et autres
Publié: (2025)

Do Deep Neural Network Solutions Form a Star Domain?
par: Sonthalia, Ankit, et autres
Publié: (2024)

Highway Graph to Accelerate Reinforcement Learning
par: Yin, Zidu, et autres
Publié: (2024)

Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
par: Teney, Damien, et autres
Publié: (2025)

Exploring Context Window of Large Language Models via Decomposed Positional Vectors
par: Dong, Zican, et autres
Publié: (2024)

Variational Task Vector Composition
par: Zhang, Boyuan, et autres
Publié: (2025)

Neural Redshift: Random Networks are not Random Functions
par: Teney, Damien, et autres
Publié: (2024)

A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations
par: Cheng, Hongrong, et autres
Publié: (2023)

ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
par: Shamsi, Afshar, et autres
Publié: (2024)

Identifying Weight-Variant Latent Causal Models
par: Liu, Yuhang, et autres
Publié: (2022)

Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
par: McDonnell, Mark D., et autres
Publié: (2024)

Identifiable Latent Polynomial Causal Models Through the Lens of Change
par: Liu, Yuhang, et autres
Publié: (2023)

RanPAC: Random Projections and Pre-trained Models for Continual Learning
par: McDonnell, Mark D., et autres
Publié: (2023)

CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection
par: Darban, Zahra Zamanzadeh, et autres
Publié: (2025)

Towards Identifiable Latent Additive Noise Models
par: Liu, Yuhang, et autres
Publié: (2024)

Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding
par: Li, Xinyu, et autres
Publié: (2026)

Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation
par: Liu, Yuhang, et autres
Publié: (2022)

VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphics
par: Kuchař, Josef, et autres
Publié: (2025)

The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence
par: Cai, Yichao, et autres
Publié: (2026)

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product
par: Albert, Paul, et autres
Publié: (2025)

On Fairness of Task Arithmetic: The Role of Task Vectors
par: Naganuma, Hiroki, et autres
Publié: (2025)

Task Vector Quantization for Memory-Efficient Model Merging
par: Kim, Youngeun, et autres
Publié: (2025)

Analytic DAG Constraints for Differentiable DAG Learning
par: Zhang, Zhen, et autres
Publié: (2025)

The Character Error Vector: Decomposable errors for page-level OCR evaluation
par: Bourne, Jonathan, et autres
Publié: (2026)

Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs
par: Liu, Yuhang, et autres
Publié: (2026)

Adaptive Task Vectors for Large Language Models
par: Kang, Joonseong, et autres
Publié: (2025)

Decomposed Inductive Procedure Learning: Learning Academic Tasks with Human-Like Data Efficiency
par: Weitekamp, Daniel, et autres
Publié: (2025)

On Task Vectors and Gradients
par: Zhou, Luca, et autres
Publié: (2025)

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning
par: Liu, Yuhang, et autres
Publié: (2024)

Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
par: Myers, Vivek, et autres
Publié: (2024)