Imagen de Portada

Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Son, Jungyong, Jung, Jinwook, Park, Minhee, Baik, Sungyong
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
por: Lee, Yeoreum, et al.
Publicado: (2025)

Find A Winning Sign: Sign Is All We Need to Win the Lottery
por: Oh, Junghun, et al.
Publicado: (2025)

SCOPE-FE: Structured Control of Operator and Pairwise Exploration for Feature Engineering
por: Park, Minhee, et al.
Publicado: (2026)

Deep Variational Bayesian Modeling of Haze Degradation Process
por: Im, Eun Woo, et al.
Publicado: (2024)

EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure
por: Ahn, Junyeong, et al.
Publicado: (2026)

BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers
por: Seo, Jungwook, et al.
Publicado: (2026)

Task Vector Quantization for Memory-Efficient Model Merging
por: Kim, Youngeun, et al.
Publicado: (2025)

Adaptive Task Vectors for Large Language Models
por: Kang, Joonseong, et al.
Publicado: (2025)

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache
por: Son, Donghyun, et al.
Publicado: (2025)

Finding Manifolds With Bilinear Autoencoders
por: Dooms, Thomas, et al.
Publicado: (2025)

Learning to Schedule in Parallel-Server Queues with Stochastic Bilinear Rewards
por: Kim, Jung-hun, et al.
Publicado: (2021)

AIS-LLM: A Unified Framework for Maritime Trajectory Prediction, Anomaly Detection, and Collision Risk Assessment with Explainable Forecasting
por: Park, Hyobin, et al.
Publicado: (2025)

ELM-DeepONets: Backpropagation-Free Training of Deep Operator Networks via Extreme Learning Machines
por: Son, Hwijae
Publicado: (2025)

On Fairness of Task Arithmetic: The Role of Task Vectors
por: Naganuma, Hiroki, et al.
Publicado: (2025)

Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks
por: Hölzl, Florian A., et al.
Publicado: (2025)

Bilinear autoencoders find interpretable manifolds
por: Dooms, Thomas, et al.
Publicado: (2026)

Training-Free Vector Quantization via Gaussian VAEs
por: Xu, Tongda, et al.
Publicado: (2025)

Leveraging RAG for Training-Free Alignment of LLMs
por: Halloran, John T.
Publicado: (2026)

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment
por: Li, Xiuyu, et al.
Publicado: (2026)

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs
por: Lorenz, Tobias, et al.
Publicado: (2024)

Stop Misusing t-SNE and UMAP for Visual Analytics
por: Jeon, Hyeon, et al.
Publicado: (2025)

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
por: Cheng, Runxi, et al.
Publicado: (2025)

Domain Transfer Becomes Identifiable via a Single Alignment
por: Shrestha, Sagar, et al.
Publicado: (2026)

On Task Vectors and Gradients
por: Zhou, Luca, et al.
Publicado: (2025)

Metric Design != Metric Behavior: Improving Metric Selection for the Unbiased Evaluation of Dimensionality Reduction
por: Bae, Jiyeon, et al.
Publicado: (2025)

Beyond Task Vectors: Selective Task Arithmetic Based on Importance Metrics
por: Bowen, Tian, et al.
Publicado: (2024)

Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
por: Seo, Jungwook, et al.
Publicado: (2026)

Prognostics of Multisensor Systems with Unknown and Unlabeled Failure Modes via Bayesian Nonparametric Process Mixtures
por: Fu, Kani, et al.
Publicado: (2026)

Bilinear MLPs enable weight-based mechanistic interpretability
por: Pearce, Michael T., et al.
Publicado: (2024)

Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention
por: Varner, Jeffrey D.
Publicado: (2026)

Transporting Task Vectors across Different Architectures without Training
por: Rinaldi, Filippo, et al.
Publicado: (2026)

Decomposing Task Vectors for Refined Model Editing
por: Damirchi, Hamed, et al.
Publicado: (2025)

Variational Task Vector Composition
por: Zhang, Boyuan, et al.
Publicado: (2025)

ASNN: Learning to Suggest Neural Architectures from Performance Distributions
por: Hong, Jinwook
Publicado: (2025)

Is Prompt Selection Necessary for Task-Free Online Continual Learning?
por: Park, Seoyoung, et al.
Publicado: (2026)

Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
por: Mozafari, Mostafa, et al.
Publicado: (2025)

Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation
por: Fujii, Hiroki, et al.
Publicado: (2026)

SAT: Sequential Agent Tuning for Coordinator Free Plug and Play Multi-LLM Training with Monotonic Improvement Guarantees
por: Xie, Yi, et al.
Publicado: (2026)

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
por: Zeng, Siqi, et al.
Publicado: (2025)

Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
por: Park, Youngrok, et al.
Publicado: (2025)