Imagen de Portada

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Lu, Zhang, Tianyu, Bu, Zhiqi, Wang, Suyuchen, He, Huan, Fu, Jie, Wu, Yonghui, Bian, Jiang, Chen, Yong, Bengio, Yoshua
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
por: Zhang, Tianyu, et al.
Publicado: (2024)

Scope: Selective Cross-modal Orchestration of Visual Perception Experts
por: Zhang, Tianyu, et al.
Publicado: (2025)

Learning Decision Trees as Amortized Structure Inference
por: Mahfoud, Mohammed, et al.
Publicado: (2025)

Amortizing intractable inference in large language models
por: Hu, Edward J., et al.
Publicado: (2023)

Large Language Models as Amortized Pareto-Front Generators for Constrained Bi-Objective Convex Optimization
por: Xu, Peipei, et al.
Publicado: (2026)

Machine learning and information theory concepts towards an AI Mathematician
por: Bengio, Yoshua, et al.
Publicado: (2024)

Amortized Active Generation of Pareto Sets
por: Steinberg, Daniel M., et al.
Publicado: (2025)

Baking Symmetry into GFlowNets
por: Ma, George, et al.
Publicado: (2024)

Amortizing intractable inference in diffusion models for vision, language, and control
por: Venkatraman, Siddarth, et al.
Publicado: (2024)

Scaling depth capacity via zero/one-layer model expansion
por: Bu, Zhiqi
Publicado: (2025)

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback
por: Jiralerspong, Thomas, et al.
Publicado: (2026)

Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning
por: Yoon, Jaesik, et al.
Publicado: (2025)

Pareto Front Approximation for Multi-Objective Session-Based Recommender Systems
por: Wilm, Timo, et al.
Publicado: (2024)

C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
por: Liu, Ruohong, et al.
Publicado: (2024)

Optimal Linear MAP Decoding of Convolutional Codes
por: Li, Yonghui, et al.
Publicado: (2025)

When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks
por: Lo, Chung-Hsiang, et al.
Publicado: (2026)

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
por: Scimeca, Luca, et al.
Publicado: (2025)

Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection
por: Xu, Shiyun, et al.
Publicado: (2025)

On Generalization for Generative Flow Networks
por: Krichel, Anas, et al.
Publicado: (2024)

Interventional Causal Representation Learning
por: Ahuja, Kartik, et al.
Publicado: (2022)

A Complexity-Based Theory of Compositionality
por: Elmoznino, Eric, et al.
Publicado: (2024)

Visual symbolic mechanisms: Emergent symbol processing in vision language models
por: Assouel, Rim, et al.
Publicado: (2025)

Relative Trajectory Balance is equivalent to Trust-PCL
por: Deleu, Tristan, et al.
Publicado: (2025)

In-Context Parametric Inference: Point or Distribution Estimators?
por: Mittal, Sarthak, et al.
Publicado: (2025)

GFlowNet Foundations
por: Bengio, Yoshua, et al.
Publicado: (2021)

Memory Efficient Neural Processes via Constant Memory Attention Block
por: Feng, Leo, et al.
Publicado: (2023)

AP-BMM: Approximating Capability-Cost Pareto Sets of LLMs via Asynchronous Prior-Guided Bayesian Model Merging
por: Chen, Kesheng, et al.
Publicado: (2025)

Cascaded Transformer for Robust and Scalable SLA Decomposition via Amortized Optimization
por: Hsu, Cyril Shih-Huan
Publicado: (2026)

Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
por: Liu, Zhen, et al.
Publicado: (2024)

Expected flow networks in stochastic environments and two-player zero-sum games
por: Jiralerspong, Marco, et al.
Publicado: (2023)

Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
por: Chen, Weiyu, et al.
Publicado: (2024)

Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity
por: Williams-King, David, et al.
Publicado: (2025)

RL, but don't do anything I wouldn't do
por: Cohen, Michael K., et al.
Publicado: (2024)

Local Search GFlowNets
por: Kim, Minsu, et al.
Publicado: (2023)

Active Attacks: Red-teaming LLMs via Adaptive Environments
por: Yun, Taeyoung, et al.
Publicado: (2025)

Approximating Pareto Frontiers in Stochastic Multi-Objective Optimization via Hashing and Randomization
por: Li, Jinzhao, et al.
Publicado: (2026)

A Newton Method for Hausdorff Approximations of the Pareto Front within Multi-objective Evolutionary Algorithms
por: Wang, Hao, et al.
Publicado: (2024)

Multi-Objective Bayesian Optimization with Independent Tanimoto Kernel Gaussian Processes for Diverse Pareto Front Exploration
por: Yong, Anabel
Publicado: (2025)

Pareto Front Shape-Agnostic Pareto Set Learning in Multi-Objective Optimization
por: Ye, Rongguang, et al.
Publicado: (2024)

Monte Carlo Tree Diffusion for System 2 Planning
por: Yoon, Jaesik, et al.
Publicado: (2025)