Imagen de Portada

Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Velikanov, Maksim, Chahed, Ilyas, Zuo, Jingwei, Rhaiem, Dhia Eddine, Belkada, Younes, Hacid, Hakim
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

Falcon Mamba: The First Competitive Attention-free 7B Language Model
por: Zuo, Jingwei, et al.
Publicado: (2024)

Re-thinking Human Activity Recognition with Hierarchy-aware Label Relationship Modeling
por: Zuo, Jingwei, et al.
Publicado: (2024)

MAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization
por: Zuo, Jingwei, et al.
Publicado: (2024)

SGD with memory: fundamental properties and stochastic acceleration
por: Yarotsky, Dmitry, et al.
Publicado: (2024)

Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions
por: Velikanov, Maksim, et al.
Publicado: (2022)

Generalization error of spectral algorithms
por: Velikanov, Maksim, et al.
Publicado: (2024)

Constrained Online Convex Optimization with Memory and Predictions
por: Abdullah, Mohammed, et al.
Publicado: (2026)

PORT: Preference Optimization on Reasoning Traces
por: Lahlou, Salem, et al.
Publicado: (2024)

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
por: Zuo, Jingwei, et al.
Publicado: (2025)

BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction
por: Azam, Ubaid, et al.
Publicado: (2024)

LEAP: Learnable End-to-End Adaptive Pruning of Large Language Models
por: Mozaffari, Mohammad, et al.
Publicado: (2026)

WavLink: Compact Audio-Text Embeddings with a Global Whisper Token
por: Kumar, Gokul Karthik, et al.
Publicado: (2026)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
por: Firdoussi, Aymane El, et al.
Publicado: (2024)

Competitive Audio-Language Models with Data-Efficient Single-Stage Training on Public Data
por: Kumar, Gokul Karthik, et al.
Publicado: (2025)

When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product
por: Wu, Youqi, et al.
Publicado: (2025)

Data Quality in Edge Machine Learning: A State-of-the-Art Survey
por: Belgoumri, Mohammed Djameleddine, et al.
Publicado: (2024)

LESA: Learnable LLM Layer Scaling-Up
por: Yang, Yifei, et al.
Publicado: (2025)

From Uncertainty to Trust: Kernel Dropout for AI-Powered Medical Predictions
por: Azam, Ubaid, et al.
Publicado: (2024)

Enforcing Consistency and Fairness in Multi-level Hierarchical Classification with a Mask-based Output Layer
por: Chen, Shijing, et al.
Publicado: (2025)

Towards Fully FP8 GEMM LLM Training at Scale
por: Hernández-Cano, Alejandro, et al.
Publicado: (2025)

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs
por: Hourri, Younes, et al.
Publicado: (2025)

Training Machine Learning models at the Edge: A Survey
por: Khouas, Aymen Rayane, et al.
Publicado: (2024)

Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation
por: Levin, Ilya, et al.
Publicado: (2026)

Far From Sight, Far From Mind: Inverse Distance Weighting for Graph Federated Recommendation
por: Khouas, Aymen Rayane, et al.
Publicado: (2025)

Alignment with Preference Optimization Is All You Need for LLM Safety
por: Alami, Reda, et al.
Publicado: (2024)

Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles
por: Belgoumri, Mohammed Djameleddine, et al.
Publicado: (2025)

A Linearized Alternating Direction Multiplier Method for Federated Matrix Completion Problems
por: Hytla, Patrick, et al.
Publicado: (2025)

Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets
por: Younsi, Adam, et al.
Publicado: (2025)

Learnable Similarity and Dissimilarity Guided Symmetric Non-Negative Matrix Factorization
por: Lyu, Wenlong, et al.
Publicado: (2024)

Alternating Direction Method of Multipliers for Nonlinear Matrix Decompositions
por: Awari, Atharva, et al.
Publicado: (2025)

On the Learnability of Watermarks for Language Models
por: Gu, Chenchen, et al.
Publicado: (2023)

Efficient Conformal Prediction under Data Heterogeneity
por: Plassier, Vincent, et al.
Publicado: (2023)

Scaling Embedding Layers in Language Models
por: Yu, Da, et al.
Publicado: (2025)

Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
por: Gao, Junqi, et al.
Publicado: (2026)

Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale
por: Aiyer, Shashaank, et al.
Publicado: (2026)

MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention
por: Curvo, Pedro M. P., et al.
Publicado: (2025)

Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy
por: Xie, Peichen, et al.
Publicado: (2025)

AKD : Adversarial Knowledge Distillation For Large Language Models Alignment on Coding tasks
por: Oulkadda, Ilyas, et al.
Publicado: (2025)

Sparse Layers are Critical to Scaling Looped Language Models
por: Lee, Ryan, et al.
Publicado: (2026)

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
por: Zhang, Junjie, et al.
Publicado: (2026)