Image de couverture de livre

Addition is almost all you need: Compressing large language models with double binary factorization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Boža, Vladimír, Macko, Vladimír
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

Two Sparse Matrices are Better than One: Sparsifying Neural Networks with Double Sparse Factorization
par: Boža, Vladimír, et autres
Publié: (2024)

MACKO: Sparse Matrix-Vector Multiplication for Low Sparsity
par: Macko, Vladimír, et autres
Publié: (2025)

Attention and Compression is all you need for Controllably Efficient Language Models
par: Prakash, Jatin, et autres
Publié: (2025)

Fast and Effective Weight Update for Pruned Large Language Models
par: Boža, Vladimír
Publié: (2024)

One protein is all you need
par: Bushuiev, Anton, et autres
Publié: (2024)

Kolmogorov GAM Networks are all you need!
par: Polson, Sarah, et autres
Publié: (2025)

KV-weights are all you need for skipless transformers
par: Graef, Nils
Publié: (2024)

Tabular Data: Is Deep Learning all you need?
par: Zabërgja, Guri, et autres
Publié: (2024)

Image compositing is all you need for data augmentation
par: Shermaine, Ang Jia Ning, et autres
Publié: (2025)

Large Language Models aren't all that you need
par: Holla, Kiran Voderhobli, et autres
Publié: (2024)

Experts are all you need: A Composable Framework for Large Language Model Inference
par: Sridharan, Shrihari, et autres
Publié: (2025)

Graph is all you need? Lightweight data-agnostic neural architecture search without training
par: Huang, Zhenhan, et autres
Publié: (2024)

Cross-Modal Safety Alignment: Is textual unlearning all you need?
par: Chakraborty, Trishna, et autres
Publié: (2024)

Attention is all you need for boosting graph convolutional neural network
par: Wu, Yinwei
Publié: (2024)

Linear attention is (maybe) all you need (to understand transformer optimization)
par: Ahn, Kwangjun, et autres
Publié: (2023)

Simulation-based inference with scattering representations: scattering is all you need
par: Lin, Kiyam, et autres
Publié: (2024)

DC is all you need: describing ReLU from a signal processing standpoint
par: Kechris, Christodoulos, et autres
Publié: (2024)

Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series
par: Petralia, Adrien, et autres
Publié: (2025)

Neural Operator: Is data all you need to model the world? An insight into the paradigm of data-driven scientific ML
par: Viswanath, Hrishikesh, et autres
Publié: (2023)

Attention is all you need for an improved CNN-based flash flood susceptibility modeling. The case of the ungauged Rheraya watershed, Morocco
par: Elghouat, Akram, et autres
Publié: (2024)

Slim attention: cut your context memory in half without loss -- K-cache is all you need for MHA
par: Graef, Nils, et autres
Publié: (2025)

Anti-concentration is (almost) all you need
par: Heinrich, Markus, et autres
Publié: (2025)

Is attention all you need in medical image analysis? A review
par: Papanastasiou, Giorgos, et autres
Publié: (2023)

Block removal for large language models through constrained binary optimization
par: Jansen, David, et autres
Publié: (2026)

1 bit is all we need: binary normalized neural networks
par: Cabral, Eduardo Lobo Lustoda, et autres
Publié: (2025)

Why you don't overfit, and don't need Bayes if you only train for one epoch
par: Aitchison, Laurence
Publié: (2024)

Signformer is all you need: Towards Edge AI for Sign Language
par: Yang, Eta
Publié: (2024)

Visual cognition in multimodal large language models
par: Buschoff, Luca M. Schulze, et autres
Publié: (2023)

Hypothesis generation and updating in large language models
par: Xiong, Hua-Dong
Publié: (2026)

Representation in large language models
par: Yetman, Cameron
Publié: (2025)

Compressed models are NOT miniature versions of large models
par: Rai, Rohit Raj, et autres
Publié: (2024)

A Bayesian Optimization approach for calibrating large-scale activity-based transport models
par: Agriesti, Serio, et autres
Publié: (2023)

100 instances is all you need: predicting the success of a new LLM on unseen data by testing on a few instances
par: Pacchiardi, Lorenzo, et autres
Publié: (2024)

Amortizing intractable inference in large language models
par: Hu, Edward J., et autres
Publié: (2023)

Layer-wise dynamic rank for compressing large language models
par: Mi, Zhendong, et autres
Publié: (2025)

NIRVANA: Structured pruning reimagined for large language models compression
par: Ai, Mengting, et autres
Publié: (2025)

Training microrobots to swim by a large language model
par: Xu, Zhuoqun, et autres
Publié: (2024)

Alignment faking in large language models
par: Greenblatt, Ryan, et autres
Publié: (2024)

AI-AI Bias: large language models favor communications generated by large language models
par: Laurito, Walter, et autres
Publié: (2024)

Residual vector quantization for KV cache compression in large language model
par: Kumar, Ankur
Publié: (2024)