Image de couverture de livre

From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Maximov, Egor, Kuzkina, Yulia, Kanametov, Azamat, Prutko, Alexander, Goncharov, Aleksei, Zhelnin, Maxim, Shvetsov, Egor
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
par: Zhelnin, Maxim, et autres
Publié: (2024)

MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequences
par: Moskvoretskii, Viktor, et autres
Publié: (2024)

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
par: Alanova, Shirin, et autres
Publié: (2025)

MedSyn: LLM-based Synthetic Medical Text Generation Framework
par: Kumichev, Gleb, et autres
Publié: (2024)

How to model Human Actions distribution with Event Sequence Data
par: Surkov, Egor, et autres
Publié: (2025)

EBES: Easy Benchmarking for Event Sequences
par: Osin, Dmitry, et autres
Publié: (2024)

IDAP++: Advancing Divergence-Based Pruning via Filter-Level and Layer-Level Optimization
par: Samarin, Aleksei, et autres
Publié: (2025)

Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models
par: Kharinaev, Artyom, et autres
Publié: (2025)

Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning
par: Nguyen, Khanh, et autres
Publié: (2024)

Designing Social Learning
par: Smirnov, Aleksei, et autres
Publié: (2024)

From Internal Representations to Text Quality: A Geometric Approach to LLM Evaluation
par: Yusupov, Viacheslav, et autres
Publié: (2025)

S3: A Simple Strong Sample-effective Multimodal Dialog System
par: Rykov, Elisei, et autres
Publié: (2024)

Enhancing PIBT via Multi-Action Operations
par: Yukhnevich, Egor, et autres
Publié: (2025)

Drawing Pandas: A Benchmark for LLMs in Generating Plotting Code
par: Galimzyanov, Timur, et autres
Publié: (2024)

Compact and Efficient Neural Networks for Image Recognition Based on Learned 2D Separable Transform
par: Vashkevich, Maxim, et autres
Publié: (2025)

Data filtering methods for training language models
par: Shevchenko, Egor, et autres
Publié: (2026)

SeqNAS: Neural Architecture Search for Event Sequence Classification
par: Udovichenko, Igor, et autres
Publié: (2024)

Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs
par: Zhelnin, Maxim, et autres
Publié: (2025)

Impact of hydrothermal aging on microstructure transformation in Poly(L‐lactide) nonwovens under tension in condition close to a living organism
par: Egor Morokov, et autres
Publié: (2024)

GitGoodBench: A Novel Benchmark For Evaluating Agentic Performance On Git
par: Lindenbauer, Tobias, et autres
Publié: (2025)

MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
par: Bargatin, Vladislav, et autres
Publié: (2025)

Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling
par: Khalin, Aleksei, et autres
Publié: (2026)

Re:Frame -- Retrieving Experience From Associative Memory
par: Zelezetsky, Daniil, et autres
Publié: (2025)

Beyond Early-Token Bias: Model-Specific and Language-Specific Position Effects in Multilingual LLMs
par: Menschikov, Mikhail, et autres
Publié: (2025)

Patagonian toothfish fishing at the shelf of the Kerguelen Islands
par: Prutko, V.G.
Publié: (1994)

Bounded Edit Distance: Optimal Static and Dynamic Algorithms for Small Integer Weights
par: Gorbachev, Egor, et autres
Publié: (2024)

Not Yet: Humans Outperform LLMs in a Colonel Blotto Tournament
par: Dagaev, Dmitry, et autres
Publié: (2026)

Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
par: Freire, Pedro, et autres
Publié: (2024)

Unsupervised Denoising of Diffusion-Weighted Images with Bias and Variance Corrected Noise Modeling
par: Xie, Jine, et autres
Publié: (2026)

Towards properties of adversarial image perturbations
par: Kuznetsov, Egor, et autres
Publié: (2025)

Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems
par: Nuzhin, Egor E., et autres
Publié: (2024)

PIPer: On-Device Environment Setup via Online Reinforcement Learning
par: Kovrigin, Alexander, et autres
Publié: (2025)

Small-scale photonic Kolmogorov-Arnold networks using standard telecom nonlinear modules
par: Calçado, Luca Nogueira, et autres
Publié: (2026)

Predicting Knee Osteoarthritis Progression from Structural MRI using Deep Learning
par: Panfilov, Egor, et autres
Publié: (2022)

LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients
par: Fadeev, Egor, et autres
Publié: (2025)

Smooth Gate Functions for Soft Advantage Policy Optimization
par: Denisov, Egor, et autres
Publié: (2026)

Spectral description of non-commutative local systems on surfaces and non-commutative cluster varieties
par: Goncharov, Alexander, et autres
Publié: (2021)

RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
par: Huang, Xijie, et autres
Publié: (2024)

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models
par: Chelombitko, Iaroslav, et autres
Publié: (2024)

Rota-Baxter operators of non-scalar weights, connections with coboundary Lie bialgebra structures
par: Goncharov, Maxim
Publié: (2024)