Image de couverture de livre

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shopkhoev, Dmitriy, Ali, Ammar, Zhussip, Magauiya, Malykh, Valentin, Lefkimmiatis, Stamatios, Komodakis, Nikos, Zagoruyko, Sergey
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
par: Zhussip, Magauiya, et autres
Publié: (2025)

CoSpaDi: Compressing LLMs via Calibration-Guided Sparse Dictionary Learning
par: Makhov, Denis, et autres
Publié: (2025)

COMPOT: Calibration-Optimized Matrix Procrustes Orthogonalization for Transformers Compression
par: Makhov, Denis, et autres
Publié: (2026)

ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression
par: Ali, Ammar, et autres
Publié: (2026)

Speak, Edit, Repeat: High-Fidelity Voice Editing and Zero-Shot TTS with Cross-Attentive Mamba
par: Mohammad, Baher, et autres
Publié: (2025)

A Modular Conditional Diffusion Framework for Image Reconstruction
par: Zhussip, Magauiya, et autres
Publié: (2024)

AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars
par: Fazylov, Ramazan, et autres
Publié: (2025)

GSLoc: Visual Localization with 3D Gaussian Splatting
par: Botashev, Kazii, et autres
Publié: (2024)

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
par: Karypidis, Efstathios, et autres
Publié: (2025)

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
par: Kakogeorgiou, Ioannis, et autres
Publié: (2023)

Coevolving Representations in Joint Image-Feature Diffusion
par: Kouzelis, Theodoros, et autres
Publié: (2026)

Multi-Token Prediction Needs Registers
par: Gerontopoulos, Anastasios, et autres
Publié: (2025)

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
par: Karypidis, Efstathios, et autres
Publié: (2026)

ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images
par: Schmidt-Mengin, Marius, et autres
Publié: (2024)

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

StRuCom: A Novel Dataset of Structured Code Comments in Russian
par: Dziuba, Maria, et autres
Publié: (2025)

CIDRe: A Reference-Free Multi-Aspect Criterion for Code Comment Quality Measurement
par: Dziuba, Maria, et autres
Publié: (2025)

Iterative Self-Training for Code Generation via Reinforced Re-Ranking
par: Sorokin, Nikita, et autres
Publié: (2025)

Boosting Generative Image Modeling via Joint Image-Feature Synthesis
par: Kouzelis, Theodoros, et autres
Publié: (2025)

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
par: Kouzelis, Theodoros, et autres
Publié: (2025)

DINO-Foresight: Looking into the Future with DINO
par: Karypidis, Efstathios, et autres
Publié: (2024)

Hierarchical Embedding Fusion for Retrieval-Augmented Code Generation
par: Sorokin, Nikita, et autres
Publié: (2026)

Low-resource Machine Translation for Code-switched Kazakh-Russian Language Pair
par: Borisov, Maksim, et autres
Publié: (2025)

SumHiS: Extractive Summarization Exploiting Hidden Structure
par: Pavel, Tikhonov, et autres
Publié: (2024)

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models
par: Sedykh, Ivan, et autres
Publié: (2026)

Searching by Code: a New SearchBySnippet Dataset and SnippeR Retrieval Model for Searching by Code Snippets
par: Sedykh, Ivan, et autres
Publié: (2023)

FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training
par: Cai, Fuhan, et autres
Publié: (2025)

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?
par: Aravanis, Tilemachos, et autres
Publié: (2026)

Defusing Logic Bombs in Symbolic Execution with LLM-Generated Ghost Code
par: Bouras, Dimitrios Stamatios, et autres
Publié: (2026)

Interpretable Vision Transformers in Monocular Depth Estimation via SVDA
par: Arampatzakis, Vasileios, et autres
Publié: (2026)

CCT-Code: Cross-Consistency Training for Multilingual Clone Detection and Code Search
par: Tikhonov, Anton, et autres
Publié: (2023)

Lipschitz Pruning: Hierarchical Simplification of Primitive‐Based SDFs
par: Wilhem Barbier, et autres
Publié: (2025)

AINL-Eval 2025 Shared Task: Detection of AI-Generated Scientific Abstracts in Russian
par: Batura, Tatiana, et autres
Publié: (2025)

Mapping the Unseen: Unified Promptable Panoptic Mapping with Dynamic Labeling using Foundation Models
par: Mdfaa, Mohamad Al, et autres
Publié: (2024)

Pruning by Block Benefit: Exploring the Properties of Vision Transformer Blocks during Domain Adaptation
par: Glandorf, Patrick, et autres
Publié: (2025)

Policy-based Sentence Simplification: Replacing Parallel Corpora with LLM-as-a-Judge
par: Wu, Xuanxin, et autres
Publié: (2025)

A High-Level Survey of Optical Remote Sensing
par: Koletsis, Panagiotis, et autres
Publié: (2026)

Block-based Symmetric Pruning and Fusion for Efficient Vision Transformers
par: Hsieh, Yi-Kuan, et autres
Publié: (2025)

Robust Two-View Geometry Estimation with Implicit Differentiation
par: Pyatov, Vladislav, et autres
Publié: (2024)

Block Pruning for Enhanced Efficiency in Convolutional Neural Networks
par: Wu, Cheng-En, et autres
Publié: (2023)