Image de couverture de livre

Adaptive Pruning of Pretrained Transformer via Differential Inclusions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ding, Yizhuo, Fan, Ke, Wang, Yikai, Sun, Xinwei, Fu, Yanwei
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

UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs
par: Ding, Yizhuo, et autres
Publié: (2025)

Revisiting Large Language Model Pruning using Neuron Semantic Attribution
par: Ding, Yizhuo, et autres
Publié: (2025)

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation
par: Huo, Jingyang, et autres
Publié: (2024)

Doubly Robust Proximal Causal Learning for Continuous Treatments
par: Wu, Yong, et autres
Publié: (2023)

Magnitude Pruning of Large Pretrained Transformer Models with a Mixture Gaussian Prior
par: Zhang, Mingxuan, et autres
Publié: (2024)

Robust Network Learning via Inverse Scale Variational Sparsification
par: Zhou, Zhiling, et autres
Publié: (2024)

A New Formulation of Lipschitz Constrained With Functional Gradient Learning for GANs
par: Wan, Chang, et autres
Publié: (2025)

Discovering Causal Relationships using Proxy Variables under Unmeasured Confounding
par: Wu, Yong, et autres
Publié: (2025)

Understanding Differential Transformer Unchains Pretrained Self-Attentions
par: Kong, Chaerin, et autres
Publié: (2025)

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning
par: Zhang, Jinyang, et autres
Publié: (2025)

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference
par: Zhao, Bowen, et autres
Publié: (2024)

COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability
par: Ding, Yizhuo, et autres
Publié: (2025)

Adaptive Computation Pruning for the Forgetting Transformer
par: Lin, Zhixuan, et autres
Publié: (2025)

IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
par: Li, Yixiao, et autres
Publié: (2025)

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling
par: Grangier, David, et autres
Publié: (2024)

Projection-Free CNN Pruning via Frank-Wolfe with Momentum: Sparser Models with Less Pretraining
par: Shili, Hamza ElMokhtar, et autres
Publié: (2025)

SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
par: Yasuda, Taisuke, et autres
Publié: (2024)

Adaptive Slot Attention: Object Discovery with Dynamic Slot Number
par: Fan, Ke, et autres
Publié: (2024)

Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
par: Yue, Yanwei, et autres
Publié: (2024)

Dataset Condensation for Time Series Classification via Dual Domain Matching
par: Liu, Zhanyu, et autres
Publié: (2024)

Demystifying When Pruning Works via Representation Hierarchies
par: He, Shwai, et autres
Publié: (2026)

Spiking Layer-Adaptive Magnitude-based Pruning
par: Wang, Junqiao, et autres
Publié: (2026)

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
par: Li, Albus Yizhuo, et autres
Publié: (2026)

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
par: Liu, Lawrence, et autres
Publié: (2025)

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining
par: Zhang, Ruiyi, et autres
Publié: (2024)

GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
par: Fan, Simin, et autres
Publié: (2025)

TAP-ViTs: Task-Adaptive Pruning for On-Device Deployment of Vision Transformers
par: Wang, Zhibo, et autres
Publié: (2026)

Non-transferable Pruning
par: Ding, Ruyi, et autres
Publié: (2024)

Distributional Reinforcement Learning with Diffusion Bridge Critics
par: Ding, Shutong, et autres
Publié: (2026)

Pruning and Malicious Injection: A Retraining-Free Backdoor Attack on Transformer Models
par: Zhao, Taibiao, et autres
Publié: (2025)

Variance-Adaptive Muon: Accelerating LLM Pretraining with NSR-Modulated and Variance-Scaled Momentum
par: Li, Jingru, et autres
Publié: (2026)

Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
par: Wei, Chu-Yuan, et autres
Publié: (2025)

Unified Lexical Representation for Interpretable Visual-Language Alignment
par: Li, Yifan, et autres
Publié: (2024)

MaSS: Multi-attribute Selective Suppression for Utility-preserving Data Transformation from an Information-theoretic Perspective
par: Chen, Yizhuo, et autres
Publié: (2024)

Self-supervised Pretraining for Partial Differential Equations
par: Madhavan, Varun, et autres
Publié: (2024)

SAP: Syntactic Attention Pruning for Transformer-based Language Models
par: Lee, Tzu-Yun, et autres
Publié: (2025)

EfficientLLM: Scalable Pruning-Aware Pretraining for Architecture-Agnostic Edge Language Models
par: Xing, Xingrun, et autres
Publié: (2025)

Causal Discovery via Conditional Independence Testing with Proxy Variables
par: Liu, Mingzhou, et autres
Publié: (2023)

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
par: Le, Qi, et autres
Publié: (2025)

Improving DNS Exfiltration Detection via Transformer Pretraining
par: Tomić, Miloš, et autres
Publié: (2026)