Imagen de Portada

Two-Stage Regularization-Based Structured Pruning for LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Feng, Mingkuan, Wu, Jinyang, Liu, Siyuan, Zhang, Shuai, Fang, Hongjian, Jin, Ruihan, Che, Feihu, Shao, Pengpeng, Wen, Zhengqi, Tao, Jianhua
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DReSS: Data-driven Regularized Structured Streamlining for Large Language Models
por: Feng, Mingkuan, et al.
Publicado: (2025)

RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
por: Jin, Ruihan, et al.
Publicado: (2025)

Exploring Knowledge Purification in Multi-Teacher Knowledge Distillation for LLMs
por: Jin, Ruihan, et al.
Publicado: (2026)

Pandora's Box or Aladdin's Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language Models
por: Wu, Jinyang, et al.
Publicado: (2024)

AStar: Boosting Multimodal Reasoning with Automated Structured Thinking
por: Wu, Jinyang, et al.
Publicado: (2025)

Can large language models understand uncommon meanings of common words?
por: Wu, Jinyang, et al.
Publicado: (2024)

Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS
por: Wu, Jinyang, et al.
Publicado: (2024)

TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
por: Wu, Jinyang, et al.
Publicado: (2025)

Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
por: Wu, Jinyang, et al.
Publicado: (2026)

KS-LLM: Knowledge Selection of Large Language Models with Evidence Document for Question Answering
por: Zheng, Xinxin, et al.
Publicado: (2024)

Fake News Detection and Manipulation Reasoning via Large Vision-Language Models
por: Jin, Ruihan, et al.
Publicado: (2024)

Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
por: Wu, Jinyang, et al.
Publicado: (2026)

CoNNect: Connectivity-Based Regularization for Structural Pruning
por: Franssen, Christian, et al.
Publicado: (2025)

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
por: Wu, Jinyang, et al.
Publicado: (2026)

IntraSlice: Towards High-Performance Structural Pruning with Block-Intra PCA for LLMs
por: Li, Meng, et al.
Publicado: (2026)

2SSP: A Two-Stage Framework for Structured Pruning of LLMs
por: Sandri, Fabrizio, et al.
Publicado: (2025)

Edit Content, Preserve Acoustics: Imperceptible Text-Based Speech Editing via Self-Consistency Rewards
por: Ren, Yong, et al.
Publicado: (2026)

Regularity of viscosity solutions of the $σ_k$-Yamabe-type Problem for $k>n/2$
por: Wu, Jinyang
Publicado: (2024)

Mosaic Pruning: A Hierarchical Framework for Generalizable Pruning of Mixture-of-Experts Models
por: Hu, Wentao, et al.
Publicado: (2025)

Calibration-Aware Policy Optimization for Reasoning LLMs
por: Wang, Ziqi, et al.
Publicado: (2026)

Residual Speaker Representation for One-Shot Voice Conversion
por: Xu, Le, et al.
Publicado: (2023)

DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
por: Wen, Yuhua, et al.
Publicado: (2025)

Electrostatic Force Regularization for Neural Structured Pruning
por: Ferdi, Abdesselam, et al.
Publicado: (2024)

Better, Stronger, Faster: Tackling the Trilemma in MLLM-based Segmentation with Simultaneous Textual Mask Prediction
por: Liu, Jiazhen, et al.
Publicado: (2025)

A Two-Stage Multimodal Emotion Recognition Model Based on Graph Contrastive Learning
por: Ai, Wei, et al.
Publicado: (2024)

Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection
por: Jin, Feihu, et al.
Publicado: (2026)

Learning-Time Encoding Shapes Unlearning in LLMs
por: Wu, Ruihan, et al.
Publicado: (2025)

Diff-ES: Stage-wise Structural Diffusion Pruning via Evolutionary Search
por: Liu, Zongfang, et al.
Publicado: (2026)

Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection
por: Fan, Cunhang, et al.
Publicado: (2023)

Exploring the Role of Audio in Multimodal Misinformation Detection
por: Liu, Moyang, et al.
Publicado: (2024)

PSA-MF: Personality-Sentiment Aligned Multi-Level Fusion for Multimodal Sentiment Analysis
por: Xie, Heng, et al.
Publicado: (2025)

Debunk and Infer: Multimodal Fake News Detection via Diffusion-Generated Evidence and LLM Reasoning
por: Yan, Kaiying, et al.
Publicado: (2025)

PCR‐Free Site‐Directed Mutagenesis on Repetitive Sequences Using Single‐Stranded DNA‐Assisted Double‐Stranded DNA Nicking by DNAzymes
por: Mingkuan Lyu, et al.
Publicado: (2025)

PCR‐Free Site‐Directed Mutagenesis on Repetitive Sequences Using Single‐Stranded DNA‐Assisted Double‐Stranded DNA Nicking by DNAzymes
por: Mingkuan Lyu, et al.
Publicado: (2025)

On Two-Stage Householder Orthogonalization
por: He, Zhuang-Ao, et al.
Publicado: (2026)

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes
por: Kolawole, Steven, et al.
Publicado: (2024)

RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search
por: Ren, Tao, et al.
Publicado: (2024)

MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation
por: Hsu, Hsin-Ling, et al.
Publicado: (2025)

On $P$-partitions Extended by Two-Rowed Plane Partitions
por: Li, Jingxuan, et al.
Publicado: (2024)

Hilbert Eisenstein series as Doi-Naganuma lift
por: Li, Yingkun, et al.
Publicado: (2025)