Copertina

UniPruning: Unifying Local Metric and Global Feedback for Scalable Sparse LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ding, Yizhuo, Qu, Wanying, Geng, Jiawei, Shao, Wenqi, Fu, Yanwei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

VTPerception-R1: Enhancing Multimodal Reasoning via Explicit Visual and Textual Perceptual Grounding
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers
di: Li, Albus Yizhuo, et al.
Pubblicazione: (2026)

UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs
di: Chiang, Hung-Yueh, et al.
Pubblicazione: (2025)

A Unified Framework for Locality in Scalable MARL
di: Chakraborty, Sourav, et al.
Pubblicazione: (2026)

Revisiting Large Language Model Pruning using Neuron Semantic Attribution
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs
di: Mozaffari, Mohammad, et al.
Pubblicazione: (2024)

UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation
di: Zhan, Wangzhi, et al.
Pubblicazione: (2025)

A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback
di: Kim, Kihyun, et al.
Pubblicazione: (2024)

UniRL-Zero: Reinforcement Learning on Unified Models with Joint Language Model and Diffusion Model Experts
di: Wang, Fu-Yun, et al.
Pubblicazione: (2025)

Adaptive Pruning of Pretrained Transformer via Differential Inclusions
di: Ding, Yizhuo, et al.
Pubblicazione: (2025)

TopoPrune: Robust Data Pruning via Unified Latent Space Topology
di: Roy, Arjun, et al.
Pubblicazione: (2026)

Probe Pruning: Accelerating LLMs through Dynamic Pruning via Model-Probing
di: Le, Qi, et al.
Pubblicazione: (2025)

SAFE: Finding Sparse and Flat Minima to Improve Pruning
di: Lee, Dongyeop, et al.
Pubblicazione: (2025)

COMPOL: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations
di: Sun, Yifei, et al.
Pubblicazione: (2025)

PrunePEFT: Iterative Hybrid Pruning for Parameter-Efficient Fine-tuning of LLMs
di: Yu, Tongzhou, et al.
Pubblicazione: (2025)

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

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
di: Zheng, Haizhong, et al.
Pubblicazione: (2026)

Unified Parameter-Efficient Unlearning for LLMs
di: Ding, Chenlu, et al.
Pubblicazione: (2024)

UniIF: Unified Molecule Inverse Folding
di: Gao, Zhangyang, et al.
Pubblicazione: (2024)

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
di: Choi, Moonseok, et al.
Pubblicazione: (2023)

SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale
di: Zimmer, Max, et al.
Pubblicazione: (2025)

The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models
di: Xiao, Yang, et al.
Pubblicazione: (2025)

UniTS: A Unified Multi-Task Time Series Model
di: Gao, Shanghua, et al.
Pubblicazione: (2024)

UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
di: Li, Haosen, et al.
Pubblicazione: (2026)

UniCA: Unified Covariate Adaptation for Time Series Foundation Model
di: Han, Lu, et al.
Pubblicazione: (2025)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
di: Lin, Huawei, et al.
Pubblicazione: (2025)

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
di: Ao, Shuang, et al.
Pubblicazione: (2025)

Two-Stage Regularization-Based Structured Pruning for LLMs
di: Feng, Mingkuan, et al.
Pubblicazione: (2025)

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
di: Zhang, Stephen, et al.
Pubblicazione: (2024)

JEL: A Novel Model Linking Knowledge Graph entities to News Mentions
di: Kishelev, Michael, et al.
Pubblicazione: (2025)

StructPrune: Structured Global Pruning asymptotics with $\mathcal{O}(\sqrt{N})$ GPU Memory
di: Song, Xinyuan, et al.
Pubblicazione: (2025)

PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs
di: Zimmer, Max, et al.
Pubblicazione: (2023)

Data-Free Pruning of Self-Attention Layers in LLMs
di: Saikumar, Dhananjay, et al.
Pubblicazione: (2025)

Mosaic: Composite Projection Pruning for Resource-efficient LLMs
di: Eccles, Bailey J., et al.
Pubblicazione: (2025)

From Local to Global: Revisiting Structured Pruning Paradigms for Large Language Models
di: Wang, Ziyan, et al.
Pubblicazione: (2025)

Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
di: Chen, Zhisheng, et al.
Pubblicazione: (2025)

A Unified Framework with Novel Metrics for Evaluating the Effectiveness of XAI Techniques in LLMs
di: Mersha, Melkamu Abay, et al.
Pubblicazione: (2025)

UniPool: A Globally Shared Expert Pool for Mixture-of-Experts
di: Huang, Minbin, et al.
Pubblicazione: (2026)

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
di: Zimmer, Max, et al.
Pubblicazione: (2023)