Copertina

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ding, Xuan, Sun, Rui, Zhang, Yunjian, Yan, Xiu, Zhou, Yueqi, Huang, Kaihao, Fu, Suzhong, Aviles-Rivero, Angelica I, Xie, Chuanlong, Zhu, Yao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

DipSVD: Dual-importance Protected SVD for Efficient LLM Compression
di: Ding, Xuan, et al.
Pubblicazione: (2025)

ONRW: Optimizing inversion noise for high-quality and robust watermark
di: Ding, Xuan, et al.
Pubblicazione: (2026)

VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
di: Fu, Suzhong, et al.
Pubblicazione: (2025)

Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models
di: Ding, Xuan, et al.
Pubblicazione: (2026)

Do Neural Operators Forget Geometry? The Forgetting Hypothesis in Deep Operator Learning
di: Xia, Yanming, et al.
Pubblicazione: (2026)

Don't Fix the Basis -- Learn It: Spectral Representation with Adaptive Basis Learning for PDEs
di: Zhao, Xuxiang, et al.
Pubblicazione: (2026)

AgentsEval: Clinically Faithful Evaluation of Medical Imaging Reports via Multi-Agent Reasoning
di: Fu, Suzhong, et al.
Pubblicazione: (2026)

No More Sliding Window: Efficient 3D Medical Image Segmentation with Differentiable Top-k Patch Sampling
di: Jeon, Young Seok, et al.
Pubblicazione: (2025)

Varadhan Functions, Variances, and Means on Compact Riemannian Manifolds
di: Cao, Yueqi
Pubblicazione: (2026)

Measuring the Redundancy of Decoder Layers in SpeechLLMs
di: Moumen, Adel, et al.
Pubblicazione: (2026)

Closely Placed Single‐Layer Patch Antenna Array With Self‐Decoupling Using Hybrid Modes
di: Lei Li, et al.
Pubblicazione: (2024)

AdvLogo: Adversarial Patch Attack against Object Detectors based on Diffusion Models
di: Miao, Boming, et al.
Pubblicazione: (2024)

Optimal Approximate Matrix Multiplication over Sliding Windows
di: Yao, Ziqi, et al.
Pubblicazione: (2025)

Product Interaction: An Algebraic Formalism for Deep Learning Architectures
di: Dong, Haonan, et al.
Pubblicazione: (2026)

You KAN Do It in a Single Shot: Plug-and-Play Methods with Single-Instance Priors
di: Cheng, Yanqi, et al.
Pubblicazione: (2024)

Slide-SAM: Medical SAM Meets Sliding Window
di: Quan, Quan, et al.
Pubblicazione: (2023)

SpectraKAN: Conditioning Spectral Operators
di: Cheng, Chun-Wun, et al.
Pubblicazione: (2026)

Interval Selection in Sliding Windows
di: Alexandru, Cezar-Mihail, et al.
Pubblicazione: (2024)

Sliding Window Adversarial Channels
di: Dey, Bikash Kumar, et al.
Pubblicazione: (2025)

Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection
di: Yan, Jiazhen, et al.
Pubblicazione: (2025)

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography
di: Yan, Ruiyi, et al.
Pubblicazione: (2026)

SWAT: Sliding Window Adversarial Training for Gradual Domain Adaptation
di: Wang, Zixi, et al.
Pubblicazione: (2025)

Tracking Dynamic Gaussian Density with a Theoretically Optimal Sliding Window Approach
di: Wang, Yinsong, et al.
Pubblicazione: (2024)

NorMatch: Matching Normalizing Flows with Discriminative Classifiers for Semi-Supervised Learning
di: Deng, Zhongying, et al.
Pubblicazione: (2022)

Optimised ProPainter for Video Diminished Reality Inpainting
di: Li, Pengze, et al.
Pubblicazione: (2024)

Low-Latency Sliding Window Connectivity
di: Zhang, Chao, et al.
Pubblicazione: (2024)

Fair Center Clustering in Sliding Windows
di: Ceccarello, Matteo, et al.
Pubblicazione: (2025)

Sliding Window Recurrences for Sequence Models
di: Secrieru, Dragos, et al.
Pubblicazione: (2025)

Fair Clustering in the Sliding Window Model
di: Cohen-Addad, Vincent, et al.
Pubblicazione: (2025)

Regular Languages in the Sliding Window Model
di: Ganardi, Moses, et al.
Pubblicazione: (2024)

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
di: Liu, Deyuan, et al.
Pubblicazione: (2024)

Adaptive Layer-skipping in Pre-trained LLMs
di: Luo, Xuan, et al.
Pubblicazione: (2025)

Sliding Window Attention Training for Efficient Large Language Models
di: Fu, Zichuan, et al.
Pubblicazione: (2025)

D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
di: Zhang, Lipei, et al.
Pubblicazione: (2025)

MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images
di: Bui, Doanh C., et al.
Pubblicazione: (2025)

Learning to Rank Patches for Unbiased Image Redundancy Reduction
di: Luo, Yang, et al.
Pubblicazione: (2024)

MergeBench: A Benchmark for Merging Domain-Specialized LLMs
di: He, Yifei, et al.
Pubblicazione: (2025)

Can Graph-Based Microservice Performance Detection Be Used for Microservice Intrusion Detection?
di: Ma, Yunjian
Pubblicazione: (2026)

The Weyl bound for Rankin-Selberg $L$-functions with Joint Ramification
di: Peng, Yunjian
Pubblicazione: (2025)

Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
di: Yan, Yao
Pubblicazione: (2025)