Copertina

MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	MiniCPM Team, An, Wenhao, Chen, Yingfa, Fang, Yewei, Li, Jiayi, Li, Xin, Li, Yaohui, Li, Yishan, Li, Yuxuan, Lin, Biyuan, Liu, Chuan, Liu, Hezi, Liu, Siyuan, Lyu, Hongya, Pan, Yinxu, Ren, Shixin, Shen, Xingyu, Su, Zhou, Sun, Haojun, Sun, Yangang, Thai, Zhen Leng, Tian, Xin, Wang, Rui, Wang, Xiaorong, Wang, Yudong, Wu, Bo, Xu, Xiaoyue, Xu, Dong, Xue, Shuaikang, Yang, Jiawei, Zhang, Bowen, Zhang, Jinqian, Zhang, Letian, Zhang, Shengnan, Zhang, Xinyu, Zhang, Xinyuan, Zhang, Zhu, Zhao, Hengyu, Zhao, Jiacheng, Zheng, Zhi, Zhou, Jie, Zhou, Zihan, Wang, Shuo, Xiao, Chaojun, Han, Xu, Liu, Zhiyuan, Sun, Maosong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MiniCPM4: Ultra-Efficient LLMs on End Devices
di: MiniCPM Team, et al.
Pubblicazione: (2025)

MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
di: Cui, Junbo, et al.
Pubblicazione: (2026)

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
di: Hu, Shengding, et al.
Pubblicazione: (2024)

MiniCPM-V: A GPT-4V Level MLLM on Your Phone
di: Yao, Yuan, et al.
Pubblicazione: (2024)

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
di: Yu, Tianyu, et al.
Pubblicazione: (2025)

AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
di: Li, Yishan, et al.
Pubblicazione: (2026)

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
di: Zhao, Weilin, et al.
Pubblicazione: (2024)

Robust and Scalable Model Editing for Large Language Models
di: Chen, Yingfa, et al.
Pubblicazione: (2024)

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
di: Zhou, Yixuan, et al.
Pubblicazione: (2025)

All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment
di: Zhang, Chunhui, et al.
Pubblicazione: (2023)

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
di: Zhang, Zhong, et al.
Pubblicazione: (2025)

Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts
di: Chen, Yingfa, et al.
Pubblicazione: (2026)

Robust Graph Neural Networks for Stability Analysis in Dynamic Networks
di: Zhang, Xin, et al.
Pubblicazione: (2024)

Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
di: Liu, Yewei, et al.
Pubblicazione: (2025)

BlockFFN: Towards End-Side Acceleration-Friendly Mixture-of-Experts with Chunk-Level Activation Sparsity
di: Song, Chenyang, et al.
Pubblicazione: (2025)

Data Science and Technology Towards AGI Part I: Tiered Data Management
di: Wang, Yudong, et al.
Pubblicazione: (2026)

Large Language Models as Evaluators for Recommendation Explanations
di: Zhang, Xiaoyu, et al.
Pubblicazione: (2024)

Stuffed Mamba: Oversized States Lead to the Inability to Forget
di: Chen, Yingfa, et al.
Pubblicazione: (2024)

POI Extraction From Digital City: An Engineering Exploration With Large‐Language Models
di: Mingzheng Sun, et al.
Pubblicazione: (2025)

All‐Dielectric Ultra‐Broadband Microwave Absorbing Aerogel with Optimized Dielectric Dispersion via Dielectric Relaxation Time Regulation
di: Kang Zhang, et al.
Pubblicazione: (2025)

CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling
di: Qu, Zekai, et al.
Pubblicazione: (2025)

Tailored Regulation of Graphite Microcrystals via Tandem Catalytic Carbonization for Enhanced Electrochemical Performance of Hard Carbon in the Low‐Voltage Plateau
di: Limin Zhou, et al.
Pubblicazione: (2024)

Status and prospects of the $χ_{c1}(3872)$ at BESIII
di: Zhou, Hongjian, et al.
Pubblicazione: (2025)

LP Relaxations for Routing and Wavelength Assignment with Partial Path Protection: Formulations and Computations
di: Yang, Xianyan, et al.
Pubblicazione: (2025)

AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
di: Chen, Haotian, et al.
Pubblicazione: (2026)

A Verifiable and Traceable Asymmetric Fingerprinting Scheme for Encrypted 3D Models of Oblique Photography
di: Shuaikang Liu, et al.
Pubblicazione: (2025)

LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
di: Zhang, Yuanhe, et al.
Pubblicazione: (2025)

Strong Compression–Torsion Coupling Effect in Chiral Hyperbolic Metamaterials
di: Ran Zhou, et al.
Pubblicazione: (2025)

Physiological and microbiome adaptation of coral Turbinaria peltata in response to marine heatwaves
di: Xin Zhai, et al.
Pubblicazione: (2024)

An Efficient Approach to the Design and Construction of Novel Energetic Materials: Co‐Crystallization and Chemical Reaction of Insensitive Explosive ICM‐102 in Acidic Solutions
di: Fei Wang, et al.
Pubblicazione: (2024)

Cooperative Ion Migration Suppression via Multi‐Scale Regulation for Enhancing the Performance of Inverted Perovskite Solar Cells
di: Xu Wang, et al.
Pubblicazione: (2026)

Exploring HI Galaxy Redshift Survey Strategies for the FAST Core Array Interferometry
di: Li, Zhenglong, et al.
Pubblicazione: (2025)

Network Analysis of Psychosocial Adaptation in Intestinal Stoma Patients: A National Cross‐Sectional Study in China
di: Xu Zhang, et al.
Pubblicazione: (2025)

Regulation of Octahedral Distortions and Interlayer Spacing in 2D Perovskite Capping Layer Toward Efficient and Stable Solar Cells
di: Peng Xu, et al.
Pubblicazione: (2025)

Homomorphic encryption domain asymmetric fingerprinting scheme for 3D models of oblique photography
di: Shuaikang Liu, et al.
Pubblicazione: (2024)

Neodymium‐Mediated Coordinative Chain Transfer Homopolymerization of Bio‐Based Myrcene and Copolymerization With Butadiene and Isoprene
di: Xin Li, et al.
Pubblicazione: (2024)

Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond
di: Zhang, Jichuan, et al.
Pubblicazione: (2024)

Activation of AMPK/SIRT1/PGC‐1α Signaling Pathway by Casticin Protects Against S. aureus ‐Induced Endometritis
di: Nanzhu Wang, et al.
Pubblicazione: (2026)

T3SS translocon induces pyroptosis by direct interaction with NLRC4/NAIP inflammasome.
di: Zhao, Yan, et al.
Pubblicazione: (2025)

Nasal‐Specific Immunoglobulin E to Total Immunoglobulin E Ratio Mediates the Effect of Natural Pollen Exposure on Symptom Severity in Patients With Seasonal Allergic Rhinitis
di: Dong Liu, et al.
Pubblicazione: (2025)