MoBA: Mixture of Block Attention for Long-Context LLMs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | Lu, Enzhe, Jiang, Zhejun, Liu, Jingyuan, Du, Yulun, Jiang, Tao, Hong, Chao, Liu, Shaowei, He, Weiran, Yuan, Enming, Wang, Yuzhi, Huang, Zhiqi, Yuan, Huan, Xu, Suting, Xu, Xinran, Lai, Guokun, Chen, Yanru, Zheng, Huabin, Yan, Junjie, Su, Jianlin, Wu, Yuxin, Zhang, Neo Y., Yang, Zhilin, Zhou, Xinyu, Zhang, Mingxing, Qiu, Jiezhong |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
Muon is Scalable for LLM Training
par: Liu, Jingyuan, et autres
Publié: (2025)
par: Liu, Jingyuan, et autres
Publié: (2025)
Kimi Linear: An Expressive, Efficient Attention Architecture
par: Kimi Team, et autres
Publié: (2025)
par: Kimi Team, et autres
Publié: (2025)
Attention Residuals
par: Kimi Team, et autres
Publié: (2026)
par: Kimi Team, et autres
Publié: (2026)
A Novel Nonlinear Output‐Only Damage Detection Method Based on the Prediction Error of PCA Euclidean Distances Under Environmental and Operational Variations
par: Jiezhong Huang, et autres
Publié: (2025)
par: Jiezhong Huang, et autres
Publié: (2025)
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
par: Qin, Ruoyu, et autres
Publié: (2024)
par: Qin, Ruoyu, et autres
Publié: (2024)
Evolving Prompt Adaptation for Vision-Language Models
par: Zhang, Enming, et autres
Publié: (2026)
par: Zhang, Enming, et autres
Publié: (2026)
Prefill-as-a-Service: KVCache of Next-Generation Models Could Go Cross-Datacenter
par: Qin, Ruoyu, et autres
Publié: (2026)
par: Qin, Ruoyu, et autres
Publié: (2026)
Atmospheric warming during rapid sea ice loss over the Barents–Kara seas in winter
par: Xia Hu, et autres
Publié: (2024)
par: Xia Hu, et autres
Publié: (2024)
Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfer
par: Zhang, Enming, et autres
Publié: (2025)
par: Zhang, Enming, et autres
Publié: (2025)
Unlocking Optical Prior: Spectrum-Guided Knowledge Transfer for SAR Generalized Category Discovery
par: Xia, Jingyuan, et autres
Publié: (2026)
par: Xia, Jingyuan, et autres
Publié: (2026)
The Safety-Aware Denoiser for Text Diffusion Models
par: Yusuf, Amman, et autres
Publié: (2026)
par: Yusuf, Amman, et autres
Publié: (2026)
The uniqueness of Poincaré type extremal Kähler metric
par: Xu, Yulun
Publié: (2025)
par: Xu, Yulun
Publié: (2025)
Immune escape of BA.2.86 is comparable to XBB subvariants from the plasma of BA.5‐ and BA.5‐XBB‐convalescent subpopulations
par: Xiaoyun Yang, et autres
Publié: (2024)
par: Xiaoyun Yang, et autres
Publié: (2024)
Accuracy‐Improved Fault Diagnosis Method for Rolling Bearing Based on Enhanced ESGMD‐CC and BA‐ELM Model
par: Wei Yuan, et autres
Publié: (2024)
par: Wei Yuan, et autres
Publié: (2024)
Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
par: Wu, Yanru, et autres
Publié: (2025)
par: Wu, Yanru, et autres
Publié: (2025)
Kimi k1.5: Scaling Reinforcement Learning with LLMs
par: Kimi Team, et autres
Publié: (2025)
par: Kimi Team, et autres
Publié: (2025)
Do environmental courts drive corporate green innovation? A study based on double machine learning
par: Yanru Liang, et autres
Publié: (2024)
par: Yanru Liang, et autres
Publié: (2024)
A Decade of Deep Learning for Remote Sensing Spatiotemporal Fusion: Advances, Challenges, and Opportunities
par: Sun, Enzhe, et autres
Publié: (2025)
par: Sun, Enzhe, et autres
Publié: (2025)
Spectral Switches of Light in Curved Space
par: Ju, Suting, et autres
Publié: (2024)
par: Ju, Suting, et autres
Publié: (2024)
A Baseline $T\log^2 T$ Upper Bound for KL-Regularized Prime--Zero Optimal Transport
par: Yang, Zhejun
Publié: (2025)
par: Yang, Zhejun
Publié: (2025)
Effects of Trade Liberalization on Health: Evidence From the Size of Trading Networks
par: Cheuk Yin Ho, et autres
Publié: (2026)
par: Cheuk Yin Ho, et autres
Publié: (2026)
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
par: Qin, Ruoyu, et autres
Publié: (2025)
par: Qin, Ruoyu, et autres
Publié: (2025)
Kimi-VL Technical Report
par: Kimi Team, et autres
Publié: (2025)
par: Kimi Team, et autres
Publié: (2025)
Data From: Leveraging Sequence Purification for Accurate Prediction of Multiple Conformational States with AlphaFold2
par: Xing, Enming
Publié: (2025)
par: Xing, Enming
Publié: (2025)
TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis
par: Li, Xinran, et autres
Publié: (2026)
par: Li, Xinran, et autres
Publié: (2026)
Kimi-Audio Technical Report
par: KimiTeam, et autres
Publié: (2025)
par: KimiTeam, et autres
Publié: (2025)
D-FaST: Cognitive Signal Decoding with Disentangled Frequency-Spatial-Temporal Attention
par: Chen, Weiguo, et autres
Publié: (2024)
par: Chen, Weiguo, et autres
Publié: (2024)
Canagliflozin Delays Aortic Valve Calcification by Enhancing the AMPK /Nrf2/ HO ‐1 Antioxidant Signaling Pathway in Valvular Interstitial Cells
par: Quangong Zhao, et autres
Publié: (2025)
par: Quangong Zhao, et autres
Publié: (2025)
Certain Fourier Operators and their Associated Poisson Summation Formulae on $\mathrm{GL}_1$
par: Jiang, Dihua, et autres
Publié: (2021)
par: Jiang, Dihua, et autres
Publié: (2021)
Wear Condition Evolution of Cylinder Liner‐Piston Ring on the Two‐Stroke Marine Diesel Engine Through Long‐Term Monitoring and Analysis of Cylinder Oil
par: Yicong Xu, et autres
Publié: (2025)
par: Yicong Xu, et autres
Publié: (2025)
Exploring the Interplay Between Self‐Identity, Affective Style, Emotion Regulation, and Anxiety: Based on Bayesian Network Model
par: Ruizhi Huang, et autres
Publié: (2025)
par: Ruizhi Huang, et autres
Publié: (2025)
Stopping Rules for Monte Carlo Methods: A Review
par: Wu, Jiezhong, et autres
Publié: (2025)
par: Wu, Jiezhong, et autres
Publié: (2025)
Stopping Rules for Monte Carlo Methods of Martingale Difference Type
par: Wu, Jiezhong, et autres
Publié: (2025)
par: Wu, Jiezhong, et autres
Publié: (2025)
Develop a vascularized neuroimmune organoid model for studying sporadic Alzheimer’s disease
par: Ranjie Xu, et autres
Publié: (2024)
par: Ranjie Xu, et autres
Publié: (2024)
Research on Autodocking Control Technology of the Propellant Umbilical Connector of Launch Vehicles
par: Penghui Wu, et autres
Publié: (2024)
par: Penghui Wu, et autres
Publié: (2024)
Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment
par: Sheikhaei, Mohammad Sadegh, et autres
Publié: (2025)
par: Sheikhaei, Mohammad Sadegh, et autres
Publié: (2025)
An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification
par: Sheikhaei, Mohammad Sadegh, et autres
Publié: (2024)
par: Sheikhaei, Mohammad Sadegh, et autres
Publié: (2024)
Moving Horizon Estimation for Nonlinear Systems Subject to Measurement Outliers
par: Zhilin Liu, et autres
Publié: (2025)
par: Zhilin Liu, et autres
Publié: (2025)
The Resonant Order Theory of Everything (ROTE) "A Unified Spiral Framework from Quantum to Cosmic Scale"
par: Neo Brady, Neo, et autres
Publié: (2025)
par: Neo Brady, Neo, et autres
Publié: (2025)
A Discrete‐Time Integral Sliding Mode Predictive Control for Electronic Throttle With Experiments and Comparison
par: Yun Long, et autres
Publié: (2026)
par: Yun Long, et autres
Publié: (2026)
Documents similaires
-
Muon is Scalable for LLM Training
par: Liu, Jingyuan, et autres
Publié: (2025) -
Kimi Linear: An Expressive, Efficient Attention Architecture
par: Kimi Team, et autres
Publié: (2025) -
Attention Residuals
par: Kimi Team, et autres
Publié: (2026) -
A Novel Nonlinear Output‐Only Damage Detection Method Based on the Prediction Error of PCA Euclidean Distances Under Environmental and Operational Variations
par: Jiezhong Huang, et autres
Publié: (2025) -
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
par: Qin, Ruoyu, et autres
Publié: (2024)