MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe
Fuente:
arXiv
Saved in:
| Main Authors: | Yu, Tianyu, Wang, Zefan, Wang, Chongyi, Huang, Fuwei, Ma, Wenshuo, He, Zhihui, Cai, Tianchi, Chen, Weize, Huang, Yuxiang, Zhao, Yuanqian, Xu, Bokai, Cui, Junbo, Xu, Yingjing, Ruan, Liqing, Zhang, Luoyuan, Liu, Hanyu, Tang, Jingkun, Liu, Hongyuan, Guo, Qining, Hu, Wenhao, He, Bingxiang, Zhou, Jie, Cai, Jie, Qi, Ji, Guo, Zonghao, Chen, Chi, Zeng, Guoyang, Li, Yuxuan, Cui, Ganqu, Ding, Ning, Han, Xu, Yao, Yuan, Liu, Zhiyuan, Sun, Maosong |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
by: Cui, Junbo, et al.
Published: (2026)
by: Cui, Junbo, et al.
Published: (2026)
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
by: Yao, Yuan, et al.
Published: (2024)
by: Yao, Yuan, et al.
Published: (2024)
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
by: Hu, Shengding, et al.
Published: (2024)
by: Hu, Shengding, et al.
Published: (2024)
MiniCPM4: Ultra-Efficient LLMs on End Devices
by: MiniCPM Team, et al.
Published: (2025)
by: MiniCPM Team, et al.
Published: (2025)
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
by: MiniCPM Team, et al.
Published: (2026)
by: MiniCPM Team, et al.
Published: (2026)
Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction
by: He, Chaoqun, et al.
Published: (2026)
by: He, Chaoqun, et al.
Published: (2026)
JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
by: He, Bingxiang, et al.
Published: (2025)
by: He, Bingxiang, et al.
Published: (2025)
The Afrofuturist Evolution: Creative Paths to Self‐Discovery. By Ytasha L.Womack, Chicago: Lawrence Hill Books, 2025. 321 pp. $19.99 (paperback). ISBN: 978‐0‐89733‐455‐6
by: Yingjing Xu
Published: (2025)
by: Yingjing Xu
Published: (2025)
Nigerian Speculative Fiction: The Evolution. By Chukwunonso, Ezeiyoke, New York: Routledge India, 2025. 226 pp. $34.69 (paperback). ISBN: 978‐1‐032‐95555‐1
by: Yingjing Xu, et al.
Published: (2026)
by: Yingjing Xu, et al.
Published: (2026)
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
by: Zhang, Zhong, et al.
Published: (2025)
by: Zhang, Zhong, et al.
Published: (2025)
InsightEdit: Towards Better Instruction Following for Image Editing
by: Xu, Yingjing, et al.
Published: (2024)
by: Xu, Yingjing, et al.
Published: (2024)
Some exact results on $4$-cycles: stability and supersaturation
by: He, Jialin, et al.
Published: (2019)
by: He, Jialin, et al.
Published: (2019)
Iterative Equalization of CPM With Unitary Approximate Message Passing
by: Liu, Zilong, et al.
Published: (2024)
by: Liu, Zilong, et al.
Published: (2024)
Atmos-Bench: 3D Atmospheric Structures for Climate Insight
by: Xu, Tianchi
Published: (2025)
by: Xu, Tianchi
Published: (2025)
Black‐Scholes Meet Imitation Learning: Evidence From Deep Hedging in China
by: Fuwei Jiang, et al.
Published: (2025)
by: Fuwei Jiang, et al.
Published: (2025)
ICAS: IP Adapter and ControlNet-based Attention Structure for Multi-Subject Style Transfer Optimization
by: Liu, Fuwei
Published: (2025)
by: Liu, Fuwei
Published: (2025)
Math‐anxious people suffer more in math‐related events: The perspective of reward processing on motivated behavior
by: Fang Cui, et al.
Published: (2025)
by: Fang Cui, et al.
Published: (2025)
Face4RAG: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese
by: Xu, Yunqi, et al.
Published: (2024)
by: Xu, Yunqi, et al.
Published: (2024)
Densing Law of LLMs
by: Xiao, Chaojun, et al.
Published: (2024)
by: Xiao, Chaojun, et al.
Published: (2024)
UltraFeedback: Boosting Language Models with Scaled AI Feedback
by: Cui, Ganqu, et al.
Published: (2023)
by: Cui, Ganqu, et al.
Published: (2023)
Process Reinforcement through Implicit Rewards
by: Cui, Ganqu, et al.
Published: (2025)
by: Cui, Ganqu, et al.
Published: (2025)
Explicit Topology Optimization Based on the Joint‐Driven Moving Morphable Components
by: Jiaqi Xu, et al.
Published: (2025)
by: Jiaqi Xu, et al.
Published: (2025)
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
by: Zhou, Yixuan, et al.
Published: (2025)
by: Zhou, Yixuan, et al.
Published: (2025)
Quantitative Characterization Model of Macroscopic Mechanical Properties of Recycled Concrete Based on Porosity and Pore Sizes
by: Haiyu Chen, et al.
Published: (2024)
by: Haiyu Chen, et al.
Published: (2024)
UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs
by: He, Chaoqun, et al.
Published: (2024)
by: He, Chaoqun, et al.
Published: (2024)
Freeze-in Warm Dark Matter via Dimension-6 Operators in 3-3-1 Models
by: Liu, Fuwei, et al.
Published: (2026)
by: Liu, Fuwei, et al.
Published: (2026)
Longitudinal Seismic Behavior of Cracked Tunnels Crossing Faults: Insights From a Fracture‐Aware Modeling Approach
by: Xianwang Liu, et al.
Published: (2026)
by: Xianwang Liu, et al.
Published: (2026)
Nonlinear Coupling between Magnetic Gears
by: Liu, Tianchi
Published: (2024)
by: Liu, Tianchi
Published: (2024)
The neural mechanisms of identifiable victim effect in prosocial decision‐making
by: Hailing Zhao, et al.
Published: (2024)
by: Hailing Zhao, et al.
Published: (2024)
Deep Learning–Based Fault Identification Testing Experiment for Bellows Valves
by: Jianwen Guo, et al.
Published: (2024)
by: Jianwen Guo, et al.
Published: (2024)
A hypergraph bipartite Turán problem with odd uniformity
by: Ma, Jie, et al.
Published: (2024)
by: Ma, Jie, et al.
Published: (2024)
Sharpness-Aware Data Poisoning Attack
by: He, Pengfei, et al.
Published: (2023)
by: He, Pengfei, et al.
Published: (2023)
From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones
by: Yuan, Lifan, et al.
Published: (2025)
by: Yuan, Lifan, et al.
Published: (2025)
Numerical approximations to invariant measures of hybrid stochastic differential equations with superlinear coefficients via the backward Euler-Maruyama method
by: Liu, Wei, et al.
Published: (2025)
by: Liu, Wei, et al.
Published: (2025)
Data‐Driven Online Optimization for Fluid Catalytic Cracking Using Bayesian Case‐Based Reasoning
by: Ge He, et al.
Published: (2025)
by: Ge He, et al.
Published: (2025)
The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuning
by: He, Bingxiang, et al.
Published: (2024)
by: He, Bingxiang, et al.
Published: (2024)
Combining Cloud and Mobile Computing for Machine Learning
by: Xu, Ruiqi, et al.
Published: (2024)
by: Xu, Ruiqi, et al.
Published: (2024)
Order-$v^4$ corrections to heavy quark fragmentation to S-wave heavy quarkonium
by: Cui, Sai, et al.
Published: (2025)
by: Cui, Sai, et al.
Published: (2025)
Walking-dilaton hybrid inflation with $B-L$ Higgs embedded in dynamical scalegenesis
by: Liu, Jie, et al.
Published: (2024)
by: Liu, Jie, et al.
Published: (2024)
Estimation and Inference in Ultrahigh Dimensional Partially Linear Single-Index Models
by: Cui, Shijie, et al.
Published: (2024)
by: Cui, Shijie, et al.
Published: (2024)
Similar Items
-
MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction
by: Cui, Junbo, et al.
Published: (2026) -
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
by: Yao, Yuan, et al.
Published: (2024) -
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
by: Hu, Shengding, et al.
Published: (2024) -
MiniCPM4: Ultra-Efficient LLMs on End Devices
by: MiniCPM Team, et al.
Published: (2025) -
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
by: MiniCPM Team, et al.
Published: (2026)