Adaptive Inference Router for Hybrid Reasoning
Deploy a lightweight query difficulty classification head to automatically toggle between short and long reasoning decoding strategies during inference.
Source paper
Tianyu Yu, Zefan Wang, Chongyi Wang, Fuwei Huang, Wenshuo Ma, Zhihui He, Tianchi Cai, Weize Chen, Yuxiang Huang, Yuanqian Zhao, Bokai Xu, Junbo Cui, Yingjing Xu, Liqing Ruan, Luoyuan Zhang, Hanyu Liu, Jingkun Tang, Hongyuan Liu, Qining Guo, Wenhao Hu, Bingxiang He, Jie Zhou, Jie Cai, Ji Qi, Zonghao Guo, Chi Chen, Guoyang Zeng, Yuxuan Li, Ganqu Cui, Ning Ding, Xu Han, Yuan Yao, Zhiyuan Liu, Maosong Sun
Generated by AI. The paper’s authors did not write these.
Deploy a lightweight query difficulty classification head to automatically toggle between short and long reasoning decoding strategies during inference.
Implement an entropy-aware token budget mechanism within the 3D-resampler to dynamically allocate visual query tokens based on video motion complexity.
Curate a video-OCR dataset and fine-tune the resampler and language model to learn temporal text continuity and tracking in dynamic video sequences.
MiniCPM-V 4.5 is an 8B parameter Multimodal Large Language Model (MLLM) designed to maximize performance and efficiency through architectural and training innovations. The paper introduces a unified 3D-Resampler for compact spatial-temporal visual encoding, a document learning paradigm that uses dynamic noise to unify OCR and context reasoning, and a hybrid Reinforcement Learning strategy that alternates between short and long chain-of-thought reasoning modes.
The model integrates a lightweight visual encoder with a Unified 3D-Resampler that compresses images and videos into a small, fixed number of tokens (e.g., 128 tokens for video) to reduce computational overhead. The training pipeline utilizes a 'corruption-based' document learning objective to fuse OCR and semantic understanding, followed by Reinforcement Learning with Preference Optimization (GRPO) to align both fast (short) and slow (long chain-of-thought) reasoning capabilities.