GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
EurekaTian
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
EurekaTian
Model Tree
Qwen/Qwen3.5-4B
Input Modalities
Output Modalities
Supported Functionality
SyncPro forks the decoder into synchronous internal-reasoning and external-response branches. At each streaming step, it learns whether to remain silent, reason internally, or speak, while preserving causal processing.
This checkpoint was initialized from Qwen/Qwen3.5-4B and trained on 189,403 streaming trajectories using:
The release contains merged BF16 inference weights. Optimizer shards, scheduler state, RNG state, and other resume-only training artifacts are intentionally excluded. Inference code and benchmark adapters are documented in the SyncPro repository.
The model is intended for research on causal streaming-video understanding, proactive response timing, and separated internal/external generation. Training annotations are available in SyncPro-189k. Source videos are not redistributed and must be obtained from their original publishers under the applicable terms.
The checkpoint may inherit limitations and biases from Qwen3.5-4B and the public research datasets used for training. It should not be treated as a safety-critical monitoring system.
The model weights are released under the Apache License 2.0. The annotation dataset has separate licensing and source-specific terms described on its dataset card.
bibtex
@misc{tian2026syncpro, title = {SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding}, author = {Tian, Xueyun and Xu, Bingbing and Liu, Jiaming and Yu, Jinpeng and Shi, Yang and Zhao, Yu and Huang, Ruihua and Wang, Yuanzhuo and Shen, Huawei}, year = {2026}, url = {https://eureka-maggie.github.io/SyncPro/}}