Model Description
This model is fine-tuned from Qwen3-VL-2B-Instruct using the G-Substrate framework. G-Substrate treats graph structure as a persistent structural substrate that accumulates knowledge across heterogeneous data modalities and tasks. It employs a unified structural schema for compatibility and an interleaved role-based training strategy.
Training Details
- Base model: Qwen3-VL-2B-Instruct
- Training method: Full fine-tuning (SFT) with multi-task learning
- Training data: Scene graphs, event graphs, molecular graphs, graph algorithmic tasks, and interleaved role-based data
- Epochs: 2
- Learning rate: 8e-6 (cosine schedule, warmup 10%)
- Batch size: 1 per device, 32 gradient accumulation steps
- GPUs: 2x NVIDIA A100 (DeepSpeed ZeRO-3)
Supported Tasks
Table with columns: Task, Domain, Input, Output| Task | Domain | Input | Output |
|---|
| Scene Graph Generation | Visual | Image | Graph triplets |
| Event Relation Extraction | Text | Document + events | Event relation graph |
| Molecular Graph Description | Scientific | SMILES + graph | Natural language description |
| Graph Algorithmic Reasoning | Algorithmic | Graph description | Algorithm answer |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
For batch inference with vLLM, see the G-Substrate repository.
Results
Table with columns: CT, CD, SP, BM, BLEU-4, ROUGE-L, PCIs R@50, MA-S F1, MA-T F1, MA-C F1, HiE F1| CT | CD | SP | BM | BLEU-4 | ROUGE-L | PCIs R@50 | MA-S F1 | MA-T F1 | MA-C F1 | HiE F1 |
|---|
| 98.41 | 96.97 | 48.59 | 94.54 | 51.53 | 68.47 | 25.38 | 52.20 | 42.68 | 40.91 |
Citation
@inproceedings{li2026gsubstrate,
title={Graph is a Substrate Across Data Modalities},
author={Li, Ziming and Wu, Xiaoming and Wang, Zehong and Li, Jiazheng and Tian, Yijun and Bi, Jinhe and Ma, Yunpu and Ye, Yanfang and Zhang, Chuxu},
booktitle={ICML},
year={2026}
}