Downloads · 30 days
93
5% of all-time downloads
inclusionAI/ZwZ-2B
ZwZ-2B is a image-text-to-text model from inclusionAI. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
93
5% of all-time downloads
All-time downloads
1.7K
Public
Parameters
2.4B
4.9 GB on disk
Likes
5
Public
Click a slice to open those files.
.safetensors4.9 GB · 100%
From the Hugging Face model README
📃 Paper | 🏠 Project | 🤗 Collection
</div>ZwZ-2B is a fine-grained multimodal perception model built upon Qwen3-VL-2B. It is trained using Region-to-Image Distillation (R2I) combined with reinforcement learning, enabling superior fine-grained visual understanding in a single forward pass — no inference-time zooming or tool calling required. ZwZ-2B achieves state-of-the-art performance on fine-grained perception benchmarks among open-source models of comparable size.
<div style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;max-width:780px;margin:0 auto;padding:12px 0"> <p style="font-size:11px;color:#555;margin-bottom:10px"> <table style="width:100%;border-collapse:collapse;font-size:10px"> <thead> <tr> <th style="padding:6px 4px;text-align:left;font-weight:600;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:10px" rowspan="2">Models</th> <th style="padding:6px 4px;text-align:center;font-weight:600;border-bottom:1px solid #7c3aed;color:#7c3aed;font-size:10px" colspan="8">General Perception</th> <th style="padding:6px 4px;text-align:center;font-weight:600;border-bottom:1px solid #7c3aed;color:#7c3aed;font-size:10px" colspan="2">Specific Perception</th> <th style="padding:6px 4px;text-align:center;font-weight:600;border-bottom:1px solid #7c3aed;color:#7c3aed;font-size:10px" colspan="2">OOD Generalization</th> <th style="padding:6px 4px;text-align:center;font-weight:600;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:10px" rowspan="2">Avg</th> </tr> <tr> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">ZoomBench</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">HR-4K</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">HR-8K</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">VStar</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">CV-B.</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">MME-RW-en</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">MME-RW-cn</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px;background:rgba(0,180,0,0.1)">GP-Avg</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">CountQA</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">ColorB.</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">MMStar</th> <th style="padding:5px 4px;text-align:center;font-weight:500;border-bottom:2px solid #7c3aed;color:#7c3aed;font-size:9px">BabyVision</th> </tr> </thead> <tbody> <!-- Closed-Source Models --> <tr><td colspan="14" style="padding:5px 8px;font-weight:600;font-size:9px;color:#7c3aed;border-bottom:1px solid rgba(124,58,237,0.2);background:rgba(124,58,237,0.1);font-style:italic">Closed-Source Models</td></tr> <tr style="background:rgba(255,240,150,0.15)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">GPT-5.1</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">47.22</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">67.00</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">70.16</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">84.22</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">64.04</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">55.57</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">64.78</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">31.41</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">83.43</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">71.60</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">13.92</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">59.44</td> </tr> <tr style="background:rgba(255,240,150,0.15)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Gemini-3-Flash</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">59.29</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">87.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">85.00</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">86.39</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">89.57</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">74.86</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">72.62</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">79.37</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">85.47</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">83.60</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">34.51</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.10</td> </tr> <!-- Open-Source Models --> <tr><td colspan="14" style="padding:5px 8px;font-weight:600;font-size:9px;color:#7c3aed;border-bottom:1px solid rgba(124,58,237,0.2);background:rgba(124,58,237,0.1);font-style:italic">Open-Source Models</td></tr> <tr style="background:rgba(180,180,180,0.08)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Qwen3-VL-2B</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">41.30</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">71.75</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">70.12</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">72.77</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">78.94</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">59.52</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">60.77</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">65.02</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">22.19</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">76.86</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">60.4</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">12.11</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">56.98</td> </tr> <tr style="background:rgba(180,180,180,0.08)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Qwen3-VL-4B</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">40.24</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">78.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">72.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">80.10</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">84.95</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.47</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.63</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">69.07</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">28.14</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">81.63</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">69.73</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">13.66</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">61.52</td> </tr> <tr style="background:rgba(180,180,180,0.08)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Qwen2.5-VL-7B</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">42.49</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">71.62</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">67.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">78.53</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.34</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">60.80</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">58.30</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">64.99</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">18.91</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">76.36</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">61.93</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">12.89</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">56.82</td> </tr> <tr style="background:rgba(180,180,180,0.08)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Qwen3-VL-8B</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">37.87</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">78.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">74.63</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">86.39</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">85.44</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.96</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.67</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">70.83</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">28.99</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">82.77</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">70.93</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">12.89</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">62.86</td> </tr> <tr> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">MiMo-VL-7B-RL</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">45.09</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">74.38</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">72.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">81.15</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">84.31</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.40</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">59.78</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">68.71</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">28.27</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">82.80</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">73.53</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">16.24</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">61.98</td> </tr> <tr> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">MiniCPM-V-4.5 (9B)</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">42.60</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">69.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.62</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">70.16</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">80.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">58.16</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">56.23</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">62.99</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">23.43</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">79.75</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">67.87</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">14.95</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">56.99</td> </tr> <tr> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">GLM-4.5V (108B)</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">49.23</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">81.63</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">74.88</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">83.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">87.59</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.04</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">60.71</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">71.90</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">35.93</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">84.59</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.87</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">15.72</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.04</td> </tr> <tr> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Qwen3-VL-235B-A22B</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">49.11</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>84.50</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>81.62</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">87.96</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">86.72</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">67.07</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.29</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">74.61</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>40.58</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>85.62</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>76.33</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>18.30</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">67.55</td> </tr> <tr> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">Kimi-K2.5 (1T)</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>56.33</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">81.87</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.38</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">85.86</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>89.18</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>71.51</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>68.40</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">75.50</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>52.81</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>86.61</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>81.80</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>33.25</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>71.18</strong></td> </tr> <!-- Our Models --> <tr><td colspan="14" style="padding:5px 8px;font-weight:600;font-size:9px;color:#7c3aed;border-bottom:1px solid rgba(124,58,237,0.2);background:rgba(124,58,237,0.1);font-style:italic">Our Models</td></tr> <tr style="background:rgba(100,130,255,0.06)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>ZwZ-2B (Ours)</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">53.49</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">77.00</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.38</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">82.72</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">83.36</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.61</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">65.39</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">71.85</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">21.60</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">79.37</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.40</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">17.78</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">62.28</td> </tr> <tr style="background:rgba(100,130,255,0.06)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>ZwZ-4B (Ours)</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">55.74</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">81.75</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">79.50</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>92.67</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><u>87.90</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">68.52</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">68.09</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)"><u>76.31</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">30.82</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">83.08</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">71.13</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">16.24</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.86</td> </tr> <tr style="background:rgba(100,130,255,0.06)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px"><strong>ZwZ-7B (Ours)</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">55.62</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">75.38</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">73.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">88.48</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">79.83</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.21</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">66.96</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px;background:rgba(0,180,0,0.08)">72.25</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">20.72</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">80.82</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">63.40</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">15.98</td> <td style="padding:4px 4px;text-align:center;border-bottom:1px solid rgba(128,128,128,0.15);font-size:10px">62.42</td> </tr> <tr style="background:rgba(100,130,255,0.06)"> <td style="padding:4px 4px;padding-left:14px;border-bottom:2px solid #7c3aed;font-size:10px"><strong>ZwZ-8B (Ours)</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><strong>58.11</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><u>84.38</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><strong>82.00</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><u>91.10</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px">87.40</td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><u>69.87</u></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><strong>70.59</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px;background:rgba(0,180,0,0.08)"><strong>77.64</strong></td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px">32.40</td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px">83.59</td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px">73.13</td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px">16.75</td> <td style="padding:4px 4px;text-align:center;border-bottom:2px solid #7c3aed;font-size:10px"><u>68.12</u></td> </tr> </tbody> </table> </div> <div align=center> <img src="gp_avg_comparison.png" width="90%" alt="avg_comparison"/> </div>Traditional "Thinking-with-Images" methods zoom into regions of interest during inference, incurring high latency from repeated tool calls and visual re-encoding. ZwZ transforms zooming from an inference-time tool into a training-time primitive:
pip install transformers accelerate torch
from transformers import Qwen3VLForConditionalGeneration, AutoProcessor
# default: Load the model on the available device(s)
model = Qwen3VLForConditionalGeneration.from_pretrained(
"inclusionAI/ZwZ-2B", dtype="auto", device_map="auto"
)
processor = AutoProcessor.from_pretrained("inclusionAI/ZwZ-2B")
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
},
{"type": "text", "text": "Describe this image."},
],
}
]
# Preparation for inference
inputs = processor.apply_chat_template(
messages,
tokenize=True,
add_generation_prompt=True,
return_dict=True,
return_tensors="pt"
)
inputs = inputs.to(model.device)
# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=128)
generated_ids_trimmed = [
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)
ZwZ-2B is trained on inclusionAI/ZwZ-RL-VQA, a 74K-sample Region-to-Image distilled VQA dataset synthesized from diverse image pools (SA-1B, LAION, MetaCLIP, Visual Genome, CC12M, STPLS3D).
@article{wei2026zooming,
title={Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception},
author={Wei, Lai and He, Liangbo and Lan, Jun and Dong, Lingzhong and Cai, Yutong and Li, Siyuan and Zhu, Huijia and Wang, Weiqiang and Kong, Linghe and Wang, Yue and Zhang, Zhuosheng and Huang, Weiran},
journal={arXiv preprint arXiv:2602.11858},
year={2026}
}
This model follows the license of Qwen3-VL-2B. Please refer to the base model's license for usage terms.