| Intended Task/Domain: |
Scientific research and quantum computing calibration experiment analysis |
| Model Type: |
Mixture-of-Experts Vision-Language Model (MoE VLM) based on Qwen3.5-35B-A3B |
| Intended Users: |
Quantum computing researchers, calibration engineers, and developers analyzing experiment results in automated or assisted calibration workflows. |
| Output: |
Text responses covering technical descriptions, experimental conclusions, significance assessments, fit quality evaluations, parameter extraction, and experiment success classifications. |
| Describe how the model works: |
Experiment plot images are encoded into visual tokens and combined with prompt text tokens before being processed by the Qwen3.5-35B-A3B MoE language model. The model activates 8 of 256 experts per token, corresponding to about 3B active parameters out of roughly 35B total parameters, and generates analytical text autoregressively through a vLLM-served OpenAI-compatible API. |
| Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: |
Not Applicable |
| Technical Limitations & Mitigation: |
The model is domain-specific to quantum calibration experiments and may not generalize to broader VLM tasks. Performance varies by question type, with weaker results on experimental significance and parameter extraction than on fit quality assessment. Outputs should be validated by domain experts before being used in experimental workflows. |
| Performance Metrics: |
QCalEval zero-shot scores (averaged): Q1 Technical Description 87.8, Q2 Experimental Conclusion 67.1, Q3 Experimental Significance 64.7, Q4 Fit Quality Assessment 90.5, Q5 Parameter Extraction 62.5, Q6 Experiment Success 75.3, Overall 74.7. |
| Verified to have met prescribed NVIDIA quality standards: |
Yes |
| Potential Known Risks: |
The model may misclassify rare or ambiguous experiment outcomes, may hallucinate details outside the quantum calibration domain, and does not have access to raw numerical traces or experiment metadata beyond what is visible in the input plots. |
| Governing Terms: |
The Ising-Calibration-1-35B-A3B is governed by the NVIDIA Open Model License Agreement. |
| Additional Information: |
For Qwen3.5-35B-A3B Apache License, Version 2.0. |
