Any questions related to general MAI Workshop and Challenges organization can be asked in this thread.
Mobile AI Workshop General Organization Questions
- Thread starter Andrey Ignatov
- Start date
First, thank you for launching this great challenge.
Most tasks from last year's ICCVW2025 didn't have winners selected and weren't properly concluded. I'm curious if this aspect will be resolved this time.
Also, I'm wondering if all methods submitted by teams last year will be included in report paper.
Most tasks from last year's ICCVW2025 didn't have winners selected and weren't properly concluded. I'm curious if this aspect will be resolved this time.
Also, I'm wondering if all methods submitted by teams last year will be included in report paper.
Last edited:
Yes, that's the case: we've evaluated all solutions submitted to ICCVW2025 for all challenges, but unfortunately there were not many major changes in the results / model performance compared to the previous CVPR edition. Therefore, there was not much sense in publishing challenge reports for only few solutions that demonstrated reasonable results, and they are transferred automatically to this year MAI CVPR edition. This is also better from the point of view of publications: CVPR proceedings are generally rated higher and have typically a better publicity.
Yes, exactly.
sr_enhance
New member
Please notify me by email when the test phase of the Mobile AI Challenge begins. Thank you.
rank delta
New member
I am participating in the EFFICIENT LLMS CHALLENGE. After the TEST Phase opened, the result of my submission shows Status: Failed. Based on previous discussions on the forum, it seems that this might not affect the final evaluation results. Could you please confirm whether this is expected behavior, or if there might be an issue with my submission that I should fix?
Yes, that's the case, you can ignore Codabench issues as we are validating all submissions offline.
sr_enhance
New member
Can a team submit multiple different proposals?
Each team can make only one final submission per challenge.
However, multiple solutions can be described in the challenge paper if you decide to submit one to the workshop.
yoonsuk kang
New member
I have two questions regarding the competition:
1. Preliminary Results: Even though the final deadline was pushed back, do you still plan to announce the preliminary test results?
2. Notification Policy: Just like the last year competition, if there are no major changes in the results, do you plan not to write a report paper?
Thank you
1. Preliminary Results: Even though the final deadline was pushed back, do you still plan to announce the preliminary test results?
2. Notification Policy: Just like the last year competition, if there are no major changes in the results, do you plan not to write a report paper?
Thank you
It's hard to say now if preliminary results would be released on the 21st of March for all competitions. However, that shouldn't be a blocker - if you have good results on the validation set, you can submit a paper without final numbers.
Based on preliminary numbers, it's likely that challenge papers would be prepared for the majority of competitions this year.
Yes, that's an expected behavior. Note that only your last upload counts.
Sorry, yes, it died unfortunately with old Codalab storage.
We are using the standard built-in TensorFlow PSNR/SSIM functions for computing metrics in all competitions:
https://www.tensorflow.org/api_docs/python/tf/image/psnr
https://www.tensorflow.org/api_docs/python/tf/image/ssim
Input / output image values should be in the standard [0, 255] range.
sr_enhance
New member
Has the result of the Mobile AI 2026 Rendering Realistic Bokeh Challenge been released?
Not yet, the results are released in waves, right now they are already available for Quantized Super-Res, Floating-Point Super-Res and Image Denoising Challenges. For other competitions they would be released next days.
Note that if you want to submit a paper tomorrow - you don't need to present the final challenge results there. Numerical accuracy on the validation set + runtime values on some device would be enough for the initial submission.
All results should be released by the end of this week.
rank delta
New member
Hello, has the result of the Mobile AI 2026 Efficient LLM Challenge been released? I have not received any notification email yet, so I would like to confirm the current status. Thank you!
The results for all challenges except for Stable Diffusion and Efficient LLMs have been released.
For the latter two, the results would be finalized in the next few days.
sr_enhance
New member
Dear organizers, the MAI 2026 workshop has successfully concluded. Will certificates be awarded? Otherwise, all the time we invested in the MAI competition will have been wasted.