Change Team Name Request

Your team name has been updated to BMI_DLUT.

View post 0

Change Team Name Request

Hello, Your team name has been updated to AML_LabCityU

View post 0

Change Team Name Request

We will update the team name soon. @yingyi_zhang @pengyue_jia3

View post 2

Change Team Name Request

Team name has been updated to Team_NVIDIA

View post 1

Has the Winner Notification already been sent?

My previous reply clearly states that the winner announcement will be made after the due diligence process is completed. Nowhere does it specify that it will be sent only to the winning participants. As is the standard practice for all challenges, the winner announcement email will be sent to all participating teams and candidates once the due diligence process is over.

View post 0

‼️ ⏰ Select Submission ID before 20th June, 2024 23:55 UTC

The winners are not announced yet. You will receive an email about the winner announcement once the due diligence is completed.

View post 0

Has the Winner Notification already been sent?

The winners are not announced yet. You will receive an email about the winner announcement once the due diligence is completed.

View post 1

‼️ ⏰ Select Submission ID before 20th June, 2024 23:55 UTC

Yes, we have extended the deadline till June 22nd 12:00 UTC (noon).

View post 0

⏰ Deadline Extended for Submission Selection Form (June 22nd 12:00 UTC)

Hello all,

We are extending the submission selection form deadline to June 22nd, 12:00 UTC (noon).

We will use either the top two submissions on the track-specific leaderboard or the submission IDs specified in the form. If you indicate more than two submissions for any track, we will consider the last two submission IDs. If you have already selected submission IDs on the form and wish to change them, you can do so before the new deadline.

Please note, that all submissions on the form must be eligible for the respective track. For instance, you cannot indicate a submission for Track-1 as your intended submission for Track-2 unless it is already on the leaderboard of Track-2.

Please follow the guidelines and fill out the form by 22nd June, 12:00 UTC.

All the best

View post 1

‼️ ⏰ Select Submission ID before 20th June, 2024 23:55 UTC

Yes, if your code is addressing all three tasks you can submit the same IDs for the 3 tasks.

View post 0

‼️ ⏰ Select Submission ID before 20th June, 2024 23:55 UTC

You can select 2 submission IDs for each task in the form.

View post 0

‼️ ⏰ Select Submission ID before 20th June, 2024 23:55 UTC

Hello Participants,

Please select Submission IDs for the private leaderboard evaluation.

Deadline for Form Submission:
20th June 2024, 23:59 UTC

Individual Participants:
Please submit the form only once. If multiple entries are made, we will consider your last form entry.

Teams:
If multiple team members submit the form, we will consider the Team Organizer’s last form entry as the final one.

Submit your form here: Meta Challenge Form

All the best,
Meta Comprehensive RAG Benchmark Challenge Team

View post 0

✨ Check out the KG Baseline

Hello all,

Check out the baseline and learn how to use the Knowledge Graph through MockAPI.
More details here.

All the best
Team CRAG

View post 0

🚨 IMP: Phase 2 Announcement

View post 0

Tag “Phase 2: 13 days left” appears today suddenly, and the submission remaining turns to 1?

Updates regarding Phase 2 will be shared soon. The leaderboard is visible for Round 1b.

View post 1

🚨 IMP: Phase 2 Announcement

Phase 2 Laucnh Updates: Comprehensive RAG Benchmark (CRAG) 2024

Hello everyone,

Welcome to Phase 2 of the CRAG: Comprehensive RAG Benchmark. Please carefully read the updates below.

Eligibility

• Teams: All teams with at least one successful submission in Phase 1 can enter Phase 2.

Key Updates for Phase 2

1. Time Limit: The time limit per example is 30 seconds.
2. Submission Limit: The submission limit for Phase 2 is 10 per week.
3. MockAPI Update: The MockAPI has been updated to include a private Knowledge Graph.
4. Leaderboard: 20% of the private test set will be used to run the leaderboard (same as Phase 1b).
5. Final Evaluation:
   • As soon as this phase ends, a final exhaustive evaluation will be conducted on the full Phase 2 test set on a submission of your choice (defaulting to your best submission on the leaderboard).
   • The top submission chosen by the team will be used for the final evaluation.
6. Submission Deadline: The last date to make a submission is June 20, 2024, at 23:55 UTC.

All the best,

Team CRAG 2024

View post 1

Why am I not qualified for this round.

Can you please check again? The qualifying criteria for Round 1b has now been removed, so you should be able to make a submission now.

View post 0

Is the data not available anymore?

Hi, the data is available. Please sign up for the challenge and visit the resource section to download it.

View post 0

The Generative Interior Design Challenge: How Did the Challenge Winners Transform Empty Rooms with AI

The Generative Interior Design Challenge is the latest interdisciplinary competition hosted on AIcrowd that uses Generative AI to enhance Interior Design. Participants were tasked with using AI to transform empty rooms into furnished spaces based on text descriptions. The goal was to develop a model capable of understanding a text prompt and interpreting an image of an empty room to generate a new image that includes furnishings and design prompts.

The Objective

This challenge required participants to blend their technical skills and creativity to produce aesthetically pleasing and functional designs. The goal was to change how designers, architects, and homeowners envision and plan interior spaces, making the process more efficient and accessible.

Participants used LLMs and Stable Diffusion Models to create visually appealing interiors based on text prompts and a reference image of an empty room to create visually appealing interiors based on text prompts. Submissions were evaluated on room layout, realism, functionality, and consistency with the text prompt. Generated images were also manually assessed by a panel of trained experts to ensure that the designs adhered to the original room’s structure and met standards of realism and practicality.

The amalgamation of art and technology in this challenge provided a chance to explore the impact of generative networks in advancing the interior design field and opening new avenues for client-designer interactions.

MEET THE WINNERS

1st Place: Team decem

• Prize: $7,000
• Members: Yi Zhang, Chenyue Wang, Xiaoya Liu

Background: Yi Zhang graduated with a bachelor’s degree and currently works at Sichuan Timesnew Technology Co., Ltd. Along with Chenyue Wang, and Xiaoya Liu, students of Peking University, the team blends experience and enthusiasm. They joined this challenge to improve their understanding and practical skills in diffusion and ControlNet.

Approach: The team began by learning and understanding the concepts of diffusion and ControlNet. Applying their theoretical knowledge to real-world scenarios through hands-on projects, they embraced setbacks and saw them as opportunities for growth. They prepared for the challenge with rigour and practice, ultimately topping the leaderboard.

2nd Place: Team StableDesign

• Prize: $5,000
• Members: Mykola Lavreniuk, Bartosz Ludwiczuk

Background: Mykola, a PhD in Applied Mathematics and Senior ML/CV Engineer at the Space Research Institute, holds expertise in visual analysis, detection, segmentation, and monocular depth estimation. He has developed state-of-the-art models and has experience in multimodal techniques, generative AI, and satellite image analysis. His teammate, Bartosz Ludwiczuk, is the Computer Vision Tech Lead at SoftServe. He specialises in representation learning techniques in the image domain, with experience in face recognition, image retrieval, and gait recognition. Both Mykola and Bartosz are regular participants in Machine Learning competitions, consistently achieving top ranks in AIcrowd competitions.

Approach: Team StableDesign started by developing a dataset, sourcing approximately 300,000 images from Airbnb and processing them to extract features for interior and outdoor scenes. They filtered out indoor images, generated segmentation masks and depth maps for each, and created empty room images using an inpainting pipeline. They used the llava1.5 model to generate image descriptions and trained two custom Control Nets based on depth and segmentation-conditioned images. During inference, they used an inpainting pipeline based on the Realistic_Vision v5.1 model, along with the two custom Control Nets and the IP Adapter. Their full code is available here, and their final best model can be accessed here.

3rd Place: Team XenonStack

• Prize: $3,000
• Members: Akash Pandey, Navdeep Singh Gill, Dr Jagreet Kaur

Background: Akash is an AI Solution Architect at Xenonstack, specialising in providing Generative AI solutions and overseeing AI operations. He is passionate about advancing technology through experimental projects. Xenonstack is a Technology Consulting and Solutions company focusing on platform engineering, data intelligence, and generative and edge AI. The team is led by Navdeep Singh Gill and Dr Jagreet Kaur, who have over 20 years of experience in the field and are recognised as LinkedIn’s Top AI and Data Voices.

Approach: Team XenonStack began by analysing the problem statement and baseline solution and identifying enhancement opportunities. They implemented a pipeline with a base model, exploring various prompt strategies. Their top improvements included integrating dual ControlNet models, advanced segmentation, masking models, and inpainting models to refine detail and realism. Each modification was tested and improved iteratively. Despite challenges, they continuously adapted by enhancing their strategies to meet the design criteria better, leading to their eventual victory.

Thank you to all participants, and congratulations to our winners! Their innovative approaches and hard work helped redefine the impact of AI on interior design.

View post 1

Why am I not eligible to participate?

Have you clicked on the participate button and accepted the challenge rules?

View post 0