Location
VN
Badges
Activity
Challenge Categories
Challenges Entered
Completed
Krafton AI
Build an LLM agent for five real-world games
Latest submissions
University of Wollongong
Detecting Energy Flexibility in Buildings
Latest submissions
See All| graded | 300328 | ||
| graded | 300319 | ||
| graded | 300318 |
Meta
Improve RAG with Real-World Benchmarks
Latest submissions
See All| graded | 266335 | ||
| graded | 266193 | ||
| graded | 266168 |
Seerave Foundation
A benchmark for image-based food recognition
Latest submissions
Institute of Global Health
LifeCLEF
Classify images of snake species from around the world
Latest submissions
See All| graded | 10024 | ||
| graded | 6995 | ||
| failed | 6992 |
AIcrowd
5 Problems 15 Days. Can you solve it all?
Latest submissions
See All| graded | 74031 | ||
| graded | 73938 | ||
| graded | 73831 |
Max Planck Institute for Intelligent Systems
Disentanglement: from simulation to real-world
Latest submissions
Unity Technologies
A new benchmark for Artificial Intelligence (AI) research in Reinforcement Learning
Latest submissions
Latest submissions
See All| graded | 73807 | ||
| graded | 73198 | ||
| graded | 72790 |
Testing RAG Systems with Limited Web Pages
Latest submissions
See All| graded | 266167 | ||
| failed | 266122 | ||
| failed | 265909 |
Evaluating RAG Systems With Mock KGs and APIs
Latest submissions
See All| graded | 266168 | ||
| failed | 266069 | ||
| graded | 266068 |
Enhance RAG systems With Multiple Web Sources & Mock API
Latest submissions
See All| graded | 266335 | ||
| graded | 266193 | ||
| failed | 266166 |
Sony Group Corporation
Create Videos with Spatially Aligned Stereo Audio
Latest submissions
| Participant | Rating |
|---|---|
alchemi01
|
235 |
yusuf_dogu
|
0 |
| Participant | Rating |
|---|---|
|
alchemi01
|
235 |
Orak Game Agent Challenge 2025 Forum
Flextrack Challenge 2025
🏆 Final Results & Next Steps
5 months agoThank you for the update. I’m curious to see which models are causal.
📹 Townhall Recording & Q&A with Challenge Organisers | How to use digital twin data to predict demand response capacity
6 months agoI think ‘back-cast’ refers to the fact that these datasets were collected in the past. So now we cast predictions for previous events.
In the test dataset v0.2, there are Site D, Site E, and Site F. My take is that these sites are in the private test set, not only the site F.
Issue related to submission
6 months agoHi Tuan, you can check your submissions here: AIcrowd | Flextrack Challenge 2025 | Submissions
Meta Comprehensive RAG Benchmark: KDD Cup 2-9d1937
Did somebody try deploy three llama3-8b on four T4?
Almost 2 years agoThere are 4 T4 cards. But I see that the total GPU memory is < 60GB.
Did somebody try deploy three llama3-8b on four T4?
Almost 2 years agoHow large is each llama3-8b model? If it is 16GB each, it’s possible.
Whether the task test phase can link to the Internet
Almost 2 years agoThere is the Internet when building the Docker image. But no internet when they run submissions.
The CRAG-Mock-API should move to the Meta Comphrehensive RAG Benchmark starter kit project?
Almost 2 years agoThe docker file can be customized. It is the environment to run the code in gitlab.
The CRAG-Mock-API should move to the Meta Comphrehensive RAG Benchmark starter kit project?
Almost 2 years agoLook at crag_mock_api/apiwrapper/pycragapi.py to see how to use its functions.
The openai interface cannot be used during evaluation? Why?
Almost 2 years agoYou need to pass API key. There is also no internet in the submission.
Added tag with "submission-v" prefix but no evaluation issue created
Almost 2 years agoGot this issue again.
When will the submission limit be reset?
Almost 2 years agoIn the Submission tab of the main challenge page, we can see how many submissions are left this week.
Meta KDD Cup 24 - CRAG - Retrieval Summarization
Failed to communicate with the grader
Almost 2 years agoI had the same issue. Is it fixed now? @aicrowd_team
Couldn't instantiate the backend tokenizer
Almost 2 years agoHave you tried installing the transformer package?
About Test Set Leakage in Round 1
Almost 2 years ago@aicrowd_team I suggest that the Round 2 test set should be truly private and not share any similarity or distribution with the data in Round 1.
Why am I not eligible to participate?
Almost 2 years agoI have tried again and still failed with the same reason
💬 Feedback & Suggestions
4 months agoI get this error when trying to run
run.pylocally