📢 Shared Task on Arabic Sentence Segmentation @ the 4th Arabic NLP Conference (araseg.aramlab.ai/) 📢 The shared task focuses on segmenting Arabic documents into coherent sentences. Given an Arabic document as input, participating systems must identify sentence boundaries throughout the text. The task is formulated as a binary token classification problem, where models predict whether a sentence boundary follows each token. Participating teams are welcome to take part in any number of tasks/tracks, and those who take part in the official test phase on CodaBench will present their work at 4th Arabic NLP Conference @_ArabicNLP, co-located with EMNLP 2026 @emnlpmeeting, as well as have a publication included in the official proceedings. 🏆 Awards will be given to top-performing systems 🏆 Organizers: @moelkholy1304, @khalid_elmadani, @NYHabash and @balhafni #ArabicNLP #EMNLP2026

AI4Math @ ICML 2026 Challenge is now LIVE! We’re excited to announce that the AI for Math Workshop (ICML 2026) has officially launched its challenge track! Key Dates - Challenge Open: May 1, 2026 - Paper Submission Deadline: May 25, 2026 - Challenge Deadline: June 15, 2026 Prizes 🥇$1,000 🥈 $600 🥉 $400 Challenge Topics - Semantic Alignment in Autoformalization - Formal Theorem Proving - Visual Physics Reasoning - Autoformalization in Lean 4 🔗 Website: ai4math2026.github.io/ 📌 Call for Papers: openreview.net/group?id=ICML… 🙋 Challenge Submission: ai4math2026.github.io/#chall… 👉 Become a Reviewer: forms.gle/8hfysRAKcSBmSazF9 🎯 Contact: ai4mathicml@gmail.com If you find this initiative interesting, we would greatly appreciate it if you could share this post or forward it to relevant colleagues and communities. #ICML2026 #AI4Math #workshop #mathai #ai4math #theoremproving #lean #aiforphysics #ai4physics #llm #codabench #icml #iclr #neurips

🚀 Our DDFF 12-Scene Depth From Focus Competition has officially migrated to Codabench! Join the challenge, push the boundaries of depth estimation research, and compete with the best. 🔗 codabench.org/competitions/1… @lealtaixe #codalab #codabench #ddff12scene #depthfromfocus

Arabic below IndabaX Sudan 2025 Hackathon Track 2 – Problem Solving Challenge 🔥 Powered by CodaBench This track is for participants who enjoy real technical challenges and want to work with real datasets to solve practical problems within a limited time.

学会コンペのプラットフォームといえばKaggleかCodabenchあたりが主力だと思いますが，Hugging Face Competitionsは主催者側の自由度が高くて使いやすいのでもっと広まってほしいですね！

📢 AraHealthQA 2025 - Track 1 (MentalQA) Prizes! 🏆 @_ArabicNLP Submit your system description paper for a chance to win: 🥇 1000 SAR 🥈 600 SAR 🥉 300 SAR CodaBench: codabench.org/competitions/8… Dataset: github.com/hasanhuz/MentalQA #NLP #ArabicNLP #LLM #Health #AI

🏆 We have the winners of the Synerise @ACMRecSys Challenge 2025! 🏆 After months of intense competition, innovation, and thousands of submissions, the top teams have emerged. Check out the #Final and #Academic #Leaderboards to see who made it to the top! 🧨 ➡️ Results are available via the link in the comments ➡️ Codabench link in the comments 🎉 Congratulations to all winners and participants – you’ve made this challenge unforgettable! 🚀 Authors of the challenge: Łukasz Sienkiewicz, Gergely Stomfai, Maria Janicka Jacek Dąbrowski Synerise. Dietmar Jannach, Marco Polignano, Claudio Pomo, Abhishek Srivastava Francesco Barile #Synerise #RecSysChallenge2025 #RecSys #AI #BehavioralModeling #UniversalBehavioralProfiles #SyneriseRecSysChallenge2025 #RecSys2025 #RecSys25

#NLProc Welcome to MAHED 2025 shared task at ArabicNLP 2025! MAHED 2025 - Multimodal Detection of Hope and Hate Emotions in Arabic Content as a shared task for ArabicNLP 2025. This task aims to address the critical issue of detecting hope speech, hate speech and emotional expression in Arabic content across both textual and multimodal formats. We have proposed three tasks: - Text-based Hate and Hope Speech Classification - Emotion, Offensive, and Hate Detection (Multitask) - Multimodal Hateful Meme Detection Website: marsadlab.github.io/mahed202… Data/Code: github.com/marsadlab/MAHED20… Registration: Task 1: codabench.org/competitions/9… Task 2: codabench.org/competitions/9… Task 3: codabench.org/competitions/9… Important Dates June 10, 2025: Release of training, dev data and evaluation scripts July 20, 2025: Final registration deadline and test set release July 25, 2025: Test submission deadline via CodaBench July 30, 2025: Final results released to participants August 15, 2025: System description papers due November 5-9, 2025: ArabicNLP 2025 Conference in Suzhou, China W/ @wzaghouani, Rafiul Biswas, Mabrouka Bessghaier, Shimaa Ibrahim, @gmikros Hasnat

The paper submission deadline is within 1 week: June 21st, 2025, AoE The challenge deadline is in 2 weeks: July 1st, 2025, AoE 📢Call for Papers: sites.google.com/view/ai4mat… 🎯Challenge 1, File-level Automated Proof Engineering (APE) of Formal Math Libraries (APE-Bench I): codabench.org/competitions/8… 🎯Challenge 2, Physics Reasoning with Diagrams and Expressions (SeePhys): codabench.org/competitions/7… #icml2025 #aiformath #ai4math #mathai #theoremproving #lean #aiforphysics #ai4physics #llm #codabench #icml #iclr #neurips

🚀 Thrilled to share that APE-Bench I has just been selected as Track 1 of the ICML 2025 AI4Math Workshop Challenge—the first competition devoted to automated proof engineering (APE) at scale. Formal mathematics is racing past the limits of manual refactoring, and APE-Bench I tackles that scaling crisis head-on. Instead of asking models to solve isolated theorems, we evaluate how well they engineer Lean codebases: editing, debugging, refactoring and extending real Mathlib4 files while keeping every proof sound. The benchmark distils thousands of authentic Mathlib4 commits into instruction-guided tasks, stratified by difficulty and verified with a hybrid syntax-semantics pipeline. Its four design pillars—realism, stratification, scalable evaluation, and continual evolvability—ensure that scores reflect true progress as the library grows. For ICML 2025, competitors will face both a public leaderboard and a hidden test split on Codabench (5 submissions per day, 100 total), culminating in the final evaluation on 7 July 2025. Success here lays the groundwork for the next stages of our roadmap: APE-Bench II (multi-file coordination) and APE-Bench III (fully autonomous project-level agents). Everything is open from day one: source code and evaluation harness on GitHub, the complete dataset on HuggingFace, and a detailed methodology on arXiv. Whether you’re crafting retrieval-augmented LLMs, agent toolchains, or novel semantic judges, you now have a reproducible playground to measure real-world impact. Join us in turning formal mathematics into a collaborative, industrial-scale enterprise—fork the repo, submit your model, and climb the leaderboard. Let’s engineer the future of proofs together! 🔗 GitHub github.com/xinhjBrant/APE-Be… 🔗 Data huggingface.co/APE-Bench 🔗 Paper raw.githubusercontent.com/xi… 🔗 Project Page xinhjbrant.github.io/APE-Ben… 🔗 Challenge Page sites.google.com/view/ai4mat… #icml2025 #lean

עדיין אף אחד לא הצליח לעבור את הבייסלין אז התחרות עוד פתוחה! זוהי תזכורת לכל מי שרוצה לבחון את יכולות הML, תחרות מפא"ת בעיצומה ואפשר עדיין עוד להצטרף ולנסות לזכות בפרס של $15,000. התחרות מתמקדת בסגמנטציה של קהלים על בסיס דפוסי גלישה אנונימיים. בשבוע הבא זה המועד האחרון לבקשות חבילות פייתון. מה המשימה? לבנות מודלים של למידת מכונה שיסווגו משתמשים לסגמנטים שונים על בסיס דפוסי הגלישה שלהם. הבנצ'מארק כבר מרשים עם ציון ROC-AUC של 0.88, אז זו לא תהייה תחרות קלה. למה להשתתף? סך הפרסים: 35,000$ מקום ראשון: 15,000$ מקום שני: 10,000$ מקום שלישי: 7,000$ פרס "יצירתיות" מיוחד: 3,000$ לפתרון היצרתי ביותר. פרטים חשובים: סיום: 6 באפריל 2025. פלטפורמה: Codabench. אתגר מהעולם האמיתי עם נתונים אנונימיים. לינק למידע נוסף: codabench.org/competitions/3…

You have until June 2 to send your submissions on Codabench! #CVPR2025 @KenIsNotARobot @ZiyunClaudeWang @AnthonyBisulco @ChrisKorpela @KostasPenn @vijay_r_kumar @guillermogb @PennEngineers @GRASPlab

אני שמח לעדכן על שת"פ חדש שאנחנו עושים סביב אתגר AI חדש של מפא"ת. הנה הפרטים: אתגר MAFAT מתחיל ב-16 בפברואר, ומתמקד בסגמנטציה של קהלים על בסיס דפוסי גלישה אנונימיים. מה המשימה? לבנות מודלים של למידת מכונה שיסווגו משתמשים לסגמנטים שונים על בסיס דפוסי הגלישה שלהם. הבנצ'מארק כבר מרשים עם ציון ROC-AUC של 0.88, אז זו לא תהייה תחרות קלה. למה להשתתף? סך הפרסים: 35,000$ מקום ראשון: 15,000$ מקום שני: 10,000$ מקום שלישי: 7,000$ פרס "יצירתיות" מיוחד: 3,000$ לפתרון היצרתי ביותר. פרטים חשובים: תחילת התחרות: 16 בפברואר 2025. סיום: 6 באפריל 2025. פלטפורמה: Codabench. אתגר מהעולם האמיתי עם נתונים אנונימיים. לינק למידע נוסף: codabench.org/competitions/3…

🚀 First Submission on CodaBench for SMOT4SB! 🚀 The [SMOT4SB] Public Test has officially begun! 🎉 💡 SO-HOTA: 2.768 (by zhwa2003) 👥 Participants: 30 and growing! Join the challenge and test your tracker! 💪 🔗 codabench.org/competitions/5… #MVA2025 #SMOT4SB #ComputerVision #AI

🚨 Join the Challenge! 🚨 We're excited to announce the NeurIPS competition "Erasing the Invisible: A Stress-Test Challenge for Image Watermarks" running from September 16 to November 5. This is your chance to test your skills in a cutting-edge domain and win a share of our $6000 prize pool! 🔍 Competition Overview: ▶️ Tracks: Black-box Attacks & Beige-box Attacks ▶️ Goal: Remove invisible watermarks while preserving image quality. ▶️ Inspired by: WAVES Benchmark wavesbench.github.io 🔗 Important Dates: ▶️ Sep 16 - Nov 5: Submission phase ▶️ Nov 5: Registration and submission close ▶️ Nov 20: Winning team announcement 🌐 Details and Registration: ▶️ Website: erasinginvisible.github.io ▶️ Hosted on Codabench: ⏩ Beige-Box Track: codabench.org/competitions/3… ⏩Black-Box Track: codabench.org/competitions/3… 💡 Why Participate? ▶️ Validate the robustness of image watermarks under varying conditions. ▶️ Compete in a domain inspired by real-world challenges. ▶️ Collaborate with a global community of researchers and practitioners. 💰 Prize Pool: $6000 (and counting as more sponsors join us!) ▶️ Interested in sponsoring? Contact us at erasinginvisible@googlegroups.com or furongh@umd.edu. 🔨 A Personal Note: Hosting this competition has been a challenging yet rewarding experience. Working with a dedicated organizing team, developers, and legal experts across multiple parties, I've learned a lot. We can't wait to see what you bring to the table! A big shout out to our organizing team @mucongding @TahseenRab74917 @bang_an_ @chenghao_deng @SOURADIPCHAKR18 Anirudh Satheesh @MerhdadS @ywen99 Kyle Sang @Aakriti0503 @xuandongzhao Mo Zhou @anniehartley_ @lileics @yuxiangw_cs @vishalm_patel @FeiziSoheil @tomgoldsteincs @furongh 💐 and our sponsor, center for machine learning at UMD @ml_umd @umiacs @tomgoldsteincs! Don't miss out—register today and start preparing your submissions!

Check out our #NLProc @EmoSemEval2025 shared task. We'll release new datasets in 33 lgges including MSA and Algerian Arabic. CodaBench: codabench.org/competitions/3… Algerian Arabic text snippets come from my translation of Mohammed Dib's trilogy. (To be made public :-) )

We are glad to announce @SemEvalWorkshop shared task 11: Bridging the Gap in Text-Based Emotion Detection. New textual datasets will be provided for 33 lgges (with many low-resource lgges)! Task GitHub: github.com/emotion-analysis-… CodaBench: codabench.org/competitions/3… Tracks👇🏻🧵1/

📢 Announcement for LegalLens Shared Task Participants! 🚀 The test sets are now out and ready for your predictions! Submission deadline extended to Aug 17, 2024, 23:59 AOE. Submit your work through Codabench. System paper deadline is Sept 3, 2024. @NllpWorkshop @emnlpmeeting

We just extended the submission deadline by 24 hours! New deadline is Aug 1st 12:00pm (AoE). All details are also on codabench: codabench.org/competitions/3…

Présentation de codabench, un outil pour réaliser des compétitions scientifique par Magali Richard #JOBIM2024