𝐌𝐨𝐛𝐢𝐋𝐥𝐚𝐦𝐚: 𝐚 𝟎.𝟓 𝐛𝐢𝐥𝐥𝐢𝐨𝐧 𝐩𝐚𝐫𝐚𝐦𝐞𝐭𝐞𝐫 Small Language Model (SLM) 👍Uses careful param sharing scheme 👍LLMs: b̶i̶g̶g̶e̶r̶ smaller the better! 👍 Suitable for on-device processing, energy efficiency & low memory usage for resource-constrained devices

#MobiLlama is developed at MBZUAI and I am delighted to share my contribution to this project.

🚀 Introducing All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages (ALM-Bench): A culturally diverse multilingual and multimodal VQA benchmark covering 100 languages with 22.7K QAs. 🔗 Project: mbzuai-oryx.github.io/ALM-Bench/ 📖 Paper: arxiv.org/abs/2411.16508 1/2

🙏 Thanks to the entire team! Dinura Dissanayake, Hasindri Watawana, Noor Ahsan, Nevasini, Omkar Thawakar, Aman Chadha, Hisham Cholakkal, Rao Anwer, Michael Felsberg, Jorma Laaksonen, Thamar Solorio, Monojit Choudhury, Ivan Laptev, Mubarak Shah, Salman Khan and Fahad Khan.

Will be having some interesting discussions this Friday. The registration link is there in the same thread.

We have multiple challenge tracks, and expert sessions in VidLLM. More details will be shared soon.

🚀 Introducing SB-Bench, a comprehensive framework for evaluating stereotype biases in LMMs. With over 7.5K real-world images across 9 domains, it rigorously tests LMMs’ fairness in ambiguous scenarios. ⚖️ 🔗 Website: lnkd.in/dad-9sZ8 📖 Paper: lnkd.in/dRHYpWCn

📊 We hope SB-bench serves as a critical tool in building fairer, more responsible AI systems. We welcome the community to explore, critique, and expand on this work! 🙏 Thanks to the entire core team! Vishal Narnaware, Rohit Gupta, Sirnam Swetha, and Mubarak Shah.

🚨 Submission deadline for papers to 1st Video LLMs Workshop at #CVPR2025 has been extended by 5 days to April 20 ! 📌 Non-archival | 📷 Both Novel and published work welcome 📷 🎯CFP: crcv.ucf.edu/cvpr2025-vidll… Submit at: openreview.net/group?id=thecv…

Participate in the Multilingual Video Reasoning Challenge in CVPR2025 VidLLMs CVPR2025 Workshop. 🥇

Challenge yourself to beat the best results in our #CVPR2026 VidLLMs CVPR2025 Workshop at Nashville!

With up to $3,000 in prizes from #Amazon and #Apple, brush up on your VidLMM skills in our multilingual challenge. Demo code also released.

Travel grants sponsored by Amazon and Apple are available for participants at CVPR-2025 VidLLMs workshop. Fill out this form if you are an attendee looking for support. Limited grants of $1,000 per person are available. #CVPR #CVPR2025 forms.gle/5kHSgnfo9hFrUU…

🚀 Heading to #CVPR2025 in Nashville? Don’t miss the VideoLLMs Workshop on June 11 (Grand A1)! • 🔑 6 keynotes • 🗣️ Panel “VideoLLMs vs Expert Models” • 🏆 $6 K challenge-prize reveal • 📑 Paper talks and Poster session See you there! #AI #ComputerVision #GenerativeAI

Remarks from our chair Prof Mubarak Shah kicking off the VideoLLMs workshop #CVPR2026 #CVPR #CVPR2025 #ComputerVision #AI

[Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact] To get us to AGI, new cognitive foundations are needed. This paper argues that token prediction alone (of those top LLMs) is not

Excited to share some interesting insights on Multicultural and Multilingual Model.

🚨 CFP: VidLLMs @ CVPR 2026 Workshop 🚨 Non-archival papers welcome: Video LLMs, unified multimodal, VLA, world models, data, eval/benchmarks, apps, safety. Deadline Apr 3, 2026. Submit: openreview.net/group?id=thecv… #CVPR2026 #VidLLMs