I am starting a new company:

🎉🎉 Excited to announce our workshop on "Emergent Visual Abilities and Limits of Foundation Models" at #ECCV2024! 📢📢Submit papers and Join us at ECCV for discussions! Pls check our amazing speakers and organizers! sites.google.com/view/eval-fomo…

🤔Are your open-source LLMs really safe? 🚨It may be injected with misinformation or bias! Our new paper "𝐂𝐚𝐧 𝐄𝐝𝐢𝐭𝐢𝐧𝐠 𝐋𝐋𝐌𝐬 𝐈𝐧𝐣𝐞𝐜𝐭 𝐇𝐚𝐫𝐦?" (Project website: llm-editing.github.io ) sheds light on the emerging challenges of LLMs, especially the

These are generated images. ❓ Can you tell if they are generated by OpenAI's DALL-E 3? We formulate this question as a research problem and provide the first solution. Please check our paper arxiv.org/abs/2404.02697, accepted to ECCV2024.

I’m attending #ECCV ! 🔥 present 6 papers on #AI_Safety_and_Privacy. 🔥 host a workshop titled “Emergent Visual Abilities and Limits of Foundation Models (#EVAL_FoMo)”. 🔥 a workshop talk “Understanding Complex Images with Emergent Abilities of MLLMs”. Welcome to joining us!

🚀🕵️ o1 Excels at Reasoning, But Needs Our Latest Research for Multimodal Challenges! – Our paper ( accepted at EMNLP 2024 Findings) explores visual question decomposition in Multimodal LLMs (MLLMs). Here’s a summary of what we did and why it matters. A thread 🧵:

We have an opening for a postdoctoral position on Multimodal LLMs, supported by the University of Oxford and Microsoft. If you’re interested, we encourage you to apply and join our team! tinyurl.com/2tckvr9d Deadline: 18th October.

Excited to share our🔥New #NeurIPS2024 Paper🔥: 𝐂𝐚𝐧 𝐋𝐚𝐫𝐠𝐞 𝐋𝐚𝐧𝐠𝐮𝐚𝐠𝐞 𝐌𝐨𝐝𝐞𝐥 𝐀𝐠𝐞𝐧𝐭𝐬 𝐒𝐢𝐦𝐮𝐥𝐚𝐭𝐞 𝐇𝐮𝐦𝐚𝐧 𝐓𝐫𝐮𝐬𝐭 𝐁𝐞𝐡𝐚𝐯𝐢𝐨𝐫? The project website (paper, code, demos): agent-trust.camel-ai.org The slides: tinyurl.com/mryyusmm 🌟TLDR: We

Call for interns in Google! Are you interested in building Multi-modal and Reliable Agents with Gemini? I am looking for talented interns and student researchers to join our team at Google. If interested, please fill out this form forms.gle/eHgv69yD9n463g… or PM me.