🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

New Paper Alert: Multimodal Inconsistency Reasoning (MMIR)! ✨ Ever visited a webpage where the text says “IKEA desk” yet images and descriptions elsewhere show a totally different brand? Or read a slide that shows “50% growth” in the text but the accompanying chart looks flat?

𝐁𝐞𝐚𝐭𝐢𝐧𝐠 𝐎𝐩𝐞𝐧𝐀𝐈 𝐢𝐬 𝐧𝐨𝐭 𝐚𝐬 𝐡𝐚𝐫𝐝 𝐚𝐬 𝐲𝐨𝐮 𝐭𝐡𝐢𝐧𝐤. If you don't believe you can compete, you've already lost. Winning starts with mindset. 🚀Introducing 𝑨𝒈𝒆𝒏𝒕 𝑺2, 𝐭𝐡𝐞 𝐰𝐨𝐫𝐥𝐝'𝐬 𝐛𝐞𝐬𝐭 𝐜𝐨𝐦𝐩𝐮𝐭𝐞𝐫-𝐮𝐬𝐞 𝐚𝐠𝐞𝐧𝐭, and the second

Could not attend #ICLR2025 🥲. But Chengzhi Liu will present our Multimodal Situational Safety paper on April 25, 3:00-5:30 pm in Hall 3 + Hall 2B #538. Welcome to check it out!

Before o3 impressed everyone with 🔥visual reasoning🔥, we already had faith in and were exploring models that can think with images. 🚀 Here’s our shot, GRIT: Grounded Reasoning with Images & Texts that trains MLLMs to think while performing visual grounding. It is done via RL

Still remember people commented on the close DDLS between ARR May and Neurips. Just check the ARR Oct ddl is Oct 6th🤔

🧠 More Thinking, Less Seeing? 👀 Exploring the Balance Between Reasoning and Hallucination in Multimodal Reasoning Models! Currently many multimodal reasoning models while striving for enhanced reasoning capabilities often neglect the issue of visual hallucinations. While

🚨 PhyWorldBench, New Paper Alert! 🚨 Video‑generation models are jaw‑dropping—they conjure gorgeous scenes in seconds. But can they truly simulate the real world, respecting (or intentionally bending) the laws of physics? Introducing PhyWorldBench, the large‑scale benchmark I