Yunze Man
@yunzeman
PhD student in CS at UIUC @UofIllinois. Research intern @Nvidia, ex-intern @Adobe. Previously at @CMU_Robotics. Research interests in VLM and embodied AI.
Attending #CVPR2025 6/11 to 6/15! DM me if you want to chat about 𝘃𝗶𝘀𝘂𝗮𝗹 𝗿𝗲𝗮𝘀𝗼𝗻𝗶𝗻𝗴, 𝘀𝗽𝗮𝘁𝗶𝗮𝗹 𝗶𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲, 𝗲𝗺𝗯𝗼𝗱𝗶𝗲𝗱 𝗮𝗴𝗲𝗻𝘁, or 𝘃𝗹𝗺/𝘃𝗹𝗮. 𝗔𝗿𝗴𝘂𝘀: visual-cot reasoning, Sat 10:30-12:30 (#346) yunzeman.github.io/argus 𝗢𝗥𝗚:…
How to generate billion-scale manipulation demonstrations easily? Let us leverage generative models! 🤖✨ We introduce Dex1B, a framework that generates 1 BILLION diverse dexterous hand demonstrations for both grasping 🖐️and articulation 💻 tasks using a simple C-VAE model.
Fast-dLLM Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
This is wild. MiniMax-M1 just dropped. This AI agent = Manus + Deep Research + Computer Use + Lovable in one. 1M token memory, open weights🤯 10 wild examples + prompts & demo: 1. Netflix clone with playable trailers
𝙍𝙖𝙣𝙙𝙤𝙢 𝙊𝙧𝙙𝙚𝙧 𝘼𝙪𝙩𝙤𝙧𝙚𝙜𝙧𝙚𝙨𝙨𝙞𝙫𝙚 𝙂𝙚𝙣𝙚𝙧𝙖𝙩𝙞𝙤𝙣 (𝙍𝙖𝙣𝙙𝘼𝙍) unlocks a ton of zero-shot generation capabilities. Remember to attend our Oral session!
What an ominous way to name a benchmark. This is indeed extremely hard but I wonder whether this is the hardest form of short-form textual and image reasoning QA?
We’re releasing Humanity’s Last Exam, a dataset with 3,000 questions developed with hundreds of subject matter experts to capture the human frontier of knowledge and reasoning. State-of-the-art AIs get <10% accuracy and are highly overconfident. @ai_risk @scaleai
Video understanding is the next frontier, but not all videos are alike. Models now reason over youtube clips and feature films, but what about the everyday spaces we—and our future AI assistants—navigate and experience? Introducing Thinking in Space, our latest study exploring…
What am I watching? 🤯 Way more potential unlocked!
Unitree B2-W Talent Awakening! 🥳 One year after mass production kicked off, Unitree’s B2-W Industrial Wheel has been upgraded with more exciting capabilities. Please always use robots safely and friendly. #Unitree #Quadruped #Robotdog #Parkour #EmbodiedAI #IndustrialRobot…
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡
Check out our new work on 🎲 randomized autoregressive image generation (RandAR)! Intriguing findings about positional embedding, generation orders, parallel decoding, and more. arxiv.org/abs/2412.01827
Unitree B2-W Talent Awakening! 🥳 One year after mass production kicked off, Unitree’s B2-W Industrial Wheel has been upgraded with more exciting capabilities. Please always use robots safely and friendly. #Unitree #Quadruped #Robotdog #Parkour #EmbodiedAI #IndustrialRobot…