Yisong Yue
@yisongyue
Machine Learning @Caltech (@YueLabCaltech). AI for invention at @AsariAILabs.
Inspired time @LaudeInstitute, huge congrats to @andykonwinski on the launch! Humbled to be asked to speak on the dos of impact research in front of such 🤩 researchers!! P.S. 👀 the where's waldo moment of my favorite +1 (@yisongyue) being (I hope 😅) a proud academic dad 🪞📸
Today, I’m launching a deeply personal project. I’m betting $100M that we can help computer scientists create more upside impact for humanity. Built for and by researchers, including @JeffDean & @jpineau1 on the board, @LaudeInstitute catalyzes research with real-world impact.
Today, I’m launching a deeply personal project. I’m betting $100M that we can help computer scientists create more upside impact for humanity. Built for and by researchers, including @JeffDean & @jpineau1 on the board, @LaudeInstitute catalyzes research with real-world impact.
I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery! We’re looking for strong Research Scientists and Research Engineers to help us push the frontier of autonomously discovering novel artifacts such as new knowledge, capabilities, or algorithms, in an…
Congratulations to Brian Conrad for being awarded the Barry Prize by the American Academy of Sciences (@americanacad), in part for his efforts in K-12 math education. youtu.be/2R6UBcH1Yg0?si…
ICML’s Statement about subversive hidden LLM prompts We live in a weird timeline…
There's something weirdly gross about people spamming out email campaigns to try get elected to the ICML board (or perhaps it's just how the emails are written/framed).
Beautiful story from @QuantaMagazine quantamagazine.org/ai-comes-up-wi… Honored to be featured together with @MarioKrenn6240 @KyleCranmer
You’ve generated 10k concepts with your favorite XAI method -- now what? Many concepts you’ve found are fairly obvious and uninteresting. What if you could 𝑠𝑢𝑏𝑡𝑟𝑎𝑐𝑡 obvious concepts away and focus on the more complex ones? We tackle this in our latest preprint!
Sharing our first research paper today! Product announcements to come over the next few months. Join us.
We're excited to share our latest research, focusing on better understanding and navigating dynamic real-world environments for autonomous systems. We introduce STRIDE, a new spatio-temporal road image dataset, & TARDIS, a world model that leverages it. tera-ai.com/blog/tardis
We're excited to share our latest research, focusing on better understanding and navigating dynamic real-world environments for autonomous systems. We introduce STRIDE, a new spatio-temporal road image dataset, & TARDIS, a world model that leverages it. tera-ai.com/blog/tardis
Collaboration is important for impactful work, but it is not enough! Impact comes from the collaboration between two types of people. The generators and discriminators (pun very much intended 😉). The generators dream big, swing for the fences, and don’t listen when they are…
Incredibly well deserved, @yisongyue is simply the best! Also huge shout out to @Hongkai_Zheng & Raul Astudillo who also wrote wonderful letters and the rest of the @YueLabCaltech + friends who endorsed 🦫🧡
Honored to receive the mentoring award from the Grad Student Advisory Board at @Caltech EAS. Thanks to the students who nominated me, especially @SaberaTalukder!
Honored to receive the mentoring award from the Grad Student Advisory Board at @Caltech EAS. Thanks to the students who nominated me, especially @SaberaTalukder!

First time receiving a figurine of myself! Thanks so much @ccx_cheng2!

I had to cancel my trip to @CVPR because I caught the stupid flu 🙃 So sad to miss everyone! But if you are in Nashville go check out Damiano's project tomorrow on improving 3D spatial reasoning from a single image with the power of LLMs 🌟 #CVPR2025 @marsilidamiano
I’ll be presenting VADAR at #CVPR2025 on Saturday, June 14 from 17:00-19:00 at Poster 347! Come stop by & talk about 3D visual reasoning for LLMs and visual programming!! 👋👋
I’ll be presenting VADAR at #CVPR2025 on Saturday, June 14 from 17:00-19:00 at Poster 347! Come stop by & talk about 3D visual reasoning for LLMs and visual programming!! 👋👋
1/5 LLMs are notoriously not great at 3D perception … but what if there were an alternative path to scaling 3D VQA? 👀 Introducing VADAR: a new program synthesis approach for 3D spatial reasoning! glab-caltech.github.io/vadar/
VideoPrism is now available at: github.com/google-deepmin… :)
Introducing VideoPrism, a single model for general-purpose video understanding that can handle a wide range of tasks, including classification, localization, retrieval, captioning and question answering. Learn how it works at goo.gle/49ltEXW
📣Introducing our latest work: Yet Another Quantization Algorithm! YAQA directly minimizes the KL divergence to the original model during rounding, cutting it by >30% over prior PTQ methods and giving an even closer model than Google’s QAT on Gemma! 🤯 arxiv.org/abs/2505.22988👇
It's Friday afternoon, and we’re packing for L4DC 2025 @l4dc_conf next week 😎 Excited to share MS-HGNN — our take on bringing morphological symmetry into GNNs for legged robot dynamics. 🧵 (1/4) We bake both kinematics and morphological symmetry into the model → -…
AI increasingly excels at formal math, opening up a path to large-scale automated formal verification. However, most AI-for-math work focuses on pure math rather than verification. CLEVER, a sort of HumanEval for Lean, fills this gap. The SOTA here is weak, so there’s much to do!
1/🧵Excited to share CLEVER — a new benchmark for end-to-end verified code generation in Lean. Can we go from natural language to a formally verified Lean program? CLEVER puts this to the test. 📄 arxiv.org/abs/2505.13938 💻 github.com/trishullab/cle…