Yejin Kim (@_yejinkim) 's Twitter Profile
Yejin Kim

@_yejinkim

A roboticist, a painter and a dog mom. insta: instagram.com/yejinkim.art

ID: 1058345115293347842

linkhttp://yejin-kim.com calendar_today02-11-2018 13:08:33

495 Tweet

90 Followers

376 Following

Sergey Levine (@svlevine) 's Twitter Profile Photo

A new VLA for navigation that can take in goal images, positions, and language, and exhibits some pretty neat emergent language following!

Ted Xiao (@xiao_ted) 's Twitter Profile Photo

📢The next milestone for intelligent general-purpose robots has arrived! Announcing Gemini Robotics 1.5, our flagship system which brings breakthroughs from frontier models to the physical world with two new SOTA generalists: the GR 1.5 VLA and GR 1.5 embodied reasoning model 🧵

📢The next milestone for intelligent general-purpose robots has arrived!

Announcing Gemini Robotics 1.5, our flagship system which brings breakthroughs from frontier models to the physical world with two new SOTA generalists: the GR 1.5 VLA and GR 1.5 embodied reasoning model 🧵
Songming Liu (@songming_liu) 's Twitter Profile Photo

😠💢😵‍💫Tired of endless data collection & fine-tuning every time you try out VLA? Meet RDT2, the first foundation model that zero-shot deploys on any robot arms with unseen scenes, objects & instructions. No collection. No tuning. Just plug and play🚀 Witness a clear sign of

Kevin Lin (@linkevin0) 's Twitter Profile Photo

Tired of collecting robot demos? 🚀 Introducing CP-Gen: geometry-aware data generation for robot learning. From a single demo, CP-Gen generates thousands of new demonstrations to train visuomotor policies that transfer zero-shot sim-to-real across novel geometries and poses.

Sergey Levine (@svlevine) 's Twitter Profile Photo

Come check out Pranav's presentation on RoboArena, a framework for evaluating generalist robot policies (like VLAs) with a distributed network of evaluators.

Apurva Badithela (@apurvabadithela) 's Twitter Profile Photo

Robotic manipulation has seen tremendous progress in recent years but rigorous evaluation of robot policies remains a challenge! We present our work: "Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators"! 🧵

Chelsea Finn (@chelseabfinn) 's Twitter Profile Photo

Most VLAs have no memory. MemER is a scalable method for giving VLAs long-term visual memory. Key ideas: - relevant info is in a small # of frames: store just a few key frames - manage & use memory at high level of abstraction, with a HL policy Paper: jen-pan.github.io/memer/

Yuke Zhu (@yukez) 's Twitter Profile Photo

Had a blast visiting CMU Robotics Institute and gave a talk at the RI Seminar today, where I briefly mentioned our new work, PLD, on self-improving VLAs. It achieved 99.2% on LIBERO and a one-hour continuous execution of GPU assembly with a 100% success rate. Check this out!

Jie Wang (@jiewang_zjui) 's Twitter Profile Photo

In my opinion, VLAs research is extremely empirical compared to many other directions. Simulations like LIBERO are no longer statistically meaningful to VLAs, as we can overfit to ~99% easily now. Urgent priorities: 1) Create new sim benchmarks 2) Show real-world experiments

Jeffrey Emanuel (@doodlestein) 's Twitter Profile Photo

Just read through the new LeJEPA paper by Yann LeCun and Randall Balestriero. I’ve been curious to know what Yann’s been working on lately, especially considering all his criticisms of LLMs (which I disagree with, as I think LLMs will keep improving and will take us to ASI fairly

Just read through the new LeJEPA paper by Yann LeCun and Randall Balestriero. I’ve been curious to know what Yann’s been working on lately, especially considering all his criticisms of LLMs (which I disagree with, as I think LLMs will keep improving and will take us to ASI fairly
Tony Z. Zhao (@tonyzzhao) 's Twitter Profile Photo

Today, we present a step-change in robotic AI Sunday. Introducing ACT-1: A frontier robot foundation model trained on zero robot data. - Ultra long-horizon tasks - Zero-shot generalization - Advanced dexterity 🧵->

Pieter Abbeel (@pabbeel) 's Twitter Profile Photo

Open-source: complete codebase covering multiple simulation backends, training, retargeting, and real-world inference. Infra built for humanoid, but also readily modified for quadruped (also included). Lots of infra gems/conveniences we rely on consistently. Hopefully equally

Kyle🤖🚀🦭 (@kylemorgenstein) 's Twitter Profile Photo

I have and will continue beating this drum- sim is the way. sim scales so much better than real. by the time we exhaust sim capabilities today, sim will have evolved to handle all the parts that are currently hard (contacts, soft bodies, etc.)

Ruohan Zhang (@ruohanzhang76) 's Twitter Profile Photo

1/N 🎨🤖Given only a static image of an oil painting by an expert artist, can a robot infer the corresponding control actions, such as trajectory, orientation, and applied force, to accurately reproduce the painting? 🖌️Introducing IMPASTO: a robotic oil-painting system that