Meta tags:
Headings (most frequently used words):
haoru, xue, 薛浩儒, social, latest, research, education, experience, awards, honors, teleoperation, as, service, taas,
Text of the page (most frequently used words):
and (24), 2025 (22), for (20), the (20), 2024 (18), with (16), xue (16), haoru (15), robotics (14), prof (12), website (11), #social (11), berkeley (11), learning (11), mpc (11), guanya (11), shi (11), arxiv (11), control (11), media (10), research (9), icra (9), lab (9), model (9), real (9), paper (8), 2026 (8), zhu (8), phd (7), autonomous (7), shankar (7), sastry (7), yuke (7), jim (7), fan (7), robot (7), dynamics (7), whole (7), body (7), humanoid (7), ucb (7), racing (6), nvidia (6), scale (6), wang (6), agile (6), wenli (6), xiao (6), that (6), data (6), best (5), cvpr (5), john (5), dolan (5), cmu (5), code (5), talk (5), training (5), icml (5), level (5), models (5), linxi (5), follow (5), release (5), blog (4), 2023 (4), graph (4), frontier (4), from (4), sim (4), vision (4), language (4), tairan (4), zhengyi (4), luo (4), world (4), viral (4), manipulation (4), student (4), accepted (4), new (4), free (3), 2021 (3), motor (3), indy (3), challenge (3), workshop (3), eecs (3), finalist (3), may (3), researcher (3), francesco (3), borrelli (3), visiting (3), jan (3), gear (3), based (3), policy (3), learn (3), race (3), deployed (3), error (3), regression (3), adaptive (3), pre (3), anycar (3), human (3), systems (3), dial (3), via (3), latent (3), action (3), leverb (3), huang (3), xingye (3), qingwei (3), ben (3), fernando (3), castañeda (3), yuan (3), robots (3), loco (3), tasks (3), doorman (3), generalization (3), cap (3), are (3), thrilled (3), announce (3), taas (3), email (2), youtube (2), instagram (2), linkedin (2), github (2), playground (2), homepage (2), san (2), diego (2), department (2), honors (2), 2022 (2), place (2), 2nd (2), scene (2), representation (2), dec (2), tech (2), aug (2), advisor (2), lecar (2), institute (2), supervisors (2), intern (2), pieter (2), abbeel (2), amazon (2), far (2), large (2), road (2), network (2), extraction (2), times (2), faster (2), optimal (2), online (2), extreme (2), driving (2), like (2), car (2), full (2), video (2), predictive (2), zero (2), shot (2), generalist (2), robotic (2), low (2), learned (2), stronger (2), representations (2), trevor (2), darrell (2), dantong (2), niu (2), diffusion (2), sampling (2), using (2), style (2), torque (2), top (2), locomotion (2), vla (2), peng (2), sonic (2), motion (2), distill (2), recipe (2), self (2), improving (2), find (2), simulation (2), deployment (2), scaling (2), law (2), visual (2), framework (2), door (2), opening (2), than (2), agents (2), these (2), fei (2), skills (2), receipe (2), long (2), horizon (2), program (2), stanford (2), slides (2), presentation (2), interning (2), teleoperation (2), service (2), team (2), was (2), designed, feel, files, wordpress, twitter, google, scholar, vyvyen, love, ece, henry, booker, memorial, award, 2rd, texas, speedway, 3rd, las, vegas, ces, scholarship, recipient, awards, 2019, advisors, jack, silberman, allen, yang, lead, graduate, apr, feb, present, rocky, duan, experience, electrical, eng, 2018, education, graphs, propose, sam, pipeline, aerial, image, comparable, accuracy, sota, achieved, while, being, yihui, wenping, tianwei, yue, cindy, congrui, hetang, segment, anything, use, explore, safely, perform, sim2real, handling, limit, professional, driver, size, edward, built, small, achieves, family, wheeled, embodiments, few, outperforms, specialist, policies, fine, tuning, transformer, ieee, spectrum, dvij, kalaria, tony, tao, anywhere, universal, mobility, autoregressive, leverages, yield, has, spatial, temporal, understandings, arm4r, roei, herzig, ziteng, junyi, zhang, giscard, biamby, yuvan, sharma, auto, regressive, can, achieve, legged, rewards, quadrupedal, guannan, zeji, chaoyi, pan, order, annealing, june, first, introduce, interface, between, enable, expressive, task, specification, interpolatable, execution, vocabulary, koushil, sreenath, bin, tommy, gravdahl, thomas, kragerud, qiayuan, liao, xiaoyu, instruction, oct, general, tracker, supporting, various, modes, umar, iqbal, yan, chang, kautz, simon, yuen, eugene, jeong, edy, lim, lina, song, cyrus, hogg, runyu, ding, david, minor, jiefeng, ang, cao, sirui, chen, chenran, tingwu, supersizing, tracking, natural, iclr, probe, pld, post, letting, discover, recover, their, own, flywheel, jimmy, fengyuan, yuqi, xie, andy, haotian, lin, generation, residual, investigates, right, enjoy, lunch, robust, continuous, changliu, liu, proposes, challenging, such, trained, rgb, purely, teacher, bootstrap, pixel, transfer, evaluates, providing, agentic, harnesses, write, interact, environment, get, feedbacks, improve, skill, libraries, generally, have, superior, capability, vlas, llm, performance, ken, goldberg, jiajun, guanzhi, ethan, kou, karim, refai, justin, max, benchmarking, coding, bridging, high, planning, leads, enabling, vlm, reasoning, want, build, will, fundamentally, change, society, interests, recently, ultimately, one, three, papers, joined, oral, master, thesis, darpa, ansr, safe, adaptation, intelligent, laboratory, sisl, towards, foundational, safety, critical, pathways, foundation, see, earlier, selected, how, win, home, startup, game, answer, here, why, make, sense, lesson, only, system, works, today, tesla, autopilot, time, author, latest, mail, led, multi, million, project, ucsd, across, labs, cars, 160, mph, more, before, previously, working, drive, interned, supervised, interested, foundemental, problems, physical, agi, scalable, priors, reasonings, dexterous, bair, advised, also, work, closely, affiliated, ember, center, 薛浩儒,
Text of the page (random words):
haoru xue phd at berkeley ai research uc berkeley homepage blog haoru xue 薛浩儒 i am a phd student at berkeley ai research bair uc berkeley advised by prof shankar sastry i also work closely with prof guanya shi i am affiliated with the ember center i m interning at amazon frontier ai robotics team with pieter abbeel i m interested in foundemental robot learning problems a k a receipe for physical agi scalable priors long horizon reasonings dexterous and agile motor skills in 2025 i interned at nvidia gear lab supervised by dr jim fan and prof yuke zhu previously i was a ms robotics student at cmu lecar lab and drive lab working with prof guanya shi and john m dolan research before 2024 in 2023 i was a visiting student with prof francesco borrelli at mpc lab uc berkeley from 2021 to 2024 i led ai racing tech ️ a multi million autonomous racing research project in ucb cmu and ucsd across 5 labs i deployed real world robot learning on f1 level self driving race cars at 160 mph we are the top u s team in the indy autonomous challenge learn more in my playground github mail linkedin x instagram youtube latest teleoperation as a service taas author haoru xue dec 2025 how to win the home robot startup game my answer scale data at deployment time here is why taas make sense lesson learned from the only robot learning system that works at scale today tesla autopilot 05 2025 cap x is accepted to icml 2026 doorman and viral are accepted to cvpr 2026 12 2025 new blog teleoperation as a service taas 12 2025 nvidia new paper doorman follow the release on x 11 2025 nvidia new paper viral follow the release on x 06 2025 ucb thrilled to announce leverb follow the release on x 05 2024 nvidia i am interning at nvidia gear lab 05 2025 icra dial mpc is selected as best paper finalist at icra 2025 see earlier 04 2025 icml one paper accepted at icml 2025 02 2025 new blog pathways to data scaling law of robotics foundation model 01 2025 icra three papers accepted at icra 2025 10 2024 ucb thrilled to announce anycar follow the release on x 09 2024 ucb thrilled to announce dial mpc ️ follow the release on x 08 2024 ucb i joined uc berkeley eecs phd program ai robotics 05 2024 icra presentation slides oral on learning mpc with error dynamics regression for autonomous racing 04 2024 cmu presentation slides master thesis talk on optimal control and robot learning on agile safety critical systems 04 2024 stanford talk on towards foundational control models for agile locomotion at stanford intelligent systems laboratory sisl 01 2024 ucb talk on safe online adaptation for robots with extreme dynamics at darpa ansr program 10 2023 ucb talk on learning mpc with error dynamics regression for autonomous racing at model predictive control mpc lab research ultimately i want to build generalist robots that will fundamentally change the human society recently these are my research interests enabling long horizon reasoning and generalization on vlm for robotics receipe for pre training that leads to stronger generalization bridging high level vision language planning and low level whole body motor skills on loco manipulation tasks cap x a framework for benchmarking and improving coding agents for robot manipulation max fu justin yu karim el refai ethan kou haoru xue huang huang wenli xiao guanzhi wang fei fei li guanya shi jiajun wu shankar sastry yuke zhu ken goldberg linxi jim fan icml 2026 website arxiv social media cap x evaluates frontier llm performance on robotics tasks by providing agentic harnesses agents write code to interact with the environment get feedbacks and improve via rl and skill libraries we find that these models generally have far superior generalization capability than frontier robotics models like vlas opening the sim to real door for humanoid pixel to action policy transfer haoru xue tairan he zi wang qingwei ben wenli xiao zhengyi luo ye yuan xingye da fernando castañeda guanya shi shankar sastry linxi jim fan yuke zhu cvpr 2026 website arxiv social media doorman proposes a teacher student bootstrap framework for challenging humanoid loco manipulation tasks such as door opening trained as an rgb policy purely in simulation it is up to 31 7 times faster than human in the real world viral visual sim to real at scale for humanoid loco manipulation tairan he zi wang haoru xue qingwei ben zhengyi luo wenli xiao ye yuan xingye da fernando castañeda shankar sastry changliu liu guanya shi linxi jim fan yuke zhu cvpr 2026 website arxiv social media viral investigates the scaling law of visual sim to real we find the right recipe to enjoy the free lunch of simulation zero shot robust continuous real world deployment self improving vision language action models with data generation via residual rl wenli xiao haotian lin andy peng haoru xue tairan he yuqi xie fengyuan hu jimmy wu zhengyi luo linxi jim fan guanya shi yuke zhu iclr 2026 website arxiv social media probe learn distill pld is a recipe for vla rl post training using real world data letting robots discover recover and distill their own data flywheel sonic supersizing motion tracking for natural humanoid whole body control zhengyi luo ye yuan tingwu wang chenran li sirui chen fernando castañeda zi ang cao jiefeng li david minor qingwei ben xingye da runyu ding cyrus hogg lina song edy lim eugene jeong tairan he haoru xue wenli xiao zi wang simon yuen jan kautz yan chang umar iqbal linxi jim fan yuke zhu oct 2025 website arxiv social media sonic is a general humanoid whole body motion tracker supporting various control modes leverb humanoid whole body control with latent vision language instruction haoru xue xiaoyu huang dantong niu qiayuan liao thomas kragerud jan tommy gravdahl xue bin peng guanya shi trevor darrell koushil sreenath shankar sastry june 2025 website arxiv social media leverb is the first latent whole body humanoid vla we introduce a latent vocabulary as an interface between vision language and whole body action to enable expressive task specification and interpolatable execution full order sampling based mpc for torque level locomotion control via diffusion style annealing haoru xue chaoyi pan zeji yi guannan qu guanya shi icra 2025 best paper finalist top 1 website arxiv code social media dial mpc ️ diffusion sampling based mpc can achieve adaptive and training free whole body control on legged systems using rl style rewards deployed in real on agile quadrupedal torque control pre training auto regressive robotic models with 4d representations dantong niu yuvan sharma haoru xue giscard biamby junyi zhang ziteng ji trevor darrell roei herzig icml 2025 website arxiv social media arm4r is an autoregressive robotic model that leverages low level 4d representations learned from human video data to yield a robotics model that has stronger spatial and temporal understandings anycar to anywhere learning universal dynamics model for agile and adaptive mobility wenli xiao haoru xue tony tao dvij kalaria john m dolan guanya shi icra 2025 website arxiv code social media ieee spectrum anycar ️ a generalist dynamics model built with transformer large scale sim pre training small scale real fine tuning achieves agile and adaptive control on a family of wheeled embodiments few or zero shot and outperforms specialist policies learning model predictive control with error dynamics regression for autonomous racing haoru xue edward l zhu john m dolan francesco borrelli icra 2024 website arxiv video code social media talk use mpc robot learning to explore optimal policy and dynamics model online safely perform sim2real and learn the handling limit of extreme driving like a professional race car driver deployed on a full size race car segment anything model for road network graph extraction congrui hetang haoru xue cindy le tianwei yue wenping wang yihui he cvpr 2024 workshop arxiv code we propose a sam based pipeline for large scale road network extraction from aerial image comparable accuracy with sota is achieved while being 40 times faster best paper 2nd workshop on scene graphs and graph representation learning education uc berkeley eecs phd ai robotics 2024 prof shankar sastry cmu robotics institute ms robotics 2022 2024 prof guanya shi john dolan uc san diego electrical eng 2018 2021 experience amazon frontier ai robotics far phd research intern feb 2026 present supervisors prof pieter abbeel dr rocky duan nvidia gear lab phd research intern may 2025 jan 2026 supervisors dr jim fan prof yuke zhu lecar lab cmu robotics institute visiting researcher may aug 2024 advisor prof guanya shi mpc lab uc berkeley visiting researcher apr aug 2023 advisor prof francesco borrelli ai racing tech lead graduate researcher dec 2019 may 2024 advisors prof shankar sastry john dolan dr allen yang jack silberman awards honors 2025 best paper finalist icra 2025 2024 uc berkeley eecs department scholarship recipient 2024 best paper cvpr 2nd workshop on scene graph s and graph representation learning 2023 3rd place indy autonomous challenge at las vegas ces 2022 2rd place indy autonomous challenge at texas motor speedway 2021 henry g booker memorial honors award uc san diego ece department i love robotics vyvyen homepage blog haoru xue phd at berkeley ai research uc berkeley playground social google scholar github email linkedin twitter x instagram youtube designed with wordpress feel free to email me for the website files
|
