Meta tags:
description=Chaoyi Pan is a PhD candidate in ECE at Carnegie Mellon University, researching physics-based robot data generation and generative models in control.;
author=Chaoyi Pan;

Headings (most frequently used words):

based, control, and, sampling, optimization, of, mpc, learning, in, generative, physics, robotics, diffusion, for, trajectory, via, with, lab, tsinghua, chaoyi, pan, news, publications, blog, projects, experience, action, representation, data, generation, systems, much, ado, about, noising, dispelling, the, myths, robotic, spider, scalable, informed, dexterous, retargeting, model, full, order, torque, level, locomotion, style, annealing, covo, theoretical, analysis, optimal, covariance, design, hand, manipulation, unknown, shapes, tactile, sensing, efficient, bimanual, handover, rearrangement, symmetry, aware, actor, critic, flexible, decentralized, displacement, formation, multi, agent, reinforcement, approach, agile, drone, transportation, explicit, time, intelligent, blind, navigation, headgear, on, head, conditioned, reflexes, amazon, frontier, ai, meta, fair, embodiment, actions, research, team, carnegie, mellon, university, stanford, interactive, perception, robot, wulab, slab,

Text of the page (most frequently used words):
and (16), for (13), based (13), chaoyi (12), pan (12), #control (11), #research (11), paper (10), 2025 (9), prof (9), learning (8), guanya (8), shi (8), 2024 (8), optimization (7), code (7), supervised (6), generative (6), guannan (6), website (6), the (6), carnegie (5), mellon (5), university (5), system (5), with (5), phd (5), yuan (4), jun (4), usa (4), robot (4), model (4), physics (4), data (4), trajectory (4), diffusion (4), mpc (4), using (3), sep (3), 2022 (3), intern (3), lab (3), models (3), 2023 (3), human (3), aug (3), robotics (3), through (3), icra (3), zeji (3), sampling (3), generation (3), about (3), candidate (3), decentralized (2), formation (2), multi (2), agent (2), shen (2), assistant (2), beijing (2), china (2), tsinghua (2), 2021 (2), developed (2), bimanual (2), handover (2), rearrangement (2), tasks (2), reinforcement (2), tactile (2), hand (2), manipulation (2), jeannette (2), bohg (2), stanford (2), pittsburgh (2), present (2), retargeting (2), trajectories (2), francois (2), hogan (2), embodiment (2), working (2), understanding (2), action (2), representation (2), large (2), scale (2), behavior (2), cloning (2), 2026 (2), experience (2), headgear (2), head (2), conditioned (2), navigation (2), transportation (2), explicit (2), time (2), aware (2), projects (2), tutorial (2), feb (2), jul (2), blog (2), wang (2), via (2), best (2), spider (2), much (2), ado (2), noising (2), publications (2), nov (2), released (2), news (2), designed, mobile, robots, hausdorff, distance, slab, oct, 2020, coordination, structured, wulab, implemented, bayesian, without, object, shape, prior, vision, information, summer, interactive, perception, developing, bridging, contact, rich, real, world, student, universal, converting, raw, interaction, feasible, science, meta, fair, actions, team, collection, rocky, duan, san, francisco, amazon, frontier, jan, wearable, that, guides, visually, impaired, users, reflex, signals, intuitive, hands, free, obstacle, avoidance, intelligent, blind, reflexes, quadrotor, drones, carrying, slung, payloads, enabling, aggressive, aerial, maneuvers, collision, planning, agile, drone, view, all, posts, missing, lesson, how, navigate, project, reading, hillbilly, elegy, memoir, family, culture, crisis, resources, recommendation, eusipco, yuzi, yan, zexu, zhang, flexible, displacement, approach, yunfei, huazhe, xiaolong, efficient, symmetry, actor, critic, iros, marion, lepert, shenli, rika, antonova, unknown, shapes, sensing, systems, l4dc, guanqi, covo, theoretical, analysis, optimal, covariance, design, finalist, haoru, xue, full, order, torque, level, locomotion, style, annealing, neurips, arxiv, changhao, haozhi, ziqi, liu, homanga, bharadhwaj, akarsh, sharma, tingfan, jitendra, malik, scalable, informed, dexterous, iclr, giri, anantharaman, nai, chieh, huang, claire, jin, daniel, pfrommer, chenyang, frank, permenter, nicholas, boffi, max, simchowitz, dispelling, myths, robotic, denotes, equal, contribution, passed, qualification, exam, officially, received, hsu, chang, memorial, fellowship, nominated, award, dial, apr, cross, from, demonstrations, first, empirical, study, policies, dec, linkedin, twitter, github, scholar, email, interests, lie, intersection, 3rd, year, affiliated, lecar, institute, electrical, computer, engineering,

Text of the page (random words):
chaoyi pan carnegie mellon university chaoyi pan about news publications blog projects experience chaoyi pan phd candidate carnegie mellon university i am a 3rd year phd candidate in electrical and computer engineering affiliated with the robotics institute at carnegie mellon university working with prof guanya shi lecar lab and prof guannan qu my research interests lie at the intersection of physics based robot data generation and the understanding of generative models in control email scholar github twitter linkedin cv news dec 2025 much ado about noising is released the first large scale empirical study on generative control policies for behavior cloning nov 2025 spider is released cross embodiment data generation and learning from human demonstrations apr 2025 dial mpc nominated for icra 2025 best paper award feb 2025 received the hsu chang memorial fellowship nov 2024 passed phd qualification exam officially a phd candidate publications denotes equal contribution action representation in generative control much ado about noising dispelling the myths of generative robotic control chaoyi pan giri anantharaman nai chieh huang claire jin daniel pfrommer chenyang yuan frank permenter guannan qu nicholas boffi guanya shi max simchowitz iclr 2026 paper code website physics based data generation spider scalable physics informed dexterous retargeting chaoyi pan changhao wang haozhi qi ziqi liu homanga bharadhwaj akarsh sharma tingfan wu guanya shi jitendra malik francois hogan arxiv 2025 paper code website model based diffusion for trajectory optimization chaoyi pan zeji yi guanya shi guannan qu neurips 2024 paper code website sampling based optimization 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 paper code website covo mpc theoretical analysis of sampling based mpc and optimal covariance design zeji yi chaoyi pan guanqi he guannan qu guanya shi l4dc 2024 paper code website robotics systems in hand manipulation of unknown shapes with tactile sensing chaoyi pan marion lepert shenli yuan rika antonova jeannette bohg iros 2023 paper efficient bimanual handover and rearrangement via symmetry aware actor critic learning yunfei li chaoyi pan huazhe xu xiaolong wang yi wu icra 2023 paper code website flexible decentralized displacement based formation control a multi agent reinforcement learning approach chaoyi pan yuzi yan zexu zhang yuan shen eusipco 2022 paper code blog aug 2024 learning control resources recommendation research aug 2024 hillbilly elegy a memoir of a family and culture in crisis reading jul 2024 missing lesson how to navigate through a cs research project research jul 2024 model based diffusion for trajectory optimization tutorial research feb 2024 diffusion model for learning and control tutorial research view all posts projects agile drone transportation with explicit time trajectory optimization trajectory optimization for quadrotor drones carrying slung payloads enabling aggressive aerial transportation maneuvers through explicit time optimization and collision aware planning intelligent blind navigation headgear based on head conditioned reflexes a wearable headgear system that guides visually impaired users through head conditioned reflex signals for intuitive hands free obstacle avoidance navigation experience jan 2026 present amazon frontier ai and robotics lab research intern san francisco usa working on understanding of action representation and large scale behavior cloning data collection supervised by prof guanya shi and prof rocky duan jun aug 2025 meta fair embodiment actions research team research science intern pittsburgh usa developed universal human to robot physics based retargeting system for converting raw human interaction trajectories to feasible robot trajectories supervised by francois hogan jun 2023 present carnegie mellon university phd student pittsburgh usa developing generative models for control bridging learning based generative models with model based control for contact rich real world tasks supervised by prof guanya shi and prof guannan qu jun sep 2022 stanford interactive perception and robot learning lab summer intern stanford usa implemented tactile based in hand manipulation system using bayesian optimization without object shape prior or vision information supervised by prof jeannette bohg sep 2021 jun 2022 tsinghua wulab research assistant beijing china developed bimanual coordination system for handover and rearrangement tasks using structured reinforcement learning supervised by prof yi wu oct 2020 sep 2021 tsinghua slab research assistant beijing china designed decentralized formation control system for mobile robots using multi agent rl and hausdorff distance supervised by prof yuan shen 2025 chaoyi pan carnegie mellon university