Meta tags:
keywords=blog, accent, , Ruoshi Liu 刘若石, jekyll;
author=;
description=;

Headings (most frequently used words):

about, contact, news, publication, invited, talks, reviewer, other, things,

Text of the page (most frequently used words):
hosted (30), the (28), 2024 (25), ruoshi (23), liu (22), paper (22), world (20), carl (19), vondrick (19), 2023 (16), project (16), page (16), and (15), learning (13), for (13), generative (11), cvpr (10), vision (10), from (10), human (10), 2025 (9), physical (9), code (9), oct (8), video (8), available (7), generating (7), recording (6), interaction (6), intelligent (6), computer (6), mar (5), nov (5), workshop (5), models (5), university (5), towards (5), robots (5), beyond (5), capability (5), pavel (5), tokmakov (5), ege (5), ozguroglu (5), shuran (5), song (5), iccv (4), eccv (4), jun (4), real (4), research (4), junbang (4), liang (4), sruthi (4), sudhakar (4), scientist (4), with (4), can (3), corl (3), feb (3), dec (3), large (3), model (3), 2021 (3), upenn (3), understanding (3), chen (3), wang (3), object (3), robot (3), seminar (3), umd (3), michael (3), rundi (3), basile (3), van (3), hoorick (3), zero (3), achal (3), dave (3), arxiv (3), oral (3), data (3), are (2), like (2), enjoy (2), fan (2), most (2), work (2), that (2), iclr (2), neurips (2), icra (2), siggraph (2), sep (2), may (2), apr (2), nyc (2), day (2), jul (2), webinar (2), dinesh (2), jayaraman (2), predictability (2), future (2), wei (2), alan (2), synthesis (2), reconstruction (2), christian (2), seeing (2), unseen (2), neural (2), network (2), inversion (2), nyu (2), design (2), tools (2), generation (2), intelligence (2), embodied (2), hao (2), mengxue (2), hou (2), andrew (2), owens (2), umichigan (2), better (2), than (2), georgia (2), dídac (2), surís (2), chengzhi (2), mao (2), park (2), blog (2), post (2), demo (2), shot (2), objects (2), changxi (2), zheng (2), qian (2), rendering (2), huy (2), new (2), novel (2), alper (2), canberk (2), step (2), via (2), self (2), 2026 (2), joined (2), amazon (2), far (2), github (2), linkedin (2), perception (2), cvpr24 (2), iccv23 (2), cvpr23 (2), corl24 (2), eccv24 (2), goal (2), this (2), phd (2), about (2), first, name, translated, into, virtual, meetings, sometimes, interrupted, year, old, domestic, shorthair, playing, guitar, few, bands, whose, music, deeply, big, movie, admire, performing, non, convex, gradient, ascent, descent, hiking, skiing, person, feel, weird, complicated, but, love, hirokazu, kore, eda, lee, chang, dong, quentin, tarantino, stanley, kubrick, sunset, rollercoaster, pink, floyd, radiohead, omnipotent, youth, society, pattie, rolling, stone, other, things, rss, icml, aaai, aistats, asia, tpami, ijcv, accv, reviewer, guest, lecture, chinese, games, 2022, chiu, mit, inverting, visual, guanying, xiaoguang, han, aigc, yuille, ccvl, lab, jhu, analysis, rupprecht, slides, oxford, shubham, tulsiani, cmu, james, tompkin, brown, adrien, gaidon, tri, angjoo, kanazawa, berkeley, jiajun, stanford, noah, snavely, time, kaan, akşit, ucl, feng, panel, talk, valse, fantastic, how, use, them, georgios, pavlakos, ai3dg, rhobin, shyamal, buch, hvu, 3dfm, foundation, ashok, veeraraghavan, rice, ece, shenlong, uiuc, anand, bhattad, ttic, uchicago, notre, dame, lingjie, ranjay, krishna, washington, alyosha, efros, bair, stella, frank, dellaert, tech, abhinav, shrivastava, ruohan, gao, david, fouhey, invited, talks, soft, matter, zhengyang, zhou, chaitanya, joshi, norton, linnea, lemma, zvonimir, dogic, hagan, seth, fraden, pengyu, hong, machine, forecasting, active, nematics, sachit, menon, dennis, simon, stent, what, you, reconstruct, shadow, high, concept, humans, light, bulbs, thermal, reflection, purva, tendulkar, landscape, sergey, zakharov, impactful, one, image, matt, deitke, matthew, wallingford, huong, ngo, oscar, michel, aditya, kusupati, laforte, vikram, voleti, samir, yitzhak, gadre, eli, vanderbilt, aniruddha, kembhavi, gkioxari, kiana, ehsani, ludwig, schmidt, ali, farhadi, zero123, objaverse, colossal, universe, sin3dm, diffusion, single, textured, shape, dian, highlight, pix2gestalt, amodal, segmentation, synthesizing, wholes, abdullah, hamdi, luke, melas, kyriazi, guocheng, jinjie, mai, bernard, ghanem, andrea, vedaldi, ges, generalized, exponential, splatting, efficient, radiance, field, cheng, chi, article, min, paperbot, using, kyle, sargent, camera, dolly, extreme, monocular, dynamic, view, richard, zemel, best, award, candidate, controlling, sleight, hand, maksym, bondarenko, weights, erasedraw, draw, erasing, images, dreamitate, visuomotor, policy, differentiable, improving, autonomous, underwater, manipulation, paarth, shah, rares, ambrus, generators, policies, mia, chiquier, detienne, wesley, alexandra, horowitz, york, smells, multimodal, dataset, olfaction, publication, resarch, fair, accepted, faculty, offer, news, twitter, edu, contact, equipping, scale, spatial, environment, adding, structures, significantly, mitigate, hallucination, enable, knowledge, transfer, modality, used, improve, skills, learned, through, supervised, exploration, icml25, icra25, iclr24, physically, grounding, neurips23, action, prior, develop, breaking, down, tackles, three, fundamental, aspects, systems, interact, frontier, robotics, science, department, maryland, college, got, advised, also, worked, closely, during, columbia, incoming, assistant, professor, semantic, google, scholar, 刘若石,

Text of the page (random words):
ruoshi liu ruoshi liu 刘若石 github google scholar semantic linkedin about about i am a research scientist at amazon frontier ai robotics far and an incoming assistant professor in the computer science department at university of maryland college park i got my phd from columbia university advised by carl vondrick i also worked closely with shuran song during my phd my research goal is to develop intelligent systems that can interact with the physical world breaking this down my work tackles three fundamental aspects of this goal a learning the action perception prior by equipping large scale vision generative models with a spatial and physical understanding of the world for interaction with the environment iccv23 corl24 eccv24 eccv24 cvpr24 neurips23 b physically grounding generative models by adding structures significantly mitigate hallucination and enable zero shot knowledge transfer to novel data modality cvpr23 corl24 cvpr23 iccv23 cvpr24 iclr24 c learning from real world interaction is used to improve the perception and interaction skills learned from human data through self supervised interaction and exploration icra25 icml25 contact ruoshi umd edu linkedin github twitter news dec 2025 joined amazon far as a resarch scientist jul 2025 joined fair as a research scientist mar 2025 accepted faculty offer from umd publication new york smells a large multimodal dataset for olfaction arxiv 2026 ege ozguroglu junbang liang ruoshi liu mia chiquier michael detienne wesley wei qian alexandra horowitz andrew owens carl vondrick paper project page data video generators are robot policies arxiv 2026 junbang liang pavel tokmakov ruoshi liu sruthi sudhakar paarth shah rares ambrus carl vondrick paper project page video code self improving autonomous underwater manipulation icra 2025 ruoshi liu huy ha mengxue hou shuran song carl vondrick paper project page video code differentiable robot rendering corl 2024 oral ruoshi liu alper canberk shuran song carl vondrick paper project page video code dreamitate real world visuomotor policy learning via video generation corl 2024 junbang liang ruoshi liu ege ozguroglu sruthi sudhakar achal dave pavel tokmakov shuran song carl vondrick paper project page video code erasedraw learning to draw step by step via erasing objects from images eccv 2024 alper canberk maksym bondarenko ege ozguroglu ruoshi liu carl vondrick paper project page code model weights controlling the world by sleight of hand eccv 2024 oral best paper award candidate sruthi sudhakar ruoshi liu basile van hoorick carl vondrick richard zemel paper project page generative camera dolly extreme monocular dynamic novel view synthesis eccv 2024 oral basile van hoorick rundi wu ege ozguroglu kyle sargent ruoshi liu pavel tokmakov achal dave changxi zheng carl vondrick paper project page code paperbot learning to design real world tools using paper arxiv 2024 ruoshi liu junbang liang sruthi sudhakar huy ha cheng chi shuran song carl vondrick paper project page 8 min video new scientist article ges generalized exponential splatting for efficient radiance field rendering cvpr 2024 abdullah hamdi luke melas kyriazi guocheng qian jinjie mai ruoshi liu carl vondrick bernard ghanem andrea vedaldi paper project page pix2gestalt amodal segmentation by synthesizing wholes cvpr 2024 highlight ege ozguroglu ruoshi liu dídac surís dian chen achal dave pavel tokmakov carl vondrick paper project page sin3dm learning a diffusion model from a single 3d textured shape iclr 2024 rundi wu ruoshi liu carl vondrick changxi zheng paper project page code demo objaverse xl a colossal universe of 3d objects neurips 2023 matt deitke ruoshi liu matthew wallingford huong ngo oscar michel aditya kusupati alan fan christian laforte vikram voleti samir yitzhak gadre eli vanderbilt aniruddha kembhavi carl vondrick georgia gkioxari kiana ehsani ludwig schmidt ali farhadi paper project page code zero123 xl zero 1 to 3 zero shot one image to 3d object iccv 2023 3 most impactful paper at iccv 2023 ruoshi liu rundi wu basile van hoorick pavel tokmakov sergey zakharov carl vondrick paper project page code demo landscape learning for neural network inversion iccv 2023 ruoshi liu chengzhi mao purva tendulkar hao wang carl vondrick paper blog post humans as light bulbs 3d human reconstruction from thermal reflection cvpr 2023 high concept research ruoshi liu carl vondrick paper project page what you can reconstruct from a shadow cvpr 2023 ruoshi liu sachit menon chengzhi mao dennis park simon stent carl vondrick paper blog post learning the predictability of the future cvpr 2021 dídac surís ruoshi liu carl vondrick paper project page machine learning forecasting of active nematics soft matter 2021 zhengyang zhou chaitanya joshi ruoshi liu michael m norton linnea lemma zvonimir dogic michael f hagan seth fraden pengyu hong paper invited talks mar 2025 generative computer vision for the physical world upenn hosted by dinesh jayaraman mar 2025 generative computer vision for the physical world nyu hosted by david fouhey mar 2025 generative computer vision for the physical world umd hosted by ruohan gao and abhinav shrivastava feb 2025 generative computer vision for the physical world georgia tech hosted by frank dellaert feb 2025 generative computer vision for the physical world umichigan hosted by stella yu nov 2024 learning to do better than human bair hosted by alyosha efros nov 2024 learning to do better than human university of washington hosted by ranjay krishna oct 2024 generative embodied ai guest lecture upenn hosted by lingjie liu recording available oct 2024 towards intelligent robots beyond human capability umichigan vision seminar hosted by andrew owens oct 2024 towards intelligent robots beyond human capability university of notre dame hosted by mengxue hou oct 2024 towards intelligent robots beyond human capability ttic uchicago hosted by anand bhattad recording available oct 2024 towards intelligent robots beyond human capability uiuc vision seminar hosted by shenlong wang sep 2024 towards intelligent robots beyond human capability rice ece seminar hosted by ashok veeraraghavan jun 2024 3d foundation models for physical intelligence 3dfm workshop cvpr hosted by hao su jun 2024 from video understanding to embodied ai hvu workshop cvpr hosted by shyamal buch jun 2024 from human object interaction to robot object interaction rhobin workshop cvpr hosted by xi wang jun 2024 3d generation for physical intelligence ai3dg workshop cvpr hosted by georgios pavlakos may 2024 fantastic 3d generative models and how to use them valse webinar talk and panel available in chinese apr 2024 learning to design tools in the real world nyc vision day mar 2024 generating the 3d world nyu hosted by chen feng feb 2024 neural network inversion ucl recording available hosted by kaan akşit dec 2023 seeing the unseen ai time large model workshop dec 2023 seeing the unseen nyc vision day hosted by noah snavely nov 2023 generating the 3d world stanford hosted by jiajun wu nov 2023 generating the 3d world berkeley hosted by angjoo kanazawa nov 2023 generating the 3d world tri hosted by adrien gaidon oct 2023 generating the 3d world brown university recording available hosted by james tompkin oct 2023 generating the 3d world cmu hosted by shubham tulsiani jul 2023 generating the 3d world oxford recording and slides available hosted by christian rupprecht may 2023 analysis by synthesis for 3d reconstruction ccvl lab jhu hosted by alan yuille apr 2023 aigc in the 3d world games webinar recording available hosted by xiaoguang han and guanying chen sep 2022 inverting generative models for visual understanding mit hosted by wei chiu ma oct 2021 learning the predictability of the future upenn hosted by dinesh jayaraman reviewer cvpr iccv eccv iclr neurips rss corl icra icml aaai aistats siggraph siggraph asia tpami ijcv accv other things my first name ruoshi 若石 can be translated into like a rolling stone my virtual meetings are sometimes interrupted by pattie a 5 year old domestic shorthair i like playing guitar a few bands whose music i deeply enjoy omnipotent youth society radiohead pink floyd sunset rollercoaster i m a big movie fan and most admire the work of stanley kubrick quentin tarantino lee chang dong and hirokazu kore eda i enjoy performing non convex gradient ascent and descent a k a hiking and skiing as a person i feel that i m so weird and complicated but i love it