Meta tags:
author=Jihyun Lee;
description=Postdoctoral AI Research Scientist at Meta;

Headings (most frequently used words):

jihyun, lee, news, publications, academic, activities, awards, honors, reviewer, invited, talk, student, organizer,

Text of the page (most frequently used words):
kim (20), lee (20), paper (17), 2025 (17), #jihyun (17), project (13), tae (12), kyun (12), the (9), and (9), 2026 (9), cvpr (8), minhyuk (8), sung (8), code (7), research (7), based (6), student (6), learning (6), hand (6), eccv (5), iccv (5), neurips (5), with (5), meta (5), prof (5), accepted (5), award (4), kaist (4), 2024 (4), invited (4), poster (4), equal (4), contributions (4), shunsuke (4), saito (4), avatars (4), scientist (4), using (3), workshop (3), talk (3), icml (3), 2023 (3), for (3), donghwan (3), diffusion (3), jason (3), saragih (3), rewind (3), human (3), lead (3), msc (3), large (3), scale (3), codec (3), jun (3), postdoctoral (3), proposed (2), dct (2), ray (2), grid (2), line (2), suppression (2), method (2), undergraduate (2), competition (2), 2019 (2), outstanding (2), 2022 (2), reviewer (2), awards (2), hands (2), computer (2), siggraph (2), activities (2), 2021 (2), text (2), oral (2), presentation (2), motion (2), image (2), via (2), shape (2), min (2), choi (2), representation (2), two (2), generation (2), woo (2), object (2), full (2), dynamics (2), takehiko (2), ohkawa (2), ryosuke (2), furuta (2), yoichi (2), sato (2), mentored (2), first (2), origen (2), changmin (2), mpmavatar (2), physics (2), physhandi (2), reconstruction (2), interactions (2), publications (2), presenting (2), jul (2), giving (2), sep (2), back, top, dynamic, segmentation, silver, prize, 2018, kips, reduce, blocking, effects, honorable, mention, ksc, kcc, developed, automatic, traffic, light, control, system, reinforcement, excellence, korea, software, convergence, hackathon, mayoral, awarded, tas, who, earned, highest, ratings, survey, honors, workshops, google, explorecsr, organizer, graphics, asia, machine, iclr, aaai, vision, ijcv, etc, academic, icassp, minsu, kang, simin, injung, fast, dctts, efficient, deep, convolutional, speech, dataset, cvprw, binod, bhattarai, face, parsing, from, rgb, depth, cross, domain, mutual, hyunjin, pop, out, aware, deformation, laplacian, mva, hangil, park, yongmin, seo, taewon, joodong, yun, jaewon, contrastive, knowledge, distillation, anomaly, detection, multi, illumination, focus, display, images, honggyu, im2hands, attentive, implicit, interacting, shapes, junbong, jang, fourierhandflow, neural, fourier, query, flow, giljoo, nam, interhandgen, interaction, cascaded, reverse, woojin, cho, minjae, minje, taeyun, taewook, hyokeun, hwan, ryu, woontack, dense, graspnet, grasping, taxonomy, weipeng, alexander, richard, shih, wei, shaojie, bai, wang, real, time, egocentric, whole, body, exemplar, identity, conditioning, fabian, prada, yichen, shoou, takaaki, shiratori, generative, modeling, dependent, self, contact, poses, yunhong, daehyeon, kyeongmin, yeo, zero, shot, orientation, grounding, gaussian, accurate, robust, team, unreasonable, effectiveness, avatar, pretraining, deformable, coming, soon, naru, suzuki, tatsuro, banno, affordance, guided, prior, publication, list, available, successfully, defended, sincerely, thank, serving, thesis, committee, gyeongsik, moon, hanbyul, joo, seunghoon, hong, attending, present, also, egovis, congratulations, author, take, scgen, doctoral, consortium, kccv, aug, are, both, papers, were, led, new, students, whom, helped, mentor, joined, lca, mar, apr, affordgen, news, linkedin, github, scholar, email, aims, enable, artificial, intelligence, understand, simulate, behavior, including, surrounding, environment, recently, have, been, especially, interested, centric, world, models, hello, lab, where, fortunate, work, previously, obtained, advised, visited, intern, hosted, reality, labs, sofien, bouaziz, about,

Text of the page (random words):
jihyun lee jihyun lee about publications activities awards jihyun lee postdoctoral ai research scientist at meta hello i am a postdoctoral ai research scientist at meta codec avatars lab where i am fortunate to work with shunsuke saito and sofien bouaziz previously i obtained my ph d at kaist advised by tae kyun t k kim and minhyuk sung i visited meta reality labs as a research scientist intern in 2024 hosted by jason saragih my research aims to enable artificial intelligence to understand and simulate human behavior including interactions with the surrounding environment recently i have been especially interested in human centric world models email cv scholar github linkedin x news jun 2026 affordgen is accepted to eccv 2026 apr 2026 physhandi is accepted to icml 2026 mar 2026 lca is accepted to cvpr 2026 sep 2025 i joined meta as a postdoctoral ai research scientist sep 2025 mpmavatar and origen are accepted to neurips 2025 both papers were led by new msc students whom i helped as a mentor aug 2025 i ll be giving an invited talk at the hands workshop at iccv 2025 jul 2025 i ll be giving a talk at the doctoral consortium and presenting an invited poster on rewind at kccv 2025 jul 2025 scgen is accepted to iccv 2025 congratulations to the lead author take jun 2025 i m attending cvpr 2025 to present rewind i ll also be presenting an invited poster at the egovis workshop jun 2025 successfully defended my ph d i sincerely thank prof tae kyun kim prof minhyuk sung prof seunghoon hong prof hanbyul joo and prof gyeongsik moon for serving on my thesis committee publications full publication list is available in my cv affordance guided diffusion prior for 3d hand reconstruction naru suzuki takehiko ohkawa tatsuro banno jihyun lee ryosuke furuta yoichi sato eccv 2026 paper coming soon physhandi physics based reconstruction of hand deformable object interactions jihyun lee changmin lee donghwan kim tae kyun kim equal contributions icml 2026 project paper large scale codec avatars the unreasonable effectiveness of large scale avatar pretraining large scale codec avatars team meta cvpr 2026 project paper mpmavatar learning 3d gaussian avatars with accurate and robust physics based dynamics changmin lee jihyun lee tae kyun kim neurips 2025 mentored the lead student s first msc research project project paper code origen zero shot 3d orientation grounding in text to image generation yunhong min daehyeon choi kyeongmin yeo jihyun lee minhyuk sung equal contributions neurips 2025 mentored the lead student s first msc research project project paper code generative modeling of shape dependent self contact human poses takehiko ohkawa jihyun lee shunsuke saito jason saragih fabian prada yichen xu shoou i yu ryosuke furuta yoichi sato takaaki shiratori iccv 2025 project paper rewind real time egocentric whole body motion diffusion with exemplar based identity conditioning jihyun lee weipeng xu alexander richard shih en wei shunsuke saito shaojie bai te li wang minhyuk sung tae kyun kim jason saragih cvpr 2025 project paper dense hand object ho graspnet with full grasping taxonomy and dynamics woojin cho jihyun lee minjae yi minje kim taeyun woo donghwan kim taewook ha hyokeun lee je hwan ryu woontack woo tae kyun kim eccv 2024 project paper code interhandgen two hand interaction generation via cascaded reverse diffusion jihyun lee shunsuke saito giljoo nam minhyuk sung tae kyun kim cvpr 2024 project paper code fourierhandflow neural 4d hand representation using fourier query flow jihyun lee junbong jang donghwan kim minhyuk sung tae kyun kim neurips 2023 project paper code im2hands learning attentive implicit representation of interacting two hand shapes jihyun lee minhyuk sung honggyu choi tae kyun kim cvpr 2023 project paper code presentation poster contrastive knowledge distillation for anomaly detection in multi illumination focus display images hangil park jihyun lee yongmin seo taewon min joodong yun jaewon kim tae kyun kim equal contributions mva 2023 oral paper pop out motion 3d aware image deformation via learning shape laplacian jihyun lee minhyuk sung hyunjin kim tae kyun kim equal contributions cvpr 2022 project paper code presentation poster face parsing from rgb and depth using cross domain mutual learning jihyun lee binod bhattarai tae kyun kim cvprw 2021 oral paper dataset fast dctts efficient deep convolutional text to speech minsu kang jihyun lee simin kim injung kim icassp 2021 paper academic activities reviewer computer vision cvpr iccv eccv ijcv etc machine learning iclr neurips icml aaai computer graphics siggraph siggraph asia pg invited talk hands workshop iccv 2025 student organizer google explorecsr workshops kaist awards honors outstanding reviewer 2024 eccv outstanding ta award 2022 kaist awarded to tas who earned the highest ratings on kaist cs student survey excellence award mayoral award at korea software convergence hackathon 2019 developed an automatic traffic light control system based on reinforcement learning honorable mention award at undergraduate student paper competition 2019 ksc kcc proposed a method to reduce blocking effects of dct based x ray grid line suppression silver prize at undergraduate student paper competition 2018 kips proposed a dct based x ray grid line suppression method using dynamic segmentation back to top