Meta tags:
author=Zecheng He;

Headings (most frequently used words):

research, selected, publications, full, list, work, experience, education, professional, services,

Text of the page (most frequently used words):
zecheng (17), and (15), paper (15), zhang (11), generation (10), image (9), video (9), #research (8), ruby (7), lee (7), hou (7), computer (6), models (6), 2021 (5), 2019 (5), tianwei (5), arxiv (5), preprint (5), for (5), xiaoliang (5), dai (5), haoyu (5), felix (5), juefei (5), peter (5), vajda (5), 2024 (5), the (5), cvpr (4), sep (4), aug (4), scientist (4), meta (4), 2023 (4), your (4), chen (4), kunpeng (4), tingbo (4), peizhao (4), animesh (4), sinha (4), project (4), page (4), movie (4), personalized (4), native (4), aaai (3), university (3), intern (3), international (3), 2017 (3), attacks (3), model (3), vision (3), pattern (3), recognition (3), liu (3), yao (3), with (3), tuning (3), sun (3), browser (3), does (3), not (3), support (3), tag (3), core (3), contributor (3), engineering (2), 2015 (2), princeton (2), machine (2), learning (2), may (2), 2020 (2), staff (2), genai (2), symposium (2), against (2), privacy (2), data (2), ieee (2), collaborative (2), inference (2), annual (2), conference (2), high (2), architecture (2), understanding (2), user (2), medical (2), junjiao (2), tian (2), chih (2), yen (2), cheng (2), jialiang (2), wang (2), sam (2), tsai (2), towards (2), ankit (2), imagine (2), yourself (2), free (2), gen (2), including (2), diffusion (2), first (2), iccv, eccv, neurips, icml, iclr, bmvc, professional, services, information, science, technology, china, ustc, electrical, education, sri, jun, engineer, facebook, google, senior, reality, labs, jan, feb, present, work, experience, microarchitecture, micro, how, secure, cache, side, channel, 2018, preserving, through, obfuscation, internet, things, journal, attacking, protecting, edge, cloud, systems, security, applications, acsac, inversion, sensitive, sample, fingerprinting, deep, neural, networks, guangyuan, performance, hpca, new, reasoning, about, speculative, execution, srinivas, sunkara, xiaoxue, zang, ying, lijuan, nevan, wichers, gabriel, schubiner, jindong, artificial, intelligence, actionbert, leveraging, actions, semantic, interfaces, qingsong, yuexiang, lin, kai, yefeng, zheng, kevin, zhou, transactions, imaging, adversarial, hierarchical, feature, hiding, zsolt, kira, trainable, projected, gradient, method, robust, fine, peize, hao, tang, yujun, shi, xuan, yushi, artsiom, sanakoyeu, tao, zijian, matt, feiszli, yun, token, shuffle, resolution, autoregressive, song, yaqiao, luo, xide, xia, ahmed, elgammal, directorllm, human, centric, cong, wei, luxin, wenhu, mocha, grade, talking, character, synthesis, ramchandani, vincent, cheung, siddharth, shah, anmol, kalia, harihar, subramanyam, alireza, zareian, jain, ning, roshan, sumbaly, team, technical, report, cast, media, foundation, feng, liang, samaneh, azadi, diana, marculescu, 2025, weaver, multi, concept, personalization, anchored, prompts, selected, publications, full, list, interested, generative, based, was, leading, pretrain, post, train, lead, author, llama, focusing, design, development, moviegen, github, linkedin, scholar, email, working, controllable, obtained, from,

Text of the page (random words):
zecheng he zecheng he i am staff research scientist at meta genai working on image and video generation including personalized image video diffusion models native image generation and controllable generation i obtained my ph d from princeton university email cv scholar linkedin github research i am interested in generative models for image and video including diffusion based and native generation models i was the 1 core contributor of moviegen leading personalized video generation pretrain and post train 2 lead and first author of imagine yourself meta s first personalized image generation model and 3 core contributor to llama native image generation focusing on native model architecture design and development selected publications full list your browser does not support the video tag movie weaver tuning free multi concept video personalization with anchored prompts feng liang haoyu ma zecheng he tingbo hou ji hou kunpeng li xiaoliang dai felix juefei xu samaneh azadi animesh sinha peizhao zhang peter vajda diana marculescu computer vision and pattern recognition cvpr 2025 project page paper your browser does not support the video tag movie gen a cast of media foundation models zecheng he as core contributor the movie gen team technical report 2024 project page paper imagine yourself tuning free personalized image generation zecheng he bo sun felix juefei xu haoyu ma ankit ramchandani vincent cheung siddharth shah anmol kalia harihar subramanyam alireza zareian li chen ankit jain ning zhang peizhao zhang roshan sumbaly peter vajda animesh sinha arxiv preprint 2024 project page paper your browser does not support the video tag mocha towards movie grade talking character synthesis cong wei bo sun haoyu ma ji hou felix juefei xu zecheng he xiaoliang dai luxin zhang kunpeng li tingbo hou animesh sinha peter vajda wenhu chen arxiv preprint 2024 project page paper directorllm for human centric video generation kunpeng song tingbo hou zecheng he haoyu ma jialiang wang animesh sinha sam tsai yaqiao luo xiaoliang dai li chen xide xia peizhao zhang peter vajda ahmed elgammal felix juefei xu arxiv preprint 2024 paper token shuffle towards high resolution image generation with autoregressive models xu ma peize sun haoyu ma hao tang chih yao ma jialiang wang kunpeng li xiaoliang dai yujun shi xuan ju yushi hu artsiom sanakoyeu felix juefei xu ji hou junjiao tian tao xu tingbo hou yen cheng liu zecheng he zijian he matt feiszli peizhao zhang peter vajda sam tsai yun fu arxiv preprint 2024 paper trainable projected gradient method for robust fine tuning junjiao tian xiaoliang dai chih yao ma zecheng he yen cheng liu zsolt kira computer vision and pattern recognition cvpr 2023 paper adversarial medical image with hierarchical feature hiding qingsong yao zecheng he yuexiang li yi lin kai ma yefeng zheng s kevin zhou ieee transactions on medical imaging 2023 paper actionbert leveraging user actions for semantic understanding of user interfaces zecheng he srinivas sunkara xiaoxue zang ying xu lijuan liu nevan wichers gabriel schubiner ruby lee jindong chen annual aaai conference on artificial intelligence aaai 2021 paper new models for understanding and reasoning about speculative execution attacks zecheng he guangyuan he ruby lee international symposium on high performance computer architecture hpca 2021 paper sensitive sample fingerprinting of deep neural networks zecheng he tianwei zhang ruby lee computer vision and pattern recognition cvpr 2019 paper model inversion attacks against collaborative inference zecheng he tianwei zhang ruby lee annual computer security applications conference acsac 2019 paper attacking and protecting data privacy in edge cloud collaborative inference systems zecheng he tianwei zhang ruby lee ieee internet of things journal 2019 paper privacy preserving machine learning through data obfuscation tianwei zhang zecheng he ruby lee arxiv preprint 2018 paper how secure is your cache against side channel attacks zecheng he tianwei zhang ruby lee international symposium on microarchitecture micro 2017 paper work experience feb 2023 present staff research scientist meta genai sep 2021 jan 2023 research scientist senior research scientist meta reality labs may 2020 aug 2020 research intern google research may 2019 aug 2019 machine learning engineer intern facebook jun 2017 sep 2017 research intern sri international education sep 2015 aug 2021 ph d in electrical and computer engineering princeton university sep 2015 aug 2021 b e in information engineering university of science and technology of china ustc professional services cvpr iccv eccv neurips icml iclr aaai bmvc