Meta tags:
author=Zeyu Wang;
description=PhD in Computer Science and Engineering;

Headings (most frequently used words):

visual, for, in, and, training, 3d, of, adversarial, with, towards, the, double, unified, multimodal, pre, language, robustness, image, representation, camera, object, detection, knowledge, robust, search, publications, services, zeyu, wang, teaching, assistant, reviewer, phd, computer, science, engineering, uc, santa, cruz, education, vq, va, world, high, quality, question, answering, when, visualizing, is, first, step, to, reasoning, mira, benchmark, chain, thought, lightfusion, light, weighted, fusion, framework, understanding, generation, emerging, properties, pretraining, defense, instruction, tuning, improving, vision, model, what, if, we, recaption, billions, web, images, llama, revisiting, at, scale, rejuvenating, gpt, as, strong, learners, sculpting, holistic, contrastive, fedconv, enhancing, convolutional, neural, networks, handling, data, heterogeneity, federated, learning, distillbev, boosting, multi, cross, modal, distillation, an, inverse, scaling, law, clip, on, based, masked, autoencoders, enable, efficient, distillers, can, cnns, be, more, than, transformers, siamfc, accurate, tracking, target, estimation, guidelines, cite,

Text of the page (most frequently used words):
wang (22), zeyu (20), cite (17), pdf (16), xie (16), cihang (15), and (13), code (12), for (9), 2023 (9), denotes (9), equal (9), contribution (9), 2025 (7), #computer (6), santa (6), cruz (6), science (6), visual (6), zhou (6), 2024 (5), yuyin (5), zhu (5), arxiv (5), preprint (5), fan (5), the (4), vision (4), learning (4), november (4), with (4), training (4), haoqi (4), chaorui (4), deng (4), reviewer (3), technology (3), machine (3), 2022 (3), robust (3), alan (3), yuille (3), chen (3), junfei (3), xiao (3), january (3), adversarial (3), xianhang (3), haoqin (3), feng (3), chenhui (3), gou (3), kunchang (3), deyao (3), 2018 (3), 2021 (3), journal (2), ieee (2), transactions (2), cvpr2023 (2), iccv2023 (2), iclr2023 (2), summer (2), yuan (2), towards (2), june (2), yutong (2), bai (2), wei (2), efficient (2), knowledge (2), tmlr2024 (2), robustness (2), camera (2), object (2), detection (2), may (2), multi (2), modal (2), october (2), jieru (2), mei (2), cvpr2024 (2), shi (2), zheng (2), representation (2), language (2), image (2), pre (2), hongru (2), sucheng (2), ren (2), project (2), double (2), nie (2), weihao (2), unified (2), multimodal (2), zilong (2), publications (2), central (2), south (2), university (2), eng (2), institute (2), computing (2), chinese (2), academy (2), engineering (2), phd (2), degree (2), download, copy, powered, hugo, academic, theme, circuits, systems, video, international, pattern, analysis, intelligence, conference, eccv2024, icml2023, neurips, aaai, wacv2024, cse144, applied, fall, california, state, school, mathematics, cosmos, cse164, spring, teaching, assistant, services, aaai2020, 2019, gang, zuoxin, yinda, siamfc, accurate, tracking, target, estimation, guidelines, can, cnns, more, than, transformers, august, huiyu, masked, autoencoders, enable, distillers, zichao, shaoyuan, based, neurips2023, inverse, scaling, law, clip, september, xiaodong, yang, chenxu, luo, dingwen, distillbev, boosting, cross, distillation, liangqiong, peiran, fedconv, enhancing, convolutional, neural, networks, handling, data, heterogeneity, federated, yipeng, gao, sculpting, holistic, contrastive, icml2024, december, rejuvenating, gpt, strong, learners, revisiting, scale, dataset, icml2025, huangjie, qing, liu, bingchen, zhao, mude, hui, what, recaption, billions, web, images, llama, bhavya, kailkhura, brian, bartoldson, defense, instruction, tuning, improving, model, guang, ziang, song, xiaonan, shu, zhong, emerging, properties, pretraining, lightfusion, light, weighted, fusion, framework, understanding, generation, qinghao, huaxiu, yao, shen, yan, james, zou, yejin, choi, niklas, muennighoff, zijun, yiyang, when, visualizing, first, step, reasoning, mira, benchmark, chain, thought, hamid, rezatofighi, jianfei, cai, hongyi, zicheng, duan, world, high, quality, question, answering, automation, 2014, now, education, research, interests, mainly, lie, intersection, particular, interest, models, under, distribution, shifts, malicious, attacks, well, effective, 5th, year, student, supervised, before, this, received, have, also, spent, wonderful, times, megvii, qcraft, llnl, bytedance, seed, google, prof, service, home, search,

Text of the page (random words):
zeyu wang search zeyu wang zeyu wang home publications service zeyu wang phd in computer science and engineering uc santa cruz i am a 5th year phd student at uc santa cruz supervised by prof cihang xie before this i received my m s degree at institute of computing technology chinese academy of science in 2021 and my b eng degree at central south university in 2018 i have also spent wonderful times at google bytedance seed llnl qcraft and megvii my research interests mainly lie in the intersection of computer vision and machine learning with a particular interest for robust models under distribution shifts and malicious attacks as well as efficient and effective multi modal learning education ph d in computer science and engineering 2021 now uc santa cruz m s in computer science 2018 2021 institute of computing technology chinese academy of science b eng in automation 2014 2018 central south university publications vq va world towards high quality visual question visual answering chenhui gou zilong chen zeyu wang feng li deyao zhu zicheng duan kunchang li chaorui deng hongyi yuan haoqi fan cihang xie jianfei cai hamid rezatofighi november 2025 arxiv preprint denotes equal contribution pdf cite when visualizing is the first step to reasoning mira a benchmark for visual chain of thought yiyang zhou haoqin tu zijun wang zeyu wang niklas muennighoff fan nie yejin choi james zou chaorui deng shen yan haoqi fan cihang xie huaxiu yao qinghao ye november 2025 arxiv preprint pdf cite lightfusion a light weighted double fusion framework for unified multimodal understanding and generation zeyu wang zilong chen chenhui gou feng li chaorui deng deyao zhu kunchang li weihao yu haoqin tu haoqi fan cihang xie october 2025 arxiv preprint denotes equal contribution pdf cite emerging properties in unified multimodal pretraining chaorui deng deyao zhu kunchang li chenhui gou feng li zeyu wang shu zhong weihao yu xiaonan nie ziang song guang shi haoqi fan may 2025 arxiv preprint pdf cite code project double visual defense adversarial pre training and instruction tuning for improving vision language model robustness zeyu wang cihang xie brian bartoldson bhavya kailkhura january 2025 arxiv preprint pdf cite what if we recaption billions of web images with llama 3 xianhang li haoqin tu mude hui zeyu wang bingchen zhao junfei xiao sucheng ren jieru mei qing liu huangjie zheng yuyin zhou cihang xie june 2024 icml2025 denotes equal contribution pdf cite code dataset project revisiting adversarial training at scale zeyu wang xianhang li hongru zhu cihang xie january 2024 cvpr2024 denotes equal contribution pdf cite code rejuvenating image gpt as strong visual representation learners sucheng ren zeyu wang hongru zhu junfei xiao alan yuille cihang xie december 2023 icml2024 denotes equal contribution pdf cite code sculpting holistic 3d representation in contrastive language image 3d pre training yipeng gao zeyu wang wei shi zheng cihang xie yuyin zhou november 2023 cvpr2024 pdf cite code fedconv enhancing convolutional neural networks for handling data heterogeneity in federated learning peiran xu zeyu wang jieru mei liangqiong qu alan yuille cihang xie yuyin zhou october 2023 tmlr2024 denotes equal contribution pdf cite code distillbev boosting multi camera 3d object detection with cross modal knowledge distillation zeyu wang dingwen li chenxu luo cihang xie xiaodong yang september 2023 iccv2023 denotes equal contribution pdf cite code an inverse scaling law for clip training xianhang li zeyu wang cihang xie may 2023 neurips2023 denotes equal contribution pdf cite code on the adversarial robustness of camera based 3d object detection shaoyuan xie zichao li zeyu wang cihang xie january 2023 tmlr2024 pdf cite code masked autoencoders enable efficient knowledge distillers yutong bai zeyu wang junfei xiao chen wei huiyu wang alan yuille yuyin zhou cihang xie august 2022 cvpr2023 pdf cite code can cnns be more robust than transformers zeyu wang yutong bai yuyin zhou cihang xie june 2022 iclr2023 pdf cite code siamfc towards robust and accurate visual tracking with target estimation guidelines yinda xu zeyu wang zuoxin li ye yuan gang yu november 2019 aaai2020 denotes equal contribution pdf cite code services teaching assistant uc santa cruz cse164 computer vision spring 2022 uc santa cruz california state summer school for mathematics and science cosmos summer 2023 uc santa cruz cse144 applied machine learning fall 2023 reviewer conference reviewer cvpr2023 2024 iccv2023 eccv2024 iclr2023 2025 icml2023 2024 neurips 2023 2024 aaai 2025 wacv2024 journal reviewer ieee transactions on pattern analysis and machine intelligence international journal of computer vision ieee transactions on circuits and systems for video technology powered by the academic theme for hugo cite copy download