Meta tags:
author=Cihang Xie;

Headings (most frequently used words):

2023, 2022, 2021, 2020, 2024, 2019, 2018, 2017,

Text of the page (most frequently used words):
xie (79), cihang (70), bibtex (68), pdf (68), page (53), project (52), wang (45), 2024 (45), 2023 (42), alan (41), yuille (41), zhou (36), and (30), the (30), with (29), yuyin (28), student (28), for (25), adversarial (22), wei (21), visiting (21), next (21), zhang (20), university (20), chen (19), summer (19), cvpr (18), learning (16), jieru (16), mei (16), 2022 (16), training (15), accepted (15), from (13), xianhang (13), zeyu (13), arxiv (12), iclr (11), ren (11), image (11), neurips (11), 2020 (10), 2021 (10), are (10), undergraduate (10), graduate (10), yang (9), eccv (9), sucheng (9), vision (9), bingchen (9), zhao (9), johns (9), hopkins (9), our (9), zhishuai (8), detection (8), bai (8), imagenet (8), supervised (8), affiliated (8), iccv (7), object (7), transformers (7), huiyu (7), models (7), lei (7), haoqin (7), tmlr (7), attacks (6), jianyu (6), segmentation (6), visual (6), robust (6), yingwei (6), liu (6), huang (6), representation (6), clipa (6), accuracy (6), papers (6), release (6), model (6), nbsp (6), examples (5), lingxi (5), zhu (5), 2018 (5), shen (5), networks (5), neural (5), data (5), towards (5), junfei (5), xiao (5), clip (5), workshop (5), santa (5), cruz (5), fellowship (5), recognition (4), 2017 (4), semantic (4), slides (4), shot (4), song (4), box (4), van (4), robustness (4), gao (4), video (4), mingxing (4), tan (4), based (4), images (4), yutong (4), pre (4), one (4), masked (4), miccai (4), scaling (4), fangxun (4), shu (4), siwei (4), zijun (4), baskin (4), top (4), paper (4), research (4), press (3), report (3), deep (3), under (3), 2019 (3), improving (3), can (3), against (3), aaai (3), quoc (3), jiang (3), boqing (3), gong (3), attack (3), beyond (3), peng (3), yixiao (3), zhuowan (3), benchmark (3), cnns (3), han (3), stan (3), sclaroff (3), sarah (3), adel (3), bargal (3), nataniel (3), ruiz (3), sizhe (3), zichao (3), efficient (3), knowledge (3), multi (3), language (3), zero (3), 000 (3), instruction (3), text (3), llms (3), hongru (3), mude (3), hui (3), editing (3), mamba (3), icml (3), google (3), two (3), three (3), which (3), new (3), congratulations (3), winning (3), additionally (3), datacomp (3), professor (3), computer (3), face (2), tech (2), jun (2), objects (2), concepts (2), network (2), part (2), siyuan (2), qiao (2), semantics (2), competition (2), defense (2), track (2), defenses (2), first (2), classifier (2), that (2), strong (2), white (2), kaiming (2), laurens (2), der (2), maaten (2), transferable (2), via (2), properties (2), scale (2), universal (2), qihang (2), linjie (2), architecture (2), local (2), state (2), art (2), extra (2), adam (2), kortylewski (2), black (2), texture (2), benjamin (2), durme (2), reasoning (2), more (2), than (2), tao (2), kong (2), jinghao (2), yucheng (2), testing (2), self (2), junbo (2), xiaolin (2), using (2), pixel (2), autoencoders (2), xing (2), shao (2), lequan (2), medical (2), zihao (2), zihan (2), yiqing (2), camera (2), modal (2), yuanze (2), lin (2), yao (2), fomo (2), sight (2), hao (2), human (2), llm (2), enhancing (2), peiran (2), federated (2), junyang (2), level (2), shaoyuan (2), eacl (2), multimodal (2), naacl (2), yunchao (2), building (2), tuning (2), layernorm (2), attention (2), machine (2), shi (2), zheng (2), yipeng (2), autoregressive (2), pretraining (2), heng (2), edit (2), high (2), quality (2), dataset (2), jinrui (2), feng (2), yunfei (2), stronger (2), this (2), recaption (2), llama (2), oxford (2), california (2), san (2), diego (2), chancellor (2), jack (2), peggy (2), downes (2), students (2), january (2), february (2), july (2), attains (2), team (2), place (2), brain (2), challenge (2), 2nd (2), vit (2), igpt (2), subtrack (2), performance (2), recap (2), lab (2), interested (2), please (2), facebook (2), stolen, jon, barron, chinese, cleverhans, library, open, sources, bmvc, detecting, parts, partially, occluded, annals, mathematical, sciences, applications, vittal, premachandran, compositional, voting, deepvoting, explainable, partial, occlusion, single, enriched, book, runner, solution, nips, mitigating, effects, through, randomization, transferability, input, diversity, blog, successfully, defend, yuxin, feature, denoising, ghost, intriguing, ning, changqing, zou, chengying, lifeng, physical, camouflage, detectors, xiaochen, lian, xiaojie, jin, search, lightweight, non, pytorch, reimplementation, without, improve, xiaohui, zhenyu, liao, regional, homogeneity, perturbations, yinzhi, cao, chenglin, patchattack, reinforcement, method, defending, smooth, phd, dissertation, tang, shape, debiased, cho, jui, hsieh, xiangning, accurate, quan, tran, elias, stengel, eskin, calibrating, operations, symbolic, real, fairly, compares, evaluations, ibot, bert, online, tokenizer, fast, advprop, weichao, qiu, simulated, shengfeng, zhengqi, simple, mixing, prior, huan, vip, unified, certified, recovery, patch, spatiotemporal, yingwen, qinghua, zhehao, attackers, post, process, mitigate, score, query, kate, saenko, finding, differences, between, convnets, counterfactual, simulation, bag, tricks, fgsm, practical, disruption, translation, deepfake, ieee, tpami, hongkai, xiong, wenrui, dai, yuhui, bnet, batch, normalization, enhanced, linear, transformation, shutong, shortcut, preference, enable, distillers, qingyue, consistency, guided, meta, bootstrapping, semi, shengtian, sang, swinmm, view, swin, xiaodong, chenxu, luo, dingwen, distillbev, boosting, cross, distillation, smaug, sparse, autoencoder, christoph, feichtenhofer, haoqi, fan, yanghao, karttikeya, mangalam, diffusion, inverse, law, within, budget, unlocks, enhances, truthfulness, ethics, compress, align, curating, audio, understanding, liang, chieh, spformer, transformer, superpixel, ekin, dogus, cubuk, down, comprehensive, analysis, strategies, liangqiong, fedconv, convolutional, handling, heterogeneity, unleashing, power, prompting, localization, representations, unimodal, xin, eric, kaiwen, zonglin, navigation, attacker, wishes, byzantine, embodied, agents, finetuning, angtian, benchmarking, radiance, fields, matthew, lungren, xuxi, fengze, bootstrap, combating, label, noise, sculpting, holistic, contrastive, revisiting, yijiang, arvideo, aqa, bench, interactive, evaluating, sequential, ability, yichun, yadong, druv, pai, guoyizhe, jiahao, also, needs, registers, pixels, hierarchical, approach, global, aggregation, zhiding, shiyi, lan, wenxuan, ziqi, space, worth, 256, descriptions, make, descriptive, huaxiu, wangchunshu, junlin, yiyang, chenhang, cui, how, many, unicorns, safety, evaluation, rejuvenating, gpt, learners, huangjie, qing, what, billions, web, publications, nanyang, technological, waymo, master, umich, hong, ucla, duke, irvine, shanghai, jiao, tong, washington, pennsylvania, berkeley, amazon, southern, alumni, edinburgh, juncheng, xiaoke, recipient, yanqing, current, serving, area, chair, senior, program, committee, ijcai, dmae, june, enables, limited, computational, resources, furthermore, low, cost, just, effectively, elevates, impressive, addition, best, september, task, metastases, brats, october, november, larger, coming, december, both, base, large, red, teaming, will, code, soon, trojan, spotlight, probing, accpted, advxl, mixcon3d, l2b, march, resolution, detailed, aligned, instructions, fine, tuned, instructpix2pix, delivers, superior, april, strongest, secures, may, where, use, powered, llava, entire, billion, shows, higher, textual, help, train, t2i, recent, news, leading, has, you, these, opportunities, complete, form, multiple, openings, interns, flexible, starting, times, assured, autonomy, vlaa, hiring, follow, cihangxie, check, latest, updates, visit, group, received, degree, advised, have, worked, intern, fair, receive, bloomberg, distinguished, assistant, interest, lies, intersection, goal, systems, particularly, securing, distribution, shifts, developing, minimal, supervision, science, engineering,

Text of the page (random words):
u our lab has multiple openings for summer interns and visiting students with flexible starting times if you are interested in these opportunities please complete this form recent news new we release recap datacomp 1b where we use a llama 3 powered llava model to recaption the entire 1 3 billion images from datacomp 1b our recap datacomp 1b shows higher textual quality and can help to train stronger clip models and t2i models july 2024 three papers are accepted by eccv 2024 may 2024 congratulations to xianhang li on winning the jack baskin peggy downes baskin fellowship additionally d igpt is accepted by icml 2024 our strongest model secures an imagenet top 1 accuracy of 90 0 with vit h april 2024 we release hq edit a dataset with high resolution images detailed and aligned editing instructions our fine tuned instructpix2pix delivers superior editing performance additionally two papers are accepted by tmlr march 2024 one paper is accepted by naacl 2024 and one paper is accepted by tmlr february 2024 three papers advxl mixcon3d l2b are accepted by cvpr 2024 january 2024 our tuning layernorm in attention is accepted by iclr 2024 as a spotlight paper our visual probing is accpted by eacl 2024 new congratulations to zijun and the team on winning the 2nd place in both the base model subtrack and the large model subtrack red teaming track in neurips 2023 trojan detection challenge we will release the code and the report soon december 2023 one paper is accepted by tmlr additionally we release d igpt which attains 89 5 imagenet top 1 accuracy with vit l larger models are coming november 2023 clipa v2 is accepted by neurips 2023 r0 fomo workshop and sight beyond text is accepted by neurips 2023 instruction workshop october 2023 congratulations to siwei and the team on winning the 2nd place in task 4 brain metastases segmentation of miccai 2023 brats challenge september 2023 clipa is accepted by neurips 2023 in addition we release our best model clipa g 14 which attains 83 0 zero shot imagenet top 1 accuracy new we release clipa which enables clip training with limited computational resources furthermore at a low cost of just 15 000 our clipa v2 effectively elevates the zero shot imagenet top 1 accuracy to an impressive 81 8 july 2023 three papers are accepted by iccv 2023 june 2023 two papers are accepted by miccai 2023 february 2023 dmae is accepted by cvpr 2023 january 2023 two papers are accepted by iclr 2023 i am serving as an area chair for cvpr 2024 2023 iclr 2024 2023 2022 icml 2024 2023 iccv 2023 2021 neurips 2024 2023 2022 eccv 2022 and a senior program committee for aaai 2022 ijcai 2021 current students xianhang li ph d of 2021 uc santa cruz chancellor s fellowship jack baskin peggy downes baskin fellowship zeyu wang ph d of 2021 siwei yang ph d of 2023 mude hui ph d of 2023 co supervised with yuyin zhou jinrui yang ph d of 2023 co supervised with yuyin zhou zijun wang ph d of 2024 yanqing liu ph d of 2024 haoqin tu ph d of 2024 uc santa cruz chancellor s fellowship recipient co supervised with yuyin zhou xiaoke huang ph d of 2024 co supervised with yuyin zhou juncheng wu ph d of 2024 co supervised with yuyin zhou chen wei affiliated ph d student from johns hopkins university junfei xiao affiliated ph d student from johns hopkins university sucheng ren affiliated ph d student from johns hopkins university lei zhang affiliated ph d student from uc san diego bingchen zhao visiting graduate student from university of edinburgh fangxun shu visiting graduate student in summer 24 yunfei xie visiting undergraduate student in summer 24 alumni 2023 zijun wang visiting undergraduate student in summer 23 next ph d at uc santa cruz haoqin tu visiting graduate student in summer 23 next ph d at uc santa cruz lei zhang visiting graduate student in summer 23 next ph d at uc san diego yipeng gao visiting graduate student in summer 23 next ph d at university of southern california jieru mei affiliated ph d student from johns hopkins university next google zhuowan li affiliated ph d student from johns hopkins university next google yixiao zhang affiliated ph d student from johns hopkins university next amazon 2022 sizhe chen visiting graduate student in 2022 next ph d at uc berkeley yuanze lin visiting graduate student in summer 22 next ph d at university of oxford chen wang visiting graduate student in summer 22 next ph d at university of pennsylvania zihan li visiting graduate student in summer 22 next ph d at university of washington junyang wu visiting undergraduate student in summer 22 next ph d at shanghai jiao tong university shaoyuan xie visiting undergraduate student in summer 22 next ph d at uc irvine yiqing wang visiting undergraduate student in summer 22 next ph d at duke university peiran xu visiting undergraduate student in summer 22 next ph d at ucla yunchao zhang visiting undergraduate student in summer 22 next ph d at the university of hong kong zihao wei visiting undergraduate student in summer 22 next master at umich 2021 sucheng ren visiting graduate student in summer 21 next ph d at johns hopkins university jinghao zhou visiting undergraduate student in summer 21 next ph d at university of oxford 2020 yingwei li affiliated ph d student from johns hopkins university next waymo yucheng han visiting undergraduate student in summer 20 next ph d at nanyang technological university publications 2024 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 arxiv 2024 pdf project page bibtex rejuvenating image gpt as strong visual representation learners sucheng ren zeyu wang hongru zhu junfei xiao alan yuille cihang xie icml 2024 pdf project page bibtex how many unicorns are in this image a safety evaluation benchmark for vision llms haoqin tu chenhang cui zijun wang yiyang zhou bingchen zhao junlin han wangchunshu zhou huaxiu yao cihang xie eccv 2024 pdf project page bibtex a semantic space is worth 256 language descriptions make stronger segmentation models with descriptive properties junfei xiao ziqi zhou wenxuan li shiyi lan jieru mei zhiding yu bingchen zhao alan yuille yuyin zhou cihang xie eccv 2024 pdf project page bibtex from pixels to objects a hierarchical approach for part and object segmentation using local and global aggregation yunfei xie cihang xie alan yuille jieru mei eccv 2024 pdf bibtex autoregressive pretraining with mamba in vision sucheng ren xianhang li haoqin tu feng wang fangxun shu lei zhang jieru mei linjie yang peng wang heng wang alan yuille cihang xie arxiv 2024 pdf project page bibtex mamba vision mamba also needs registers feng wang jiahao wang sucheng ren guoyizhe wei jieru mei wei shao yuyin zhou alan yuille cihang xie arxiv 2024 pdf project page bibtex scaling white box transformers for vision jinrui yang xianhang li druv pai yuyin zhou yi ma yadong yu cihang xie arxiv 2024 pdf project page bibtex hq edit a high quality dataset for instruction based image editing mude hui siwei yang bingchen zhao yichun shi heng wang peng wang cihang xie yuyin zhou arxiv 2024 pdf project page bibtex aqa bench an interactive benchmark for evaluating llms sequential reasoning ability siwei yang bingchen zhao cihang xie arxiv 2024 pdf project page bibtex arvideo autoregressive pretraining for self supervised video representation learning sucheng ren hongru zhu chen wei yijiang li alan yuille cihang xie arxiv 2024 pdf bibtex revisiting adversarial training at scale zeyu wang xianhang li hongru zhu cihang xie cvpr 2024 pdf project page bibtex sculpting holistic 3d representation in contrastive language image 3d pre training yipeng gao zeyu wang wei shi zheng cihang xie yuyin zhou cvpr 2024 pdf project page bibtex learning to bootstrap for combating label noise yuyin zhou xianhang li fengze liu xuxi chen lequan yu cihang xie matthew p lungren lei xing cvpr 2024 pdf project page bibtex benchmarking robustness in neural radiance fields chen wang angtian wang junbo li alan yuille cihang xie cvpr adversarial machine learning workshop 2024 pdf bibtex tuning layernorm in attention towards efficient multimodal llm finetuning bingchen zhao haoqin tu chen wei jieru mei cihang xie iclr 2024 pdf project page bibtex navigation as the attacker wishes towards building byzantine robust embodied agents under federated learning yunchao zhang zonglin di kaiwen zhou cihang xie xin eric wang naacl 2024 pdf project page bibtex localization vs semantics visual representations in unimodal and multimodal models zhuowan li cihang xie benjamin van durme alan yuille eacl 2024 pdf project page bibtex on the adversarial robustness of camera based 3d object detection shaoyuan xie zichao li zeyu wang cihang xie tmlr 2024 pdf project page bibtex unleashing the power of visual prompting at the pixel level junyang wu xianhang li chen wei huiyu wang alan yuille yuyin zhou cihang xie tmlr 2024 pdf project page bibtex 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 tmlr 2024 pdf project page bibtex scaling down clip a comprehensive analysis of data architecture and training strategies zichao li cihang xie ekin dogus cubuk tmlr 2024 pdf bibtex spformer enhancing vision transformer with superpixel representation jieru mei liang chieh chen alan yuille cihang xie arxiv 2024 pdf bibtex 2023 audio visual llm for video understanding fangxun shu lei zhang hao jiang cihang xie arxiv 2023 pdf bibtex compress align curating image text data with human knowledge lei zhang fangxun shu sucheng ren hao jiang bingchen zhao cihang xie arxiv 2023 pdf bibtex sight beyond text multi modal training enhances llms in truthfulness and ethics haoqin tu bingchen zhao chen wei cihang xie neurips instruction workshop 2023 pdf project page bibtex clipa v2 scaling clip training with 81 1 zero shot imagenet accuracy within a 10 000 budget an extra 4 000 unlocks 81 8 accuracy xianhang li zeyu wang cihang xie neurips r0 fomo workshop 2023 pdf project page bibtex an inverse scaling law for clip training xianhang li zeyu wang cihang xie neurips 2023 pdf project page bibtex diffusion models as masked autoencoders chen wei karttikeya mangalam po yao huang yanghao li haoqi fan hu xu huiyu wang cihang xie alan yuille christoph feichtenhofer iccv 2023 pdf project page bibtex smaug sparse masked autoencoder for efficient video language pre training yuanze lin chen wei huiyu wang alan yuille cihang xie iccv 2023 pdf bibtex distillbev boosting multi camera 3d object detection with cross modal knowledge distillation zeyu wang dingwen li chenxu luo cihang xie xiaodong yang iccv 2023 pdf bibtex swinmm masked multi view with swin transformers for 3d medical image segmentation yiqing wang zihan li jieru mei zihao wei li liu chen wang shengtian sang alan yuille cihang xie yuyin zhou miccai 2023 pdf project page bibtex consistency guided meta learning for bootstrapping semi supervised medical image segmentation qingyue wei lequan yu xianhang li wei shao cihang xie lei xing yuyin zhou miccai 2023 pdf project page bibtex masked autoencoders enable efficient knowledge distillers yutong bai zeyu wang junfei xiao chen wei huiyu wang alan yuille yuyin zhou cihang xie cvpr 2023 pdf project page bibtex can cnns be more robust than transformers zeyu wang yutong bai yuyin zhou cihang xie iclr 2023 pdf project page bibtex one pixel shortcut on the learning preference of deep neural networks shutong wu sizhe chen cihang xie xiaolin huang iclr 2023 pdf bibtex bnet batch normalization with enhanced linear transformation yuhui xu lingxi xie cihang xie wenrui dai jieru mei siyuan qiao wei shen hongkai xiong alan yuille ieee tpami 2023 pdf project page bibtex practical disruption of image translation deepfake networks nataniel ruiz sarah adel bargal cihang xie stan sclaroff aaai 2023 pdf bibtex 2022 bag of tricks for fgsm adversarial training zichao li li liu zeyu wang yuyin zhou cihang xie arxiv 2022 pdf project page bibtex finding differences between transformers and convnets using counterfactual simulation testing nataniel ruiz sarah adel bargal cihang xie kate saenko stan sclaroff neurips 2022 pdf project page bibtex adversarial attack on attackers post process to mitigate black box score based query attacks sizhe chen zhehao huang qinghua tao yingwen wu cihang xie xiaolin huang neurips 2022 pdf project page bibtex in defense of image pre training for spatiotemporal recognition xianhang li huiyu wang chen wei jieru mei alan yuille yuyin zhou cihang xie eccv 2022 pdf project page bibtex vip unified certified detection and recovery for patch attack with vision transformers junbo li huan zhang cihang xie eccv 2022 pdf bibtex a simple data mixing prior for improving self supervised learning sucheng ren huiyu wang zhengqi gao shengfeng he alan yuille yuyin zhou cihang xie cvpr 2022 pdf project page bibtex simulated adversarial testing of face recognition models nataniel ruiz adam kortylewski weichao qiu cihang xie sarah adel bargal alan yuille stan sclaroff cvpr 2022 pdf bibtex fast advprop jieru mei yucheng han yutong bai yixiao zhang yingwei li xianhang li alan yuille cihang xie iclr 2022 pdf project page bibtex ibot image bert pre training with online tokenizer jinghao zhou chen wei huiyu wang wei shen cihang xie alan yuille tao kong iclr 2022 pdf project page press bibtex 2021 are transformers more robust than cnns yutong bai jieru mei alan yuille cihang xie neurips 2021 the first benchmark that fairly compares transformers with cnns on robustness evaluations pdf project page bibtex calibrating concepts and operations towards symbolic reasoning on real images zhuowan li elias stengel eskin yixiao zhang cihang xie quan tran benjamin van durme alan yuille iccv 2021 pdf project page bibtex robust and accurate object detection via adversarial learning xiangning chen cihang xie mingxing tan li zhang cho jui hsieh boqing gong cvpr 2021 pdf project page bibtex shape texture debiased neural network training yingwei li qihang yu mingxing tan jieru mei peng tang wei shen alan yuille cihang xie iclr 2021 pdf project page bibtex 2020 towards robust representation learning and beyond cihang xie phd dissertation pdf bibtex smooth adversarial training cihang xie mingxing tan boqing gong alan yuille quoc le tech report arxiv state of the art method for defending against adversarial attacks on imagenet pdf project page bibtex patchattack a black box texture based attack with reinforcement learning chenglin yang adam kortylewski cihang xie yinzhi cao alan yuille eccv 2020 pdf project page bibtex regional homogeneity towards learning transferable universal adversarial perturbations against defenses yingwei li song bai cihang xie zhenyu liao xiaohui shen alan yuille eccv 2020 pdf project page bibtex adversarial examples improve image recognition cihang xie min...