Meta tags:
author= Sucheng Ren;
Headings (most frequently used words):
-
Text of the page (most frequently used words):
sucheng (18), ren (18), and (17), bibtex (15), conference (14), paper (14), vision (13), computer (12), learning (11), code (11), for (10), the (10), alan (9), yuille (9), got (9), accepted (9), ieee (8), pattern (8), recognition (8), cvpr (8), wang (8), 2025 (8), autoregressive (8), nbsp (8), shengfeng (7), self (6), cihang (6), xie (6), scale (6), han (5), video (5), chen (5), objects (5), representation (5), international (5), 2023 (5), with (5), image (5), next (5), university (5), supervised (4), attention (4), token (4), research (4), prediction (4), generation (4), yang (3), guoqiang (3), object (3), liu (3), student (3), 2022 (3), models (3), distillation (3), oral (3), feng (3), based (3), machine (3), pretraining (3), liang (3), chieh (3), xiaohui (3), shen (3), qihang (3), wise (3), flow (3), matching (3), 2026 (3), var (3), salient (2), 2021 (2), unsupervised (2), segmentation (2), training (2), master (2), from (2), distilling (2), cross (2), knowledge (2), data (2), mixing (2), zhou (2), zhengqi (2), gao (2), first (2), into (2), inductive (2), integrating (2), capability (2), capturing (2), multiscale (2), each (2), layer (2), adaptively (2), merging (2), tokens (2), iccv (2), xinchao (2), former (2), mim (2), pre (2), trained (2), zhang (2), wei (2), tinymim (2), 2024 (2), gpt (2), icml (2), hongru (2), zhu (2), visual (2), tmlr (2), arvideo (2), mamba (2), modeling (2), generalize (2), flowar (2), frequency (2), aware (2), high (2), quality (2), findings (2), feb (2), johns (2), hopkins (2), may (2), jan (2), cvpr2026 (2), science (2), advised (2), prof (2), chu, xin, european, 2020, acceptance, rate, spotlight, eccv, tenet, triple, excitation, network, detection, wenxi, yongtuo, haoxin, jointly, moving, recurring, reciprocal, transformations, yong, jianming, learn, how, teach, better, modal, advanced, lip, reading, generic, strategy, that, can, improve, both, cnns, vits, yuyin, huiyu, simple, prior, improving, work, delves, influence, biases, hang, zhao, yonglong, tian, zihui, xue, tianyu, hua, advise, bias, songhua, xingyi, guided, transformer, evolving, reallocation, jiashi, daquan, shunted, via, multi, aggregation, explore, techniques, transfer, success, large, smaller, ones, zheng, fangyun, empirical, study, enhance, semantic, rich, supervision, junfei, xiao, zeyu, rejuvenating, strong, learners, transactions, use, yijiang, are, pretrain, cluster, iclr, heng, peng, linjie, jieru, mei, lei, fangxun, shu, haoqin, xianhang, simplest, design, make, compatible, any, vae, meets, conputer, beyond, explicitly, incorporates, conditioning, coming, soon, decouple, which, allows, rebuild, more, computationally, efficient, manner, nataniel, ruiz, yaodong, decoupled, selected, publications, cvpr2023, jul, iccv2023, aug, join, phd, igpt, presentation, icml2024, arm, iclr2025, icml2025, jun, xar, iccv2025, freqflow, news, github, scholar, email, lies, diffusion, generative, model, multimodal, 任苏成, where, fortunate, professor, received, degree, south, china, technology, currently, intern, apple, previously, spent, great, time, bytedance, seed, microsoft, asia, msra, tsinghua, national, singapore,
Text of the page (random words):
sucheng ren sucheng ren hi i am sucheng ren 任苏成 a computer science ph d student at johns hopkins university where i am fortunate to be advised by professor alan yuille and prof cihang xie i received my b s and m s degree in computer science from south china university of technology advised by prof shengfeng he currently i am a research intern at apple previously i spent great time at bytedance seed microsoft research asia msra tsinghua university and national university of singapore my research lies at the diffusion autoregressive based generative model and multimodal learning email nbsp nbsp cv nbsp nbsp scholar nbsp nbsp github nbsp nbsp news feb 2026 freqflow got accepted by cvpr2026 m var got accepted by cvpr2026 findings jun 2025 xar got accepted by iccv2025 may 2025 flowar got accepted by icml2025 jan 2025 arm got accepted by iclr2025 jan 2025 arvideo got accepted by tmlr may 2024 d igpt got accepted by icml2024 as oral presentation aug 2023 join johns hopkins university as a phd student jul 2023 sg former got accepted by iccv2023 feb 2023 tinymim got accepted by cvpr2023 selected publications m var decoupled scale wise autoregressive modeling for high quality image generation sucheng ren yaodong yu nataniel ruiz feng wang alan yuille cihang xie ieee conference on computer vision and pattern recognition cvpr findings 2026 paper code bibtex we decouple scale wise attention which allows to rebuild var in a more computationally efficient manner frequency aware flow matching for high quality image generation sucheng ren qihang yu ju he xiaohui shen alan yuille liang chieh chen ieee conference on computer vision and pattern recognition cvpr 2026 coming soon bibtex we explicitly incorporates frequency aware conditioning into the flow matching beyond next token next x prediction for autoregressive visual generation sucheng ren qihang yu ju he xiaohui shen alan yuille liang chieh chen international conference on conputer vision iccv 2025 paper code bibtex we generalize next token prediction to next x prediction flowar scale wise autoregressive image generation meets flow matching sucheng ren qihang yu ju he xiaohui shen alan yuille liang chieh chen international conference on machine learning icml 2025 paper code bibtex we generalize next scale prediction to simplest scale design and make it compatible with any vae 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 international conference on learning representation iclr 2025 paper code bibtex we are the first to pretrain mamba in vision with cluster based autoregressive modeling arvideo autoregressive pretraining for self supervised video representation learning sucheng ren hongru zhu chen wei yijiang li alan yuille cihang xie transactions on machine learning research tmlr 2025 paper code bibtex we use autoregressive pretraining for self supervised video representation learning rejuvenating image gpt as strong visual representation learners sucheng ren zeyu wang hongru zhu junfei xiao alan yuille cihang xie international conference on machine learning icml oral 2024 paper code bibtex we enhance image gpt with semantic rich supervision tinymim an empirical study of distilling mim pre trained models sucheng ren fangyun wei zheng zhang han hu ieee conference on computer vision and pattern recognition cvpr 2023 paper code bibtex we explore distillation techniques to transfer the success of large mim based pre trained models to smaller ones shunted self attention via multi scale token aggregation sucheng ren daquan zhou shengfeng he jiashi feng xinchao wang ieee conference on computer vision and pattern recognition cvpr oral 2022 paper code bibtex integrating the capability of capturing multiscale objects in each attention layer by adaptively merging tokens sg former self guided transformer with evolving token reallocation sucheng ren xingyi yang songhua liu xinchao wang international conference on computer vision iccv 2023 paper code bibtex integrating the capability of capturing multiscale objects in each attention layer by adaptively merging tokens co advise cross inductive bias distillation sucheng ren zhengqi gao tianyu hua zihui xue yonglong tian shengfeng he hang zhao ieee conference on computer vision and pattern recognition cvpr 2022 paper code bibtex the first work delves into the influence of models inductive biases in knowledge distillation a simple data mixing prior for improving self supervised learning sucheng ren huiyu wang zhengqi gao shengfeng he alan yuille yuyin zhou cihang xie ieee conference on computer vision and pattern recognition cvpr 2022 paper bibtex a generic training strategy in data mixing that can improve the self supervised representation learning of both cnns and vits learning from the master distilling cross modal advanced knowledge for lip reading sucheng ren yong du jianming lv guoqiang han and shengfeng he ieee conference on computer vision and pattern recognition cvpr 2021 paper bibtex training a master to learn how to teach a better student reciprocal transformations for unsupervised video object segmentation sucheng ren wenxi liu yongtuo liu haoxin chen guoqiang han and shengfeng he ieee conference on computer vision and pattern recognition cvpr 2021 paper bibtex code jointly learning salient objects moving objects recurring objects for unsupervised video object segmentation tenet triple excitation network for video salient object detection sucheng ren chu han xin yang guoqiang han and shengfeng he european conference on computer vision eccv 2020 spotlight acceptance rate 5 0 paper bibtex
|
