Meta tags:

Headings (most frequently used words):

chen, wei, research, news, blog, selected, publications, ema, quiet, hyperparameter, that, moves, diffusion, leaderboards,

Text of the page (most frequently used words):
2026 (16), chen (16), wei (15), arxiv (12), and (10), code (9), xie (8), wang (8), alan (7), yuille (7), project (7), page (7), #diffusion (7), visual (6), models (6), 2025 (6), the (6), with (5), for (5), zhang (5), world (5), pyvision (5), yunfei (5), play (5), meta (4), iclr (4), cvpr (4), neurips (4), perception (4), vision (4), generalize (4), from (4), christoph (3), feichtenhofer (3), yao (3), genex (3), daniel (3), encoder (3), multi (3), shitian (3), zhao (3), agentic (3), icml (3), learning (3), reason (3), model (3), generative (3), congratulations (3), research (3), accepted (3), university (3), 2022 (2), press (2), cihang (2), huiyu (2), ibot (2), image (2), pre (2), training (2), 2023 (2), haoqi (2), fan (2), masked (2), huang (2), cheng (2), peng (2), junfei (2), xiao (2), generating (2), explorable (2), blog (2), oral (2), not (2), workshop (2), turn (2), kaipeng (2), ming (2), shaoheng (2), lin (2), haoquan (2), through (2), game (2), memo (2), augmented (2), yifei (2), xiaoyu (2), selected (2), ema (2), hyperparameter (2), can (2), how (2), that (2), act (2), fair (2), professor (2), last, update, may, improved, scaled, dinov2, tao, kong, shen, jinghao, zhou, bert, online, tokenizer, most, influential, papers, chao, yuan, saining, feature, prediction, self, supervised, iccv, yanghao, karttikeya, mangalam, autoencoders, 2024, jiahui, zhishuai, siyuan, qiao, chenxi, liu, makes, text, strong, cross, modal, interface, jieneng, rama, chellappa, khashabi, jiahao, luoxin, tianmin, shu, taiming, piotr, dollár, nikhila, ravi, shiyu, dong, marco, monteiro, junke, hanoona, rasheed, jathushan, rajasegaran, jiale, zhi, tengyu, andrea, madotto, jang, hyun, cho, peize, sun, bolya, best, embeddings, are, output, network, interactions, llms, qilong, dynamic, tooling, wenshuo, forging, open, via, shiyi, lan, yinsong, zhangyang, pramod, viswanath, cheston, tan, hongyuan, mei, yihan, alexander, duffy, zhizhou, sha, jianzhu, bobby, kevin, memory, context, optimization, robust, agent, llm, games, preprint, zhe, gan, liang, chieh, tsu, jui, taming, outlier, tokens, transformers, publications, examine, exponential, moving, average, often, overlooked, recent, speed, run, benchmarks, seemingly, small, experimental, detail, change, benchmark, results, rankings, should, interpreted, quiet, moves, leaderboards, june, evaluation, receiving, 000, his, work, lambda, grant, presentation, aaai, new, faculty, highlight, organizing, meet, active, sensing, closed, loop, planning, serving, area, chair, news, enabling, based, reasoning, tool, agents, using, just, create, but, understand, representations, worlds, dsr, diffmae, building, foundational, encoders, power, downstream, scale, maskfeat, representation, asks, approach, this, three, angles, learn, see, about, minimal, supervision, weichen3012, gmail, com, completed, advised, after, phd, joined, postdoctoral, researcher, during, doctoral, studies, also, interned, received, honors, peking, eecs, google, deepmind, bloomberg, distinguished, johns, hopkins, assistant, computer, science, rice,

Text of the page (random words):
chen wei chen wei i am an assistant professor of computer science at rice university i completed my ph d at johns hopkins university advised by bloomberg distinguished professor alan l yuille after my phd i joined meta fair as a postdoctoral researcher during my doctoral studies i also interned at google deepmind and meta fair i received my b s with honors from peking university eecs weichen3012 at gmail com research my research asks how can ai learn to see reason about and act in the visual world with minimal supervision i approach this from three angles visual representation learning building foundational visual encoders ibot maskfeat perception encoder that power downstream perception at scale generative world models using generative models not just to create but to understand learning representations from diffusion diffmae de diffusion dsr and generating explorable worlds genex agentic vision enabling models to reason and act through vision from game based reasoning play to generalize to tool augmented visual agents pyvision pyvision rl news 2026 serving as area chair for neurips 2026 2026 congratulations to shitian zhao and yunfei xie pyvision rl and memo accepted to icml 2026 2026 co organizing the cvpr 2026 workshop on world models meet active sensing and closed loop planning 2026 selected as an aaai new faculty highlight 2026 congratulations to yunfei xie play to generalize accepted to iclr 2026 2025 perception encoder accepted to neurips 2025 as oral presentation 2025 congratulations to yunfei xie for receiving the lambda research grant 10 000 for his work on play to generalize blog with yifei wang and xiaoyu wu june 2026 generative model evaluation ema a quiet hyperparameter that moves diffusion leaderboards we examine exponential moving average ema an often overlooked hyperparameter in recent speed run image diffusion benchmarks a seemingly small experimental detail can change how benchmark results and model rankings should be interpreted selected publications taming outlier tokens in diffusion transformers xiaoyu wu yifei wang tsu jui fu liang chieh chen zhe gan chen wei arxiv preprint 2026 arxiv project page code memo memory augmented model context optimization for robust multi turn multi agent llm games yunfei xie kevin wang bobby cheng jianzhu yao zhizhou sha alexander duffy yihan xi hongyuan mei cheston tan chen wei pramod viswanath zhangyang wang icml 2026 arxiv project page code play to generalize learning to reason through game play yunfei xie yinsong ma shiyi lan alan yuille junfei xiao chen wei iclr 2026 arxiv project page code pyvision rl forging open agentic vision models via rl shitian zhao shaoheng lin ming li haoquan zhang wenshuo peng kaipeng zhang chen wei icml 2026 arxiv project page code pyvision agentic vision with dynamic tooling shitian zhao haoquan zhang shaoheng lin ming li qilong wu kaipeng zhang chen wei neurips 2025 workshop on multi turn interactions in llms arxiv project page code perception encoder the best visual embeddings are not at the output of the network daniel bolya po yao huang peize sun jang hyun cho andrea madotto chen wei tengyu ma jiale zhi jathushan rajasegaran hanoona rasheed junke wang marco monteiro hu xu shiyu dong nikhila ravi daniel li piotr dollár christoph feichtenhofer neurips 2025 oral arxiv code meta ai blog genex generating an explorable world taiming lu tianmin shu junfei xiao luoxin ye jiahao wang cheng peng chen wei daniel khashabi rama chellappa alan yuille jieneng chen iclr 2025 arxiv genex world code de diffusion makes text a strong cross modal interface chen wei chenxi liu siyuan qiao zhishuai zhang alan yuille jiahui yu cvpr 2024 arxiv project page 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 arxiv project page press masked feature prediction for self supervised visual pre training chen wei haoqi fan saining xie chao yuan wu alan yuille christoph feichtenhofer cvpr 2022 arxiv code most influential cvpr 2023 papers ibot image bert pre training with online tokenizer jinghao zhou chen wei huiyu wang wei shen cihang xie alan yuille tao kong iclr 2022 arxiv code press improved and scaled up to dinov2 by meta ai 2026 chen wei last update may 2026