Meta tags:
author=Boyang Zheng;

Headings (most frequently used words):

news, publications,

Text of the page (most frequently used words):
and (17), the (8), boyang (8), zheng (8), with (8), 2026 (7), representation (7), saining (7), xie (7), diffusion (6), paper (6), tong (6), website (5), code (5), low (5), level (5), rae (5), autoencoders (5), for (4), model (4), vision (4), tasks (4), data (4), generation (4), transformers (4), advised (4), also (3), 2024 (3), frozen (3), that (3), are (3), arxiv (3), language (3), image (3), shengbang (3), class (3), multimodal (3), internship (3), begins (3), now (3), intern (3), shanghai (3), research (3), nyu (3), honor (3), artists (2), adversarial (2), examples (2), latent (2), against (2), various (2), their (2), iclr (2), 2025 (2), improves (2), framework (2), mllms (2), chao (2), dong (2), large (2), encoder (2), shows (2), both (2), faster (2), convergence (2), text (2), ellis (2), brown (2), rob (2), fergus (2), yann (2), lecun (2), nanye (2), encoders (2), training (2), pretraining (2), how (2), visual (2), modeling (2), lab (2), doing (2), generative (2), models (2), new (2), from (2), jiao (2), university (2), degree (2), acm (2), phd (2), student (2), courant (2), tpu (2), representations (2), learning (2), this, modification, jon, barron, known, mist, method, craft, personlization, techniques, sdedit, lora, strongly, outperforming, existing, methods, aim, protecting, privacy, copyrighted, works, era, aigc, public, release, spotlight, xiaoyu, chumeng, liang, targeted, attack, protection, unauthorized, customization, careful, designed, let, llm, perform, without, any, multi, modal, prior, find, most, current, ability, blind, features, shijun, jinjin, lm4lv, aggregating, last, layers, repa, complementary, enabling, same, serve, target, achieving, state, art, results, imagenet, 256, eli, shechtman, richard, zhang, zongze, jaskirat, singh, improved, baselines, scales, scale, freeform, based, converge, generalize, better, than, flux, style, vaes, across, sizes, ziteng, wang, bingda, tang, jihan, yang, technical, report, project, page, scaling, utilize, pretrained, train, vit, decoders, top, space, achieves, strong, performance, fast, david, fan, john, nguyen, gaoyue, zhou, shengyi, qian, théophane, vallaeys, junlin, han, naila, murray, marjan, ghazvininejad, mike, lewis, nicolas, ballas, amir, bar, michael, rabbat, jakob, verbeek, luke, zettlemoyer, koustuv, sinha, systematic, study, unified, mixture, experts, showing, complements, enables, world, benefits, understanding, beyond, exploration, publications, 2023, mllm, possible, applications, visionx, site, july, see, you, york, graduated, computer, science, enrolled, blog, post, sharing, hard, earned, debugging, wisdom, lessons, two, years, academia, peter, summer, ami, labs, news, twitter, github, google, scholar, email, aims, understand, dynamics, high, dimensional, continuous, often, noisy, spaces, special, form, generated, neural, networks, particularly, interesting, specifically, attracted, make, predictions, types, these, them, efficiently, concretely, mainly, work, have, some, experience, currently, first, year, obtained, bachelor, bradley,

Text of the page (random words):
boyang bradley zheng boyang zheng i m currently a first year cs phd student at nyu courant advised by saining xie i obtained my bachelor degree at shanghai jiao tong university acm honor class my research aims to understand the dynamics of high dimensional continuous and often noisy data spaces representations as a special form of data generated by neural networks are particularly interesting to me i m specifically attracted to how to make predictions of various types on these representations and to model them efficiently concretely i mainly work on visual representation learning generative models and multimodal learning i also have some experience in low level vision and adversarial examples email google scholar github twitter news 2026 5 internship begins i m now a summer intern at ami labs 2026 1 new blog post with peter tong lessons from two years of tpu training in academia sharing hard earned tpu debugging wisdom 2026 1 enrolled as a phd student at nyu courant advised by saining xie 2025 6 graduated from shanghai jiao tong university with an honor degree in computer science acm honor class 2024 5 internship begins i m now an intern at nyu visionx lab advised by saining xie doing research on generative models and mllms i ll be on site at july see you in new york 2023 9 internship begins i m now an intern at shanghai ai lab advised by chao dong doing research on mllm and their possible applications on low level vision tasks publications beyond language modeling an exploration of multimodal pretraining shengbang tong david fan john nguyen ellis brown gaoyue zhou shengyi qian boyang zheng théophane vallaeys junlin han rob fergus naila murray marjan ghazvininejad mike lewis nicolas ballas amir bar michael rabbat jakob verbeek luke zettlemoyer koustuv sinha yann lecun saining xie arxiv 2026 website paper a systematic study of unified multimodal pretraining with representation autoencoders and mixture of experts showing how visual data complements language enables world modeling and benefits both understanding and generation diffusion transformers with representation autoencoders boyang zheng nanye ma shengbang tong saining xie iclr 2026 code website paper a class of autoencoders that utilize pretrained frozen representation encoders as encoders and train vit decoders on top training diffusion transformers in the latent space of rae achieves strong performance and fast convergence on image generation tasks scaling text to image diffusion transformers with representation autoencoders shengbang tong boyang zheng ziteng wang bingda tang nanye ma ellis brown jihan yang rob fergus yann lecun saining xie technical report 2026 code project page paper scales the rae framework to large scale freeform text to image generation and shows rae based diffusion transformers converge faster and generalize better than flux style vaes across model sizes improved baselines with representation autoencoders jaskirat singh boyang zheng zongze wu richard zhang eli shechtman saining xie arxiv 2026 code website paper improves rae by aggregating the last k encoder layers and shows that rae and repa are complementary enabling the same representation to serve as both encoder and target achieving state of the art results with faster convergence on imagenet 256 lm4lv a frozen large language model for low level vision tasks boyang zheng jinjin gu shijun li chao dong arxiv 2024 code paper a careful designed framework to let a frozen llm to perform low level vision tasks without any multi modal data or prior we also find that most current mllms 2024 5 with generation ability are blind to low level features targeted attack improves protection against unauthorized diffusion customization boyang zheng chumeng liang xiaoyu wu iclr 2025 spotlight code paper public release for artists also known as mist v2 a method to craft adversarial examples for latent diffusion model against various personlization techniques e g sdedit lora strongly outperforming existing methods we aim for protecting the privacy of artists and their copyrighted works in the era of aigc this website is a modification of jon barron s website