Meta tags:
description=CtrlGen Workshop at NeurIPS 2021 (December 13);

Headings (most frequently used words):

ctrlgen, and, workshop, controllable, generative, modeling, in, language, vision, at, neurips, 2021, december, 13, important, dates, description, call, for, papers, demonstrations,

Text of the page (most frequently used words):
and (35), the (18), 2021 (10), for (9), #language (9), workshop (8), #vision (7), generation (6), ctrlgen (6), from (5), image (5), that (5), december (5), this (4), generated (4), nlp (4), call (3), papers (3), communities (3), controllable (3), has (3), models (3), areas (3), disentanglement (3), important (3), machine (3), such (3), other (3), deadline (3), paper (3), generative (3), neurips (3), pages (2), our (2), demonstrations (2), researchers (2), challenges (2), explore (2), its (2), about (2), increased (2), interaction (2), including (2), may (2), enhanced (2), controllability (2), these (2), but (2), learning (2), human (2), like (2), texts (2), more (2), images (2), content (2), ability (2), into (2), are (2), demo (2), acceptance (2), notification (2), submission (2), november (2), october (2), recording (2), here (2), speakers (2), modeling (2), page, was, github, please, see, details, propose, bring, together, discuss, current, potential, directions, improve, quality, correctness, diversity, excitement, significantly, recently, thanks, advent, improvement, large, transformer, networks, gans, feel, opportune, time, hold, new, subject, hope, will, foster, discussion, across, range, structured, prediction, sprout, fruitful, cross, domain, relations, open, door, achieving, ambitious, goals, introduces, not, only, perspectives, ones, closely, pertain, whole, which, concurrently, witnessed, growing, body, work, relevant, domains, interpretability, robustness, representation, believe, progress, towards, realization, benefit, greatly, insights, over, past, few, years, there, been, interest, within, gpt, start, sound, fluid, natural, videos, gan, appear, realistic, began, focusing, qualitative, properties, control, style, structure, incorporate, information, external, sources, output, aims, extremely, make, useful, real, world, applications, creativity, entertainment, ethical, purposes, training, self, driving, vehicles, improving, conversational, agents, personal, assistants, effectively, interact, description, note, above, deadlines, all, 59pm, aoe, date, camera, ready, dates, contact, ctrlgenworkshop, gmail, com, now, publicly, available, starts, around, minutes, main, update, feb, 2022, took, place, virtually, aimed, manipulation, modalities, featured, exciting, lineup, live, panel, session, interactive, activities, networking, opportunities, monday, organizers, demos, accepted, panelists, schedule, home, skip,

Text of the page (random words):
ctrlgen controllable generative modeling in language and vision ctrlgen workshop at neurips 2021 december 13 skip to the content ctrlgen controllable generative modeling in language and vision ctrlgen workshop at neurips 2021 december 13 home schedule speakers and panelists accepted papers demos organizers ctrlgen is a neurips 2021 workshop that took place virtually on monday december 13 2021 here it aimed to explore disentanglement controllability and manipulation for the generative vision and language modalities we featured an exciting lineup of speakers a live qa and panel session interactive activities and networking opportunities update feb 2022 the recording of our workshop is now publicly available here it starts at around 35 minutes into the main recording contact ctrlgenworkshop gmail com important dates paper submission deadline october 3 2021 paper acceptance notification october 25 2021 paper camera ready deadline november 5 2021 demo submission deadline november 26 2021 demo acceptance notification december 3 2021 workshop date december 13 2021 note that the above deadlines are all 11 59pm aoe workshop description over the past few years there has been an increased interest in the areas of language and image generation within the ml nlp and vision communities as generated texts by models like gpt 3 start to sound more fluid and natural and generated images and videos by gan models appear more realistic researchers began focusing on qualitative properties of the generated content such as the ability to control its style and structure or incorporate information from external sources and other texts or images into the output such aims are extremely important to make language and image generation useful for human machine interaction and other real world applications including machine co creativity entertainment ethical purposes enhanced training for self driving vehicles and improving the ability of conversational agents and personal assistants to effectively interact achieving these ambitious but important goals introduces challenges not only from nlp and vision perspectives but ones that closely pertain to machine learning as a whole which has concurrently witnessed a growing body of work in relevant domains such as interpretability disentanglement robustness and representation learning we believe progress towards the realization of human like language and image generation may benefit greatly from insights in these and other ml areas in this workshop we propose to bring together researchers from the nlp vision and ml communities to discuss the current challenges and explore potential directions for controllable generation and improve its quality correctness and diversity as excitement about language and image generation has significantly increased recently thanks to the advent and improvement of large language models transformer networks and gans we feel this is the opportune time to hold a new workshop about this subject we hope ctrlgen will foster discussion and interaction across nlp vision and ml communities including areas that range from structured prediction to disentanglement and sprout fruitful cross domain relations that may open the door for enhanced controllability in language and image generation call for papers and demonstrations please see our call for papers and call for demonstrations pages for details this page was generated by github pages