Meta tags:
author=Jinbo Xing;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
nbsp (162), video (45), and (35), arxiv (28), jinbo (28), xing (28), zhang (27), image (24), code (24), project (24), 2025 (21), liu (20), paper (18), generation (17), with (17), for (15), computer (14), the (14), chen (14), 2026 (13), diffusion (13), 2024 (12), wang (12), research (11), multi (11), tien (11), tsin (11), wong (11), xia (10), 2023 (9), menghan (9), models (9), shan (9), conference (8), siggraph (8), ieee (8), vision (8), motion (8), model (8), ying (8), transactions (7), 2021 (7), control (7), wan (7), demo (7), text (7), via (7), high (7), cvpr (6), journal (6), systems (6), controllable (6), method (6), yuechen (6), scale (6), based (6), can (6), colorization (6), given (6), xintao (6), yong (6), asia (5), pattern (5), 2022 (5), cuhk (5), present (5), synthesis (5), xiaodong (5), cun (5), hanyuan (5), haoxin (5), generate (5), framework (5), fidelity (5), creation (5), yang (5), training (5), modal (5), eccv (4), iclr (4), neurips (4), chi (4), international (4), multimedia (4), csci (4), unified (4), scholarship (4), intern (4), prof (4), data (4), huang (4), knowledge (4), interpolation (4), real (4), wenbo (4), images (4), processing (4), scene (4), view (4), novel (4), preprint (4), qifeng (4), yingqing (4), videos (4), open (4), subject (4), customization (4), may (3), iccv (3), intelligence (3), visual (3), fall (3), spring (3), workshop (3), generative (3), engineering (3), 2020 (3), science (3), 2018 (3), jul (3), mentor (3), lab (3), long (3), tongyi (3), task (3), using (3), aware (3), frame (3), world (3), arbitrary (3), stylized (3), reference (3), recognition (3), jiaya (3), jia (3), facial (3), prior (3), which (3), driven (3), semantic (3), xie (3), trained (3), yuan (3), neural (3), information (3), applications (3), editing (3), dynamic (3), your (3), quality (3), track (3), taming (3), large (3), oral (3), from (3), camera (3), enables (3), learning (3), feng (3), omni (3), todo (3), understanding (3), dot (3), design (2), legends (2), review (2), analysis (2), machine (2), tpami (2), visualization (2), graphics (2), tvcg (2), acm (2), academic (2), programming (2), introduction (2), 3280 (2), computational (2), organizer (2), 1st (2), higen (2), jun (2), oct (2), animation (2), 2019 (2), elite (2), stream (2), zhao (2), supervisor (2), helen (2), meng (2), scientist (2), mai (2), alibaba (2), work (2), zhou (2), unstructured (2), oriented (2), dialog (2), retrieval (2), flow (2), non (2), motions (2), invertible (2), downscaling (2), aidn (2), radiance (2), fields (2), discrete (2), more (2), chengze (2), minshan (2), pre (2), existing (2), clips (2), coherent (2), storytelling (2), chao (2), weng (2), our (2), its (2), approach (2), customized (2), inpainting (2), style (2), eric (2), magicstick (2), transformations (2), yue (2), consistent (2), yujiu (2), gongye (2), wangbo (2), domain (2), foundation (2), cartoon (2), technical (2), construction (2), dit (2), kai (2), generating (2), monocular (2), while (2), through (2), carving (2), progressive (2), bin (2), guo (2), yan (2), follow (2), representations (2), zeyu (2), zhu (2), han (2), are (2), that (2), wing (2), cinematic (2), shot (2), short (2), context (2), chaojie (2), mao (2), decoupled (2), interleaved (2), last, updated, web, page, credit, jon, barron, lover, league, apex, best, rank, diamond, keen, amateur, photographer, misc, ijcv, computing, surveys, csur, tmm, tvcj, circuits, technology, tcsvt, services, game, software, production, cmsc, 5727, problem, solving, engg, 1110, advanced, gpu, 5390, imaging, 3290, teaching, 2nd, huawei, feb, bfl, black, forest, labs, games, webinar, innovation, application, invited, talks, full, undergraduate, students, mainland, dean, list, faculty, 2016, student, distinguished, performance, msc, programme, postgraduate, studentship, awards, summer, electronic, dept, aug, assistant, stanley, big, decision, analytics, centre, tencent, jan, adobe, mar, experiences, mudit, chaudhary, borislav, dzodzo, sida, chun, hei, mingzhi, lyu, lun, yiu, nie, tianhua, xiaoying, jingyan, hong, cheng, wai, lam, all, authors, contribute, equally, propose, system, capable, accessing, poster, reading, aaai, artificial, program, dstc9, aaaiw, access, modeling, language, inference, integrative, response, address, complicated, linear, media, cvm, generic, network, natively, downscale, factors, meanwhile, could, restored, whenever, necessary, interactive, inspection, tip, stylization, utilizing, stylize, single, taken, xufeng, yao, zexin, ref, npr, photorealistic, minimize, over, smoothed, expression, learned, means, dramatic, expressive, accurate, lip, movements, achieved, jue, codetalker, speech, leaverages, rich, takes, another, level, improved, piggybacked, effective, adaptation, sing, leung, ai4va, utilize, abundance, synthesize, customizing, their, appearances, concepts, gong, animate, story, augmented, proposed, aligned, variants, compatible, transfer, etc, spotlight, rival, variation, aligning, inversion, chain, modify, properties, shape, size, location, leveraging, keyframe, extracted, internal, signals, cvf, winter, wacv, siran, chenyang, sen, liang, handle, description, structure, depth, temporally, include, life, rerendering, yuxin, make, textual, structural, guidance, sourced, foundational, yaofang, shaoshu, videocrafter1, styles, prompt, stylecrafter, enhancing, adapter, yonghong, tian, xiangjun, gao, zhipeng, xiaoyu, viewcrafter, european, dynamicrafter, animating, priors, selected, papers, trailer, tooncrafter, pipeline, alan, yuille, zhe, lin, xiaokang, yulun, tianyu, soo, kim, zhifei, yuqian, yiwei, yuanhao, cai, omnivcus, feedforward, multimodal, conditions, views, casually, captured, also, supporting, exact, pose, mark, trajectorycrafter, redirecting, trajectory, jenga, accelerates, hunyuanvideo, attention, resolution, pengfei, xin, tao, bohao, peng, shaoteng, free, efficient, token, canvas, uploaded, user, both, preceding, succeeding, states, drawing, process, maneesh, agrawala, yuwei, chuan, lvmin, past, future, digital, painting, processes, input, various, trajectories, edited, first, maintaining, consistency, ayden, yinhan, david, junhao, hongyu, xinhua, kunyu, empowering, diagnostic, benchmark, designed, evaluate, physical, realism, beyond, yihao, wenlong, qiao, hongsheng, shuo, cao, kaiwen, songhao, zhuo, yuandong, picabench, how, far, physically, realistic, precise, two, stage, paradigm, hongming, xihui, yike, yingya, ruihang, chu, yutong, rui, haonan, qiu, xiang, zhekai, hangjie, shiwei, xinyu, yujie, wei, dreamvideo, controlled, latent, identity, reinforcement, proceedings, object, aniruddha, mahapatra, jiahui, cusuh, ham, motioncanvas, agentic, minute, recursively, breaking, into, manageable, bohan, zhuang, gholamreza, haffari, zihan, weijie, yefei, akide, reca, extrapolation, recursive, allocation, unifed, strategy, perform, tasks, lianghua, tong, shen, chongyang, zhong, chenwei, keyu, jie, xiao, zhen, yulin, pan, jingfeng, xiaotang, gai, yuxiang, tuo, zeyinzi, jiang, weaver, works, core, contributors, architecture, report, wan2, commercial, linkedin, researchgate, github, google, scholar, email, please, reach, out, jinboxing, link, edu, team, actively, looking, interns, cutting, edge, topics, mllm, focusing, content, previously, received, class, honor, degrees, respectively, obtained, degree, supervised, engineer,

Text of the page (random words):
jinbo xing jinbo xing research scientist engineer alibaba tongyi lab wan i obtained my ph d degree in computer science and engineering from cuhk supervised by prof tien tsin wong and prof chi wing fu previously i received my b sc 1st class honor elite stream and m sc degrees in computer science at cuhk in 2020 and 2021 respectively i m focusing on video and multi modal content understanding generation tongyi wan team we are actively looking for research interns to work on cutting edge research topics video generation mllm please reach out to me at jinboxing at link dot cuhk dot edu dot hk email nbsp nbsp google scholar nbsp nbsp github nbsp nbsp researchgate nbsp nbsp linkedin nbsp nbsp x nbsp nbsp cv commercial applications wan2 7 image technical report wan 2 6 wan 2 5 core contributors of large scale data construction and foundation model architecture training research works wan weaver interleaved multi modal generation via decoupled training jinbo xing zeyinzi jiang yuxiang tuo chaojie mao xiaotang gai xi chen jingfeng zhang yulin pan zhen han jie xiao keyu yan chenwei xie chongyang zhong kai zhu tong shen lianghua huang yu liu yujiu yang computer vision and pattern recognition cvpr oral 2026 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code todo a unifed multi modal understanding and generation model trained with a decoupled training strategy which can perform interleaved multi modal generation and multi modal understanding tasks reca multi shot long video extrapolation via recursive context allocation akide liu jinbo xing chaojie mao ye li zeyu zhang yefei he weijie wang zihan wang yu liu gholamreza haffari bohan zhuang arxiv preprint 2026 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code todo a agentic framework that enables existing short video models to generate consistent multi minute cinematic videos by recursively breaking the task into manageable context aware short clips motioncanvas cinematic shot design with controllable image to video generation jinbo xing long mai cusuh ham jiahui huang aniruddha mahapatra chi wing fu tien tsin wong feng liu siggraph 2025 conference proceedings paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code a unified camera and object motion control framework for dit based image to video diffusion models dreamvideo omni omni motion controlled multi subject video customization with latent identity reinforcement learning yujie wei xinyu liu shiwei zhang hangjie yuan jinbo xing zhekai chen xiang wang haonan qiu rui zhao yutong feng ruihang chu yingya zhang yike guo xihui liu hongming shan arxiv preprint 2026 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code todo a unified video synthesis framework that enables precise multi subject customization and omni motion control via a progressive two stage training paradigm picabench how far are we from physically realistic image editing yuandong pu le zhuo songhao han jinbo xing kaiwen zhu shuo cao bin fu si liu hongsheng li yu qiao wenlong zhang xi chen yihao liu international conference on learning representations iclr 2026 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code a diagnostic benchmark designed to evaluate physical realism in image editing beyond semantic fidelity follow your creation empowering 4d creation through video inpainting yue ma kunyu feng xinhua zhang hongyu liu david junhao zhang jinbo xing yinhan zhang ayden yang zeyu wang qifeng chen international conference on learning representations iclr 2026 paper nbsp nbsp arxiv nbsp nbsp project given an input video follow your creation enables 4d video creation with various camera trajectories and edited first frame while maintaining multi view consistency generating past and future in digital painting processes lvmin zhang chuan yan yuwei guo jinbo xing maneesh agrawala siggraph 2025 journal track paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code given a canvas image uploaded by a user the framework can generate both preceding and succeeding states of the drawing process training free efficient video generation via dynamic token carving yuechen zhang jinbo xing bin xia shaoteng liu bohao peng xin tao pengfei wan eric lo jiaya jia neural information processing systems neurips 2025 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code jenga accelerates hunyuanvideo by 4 68 10 35 through dynamic attention carving and progressive resolution generation trajectorycrafter redirecting camera trajectory for monocular videos via diffusion models mark yu wenbo hu jinbo xing ying shan international conference on computer vision iccv oral 2025 arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code generating high fidelity novel views from casually captured monocular video while also supporting exact pose control omnivcus feedforward subject driven video customization with multimodal control conditions yuanhao cai he zhang xi chen jinbo xing kai zhang yiwei hu yuqian zhou zhifei zhang soo ye kim tianyu wang yulun zhang xiaokang yang zhe lin alan yuille neural information processing systems neurips 2025 arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code a data construction pipeline and a dit based method for controllable subject driven video customization tooncrafter generative cartoon interpolation jinbo xing hanyuan liu menghan xia yong zhang xintao wang ying shan tien tsin wong siggraph asia 2024 journal track selected in technical papers trailer paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code taming large scale video diffusion models for generative cartoon interpolation dynamicrafter animating open domain images with video diffusion priors jinbo xing menghan xia yong zhang haoxin chen wangbo yu hanyuan liu gongye liu xintao wang ying shan tien tsin wong european conference on computer vision eccv oral 2024 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code an open domain high quality image to video foundation model viewcrafter taming video diffusion models for high fidelity novel view synthesis wangbo yu jinbo xing li yuan wenbo hu xiaoyu li zhipeng huang xiangjun gao tien tsin wong ying shan yonghong tian ieee transactions on pattern analysis and machine intelligence tpami 2025 arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code taming large scale video diffusion models for high fidelity novel view synthesis stylecrafter enhancing stylized text to video generation with style adapter gongye liu menghan xia yong zhang haoxin chen jinbo xing xintao wang yujiu yang ying shan siggraph asia 2024 journal track paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp demo nbsp nbsp code given a stylized image as reference the model can generate images and videos with consistent styles based on text prompt videocrafter1 open diffusion models for high quality video generation haoxin chen menghan xia yingqing he yong zhang xiaodong cun shaoshu yang jinbo xing yaofang liu qifeng chen xintao wang chao weng ying shan arxiv preprint 2023 arxiv nbsp nbsp project nbsp nbsp code an open sourced foundational text to video and image to video diffusion model for high quality video generation make your video customized video generation using textual and structural guidance jinbo xing menghan xia yuxin liu yuechen zhang yong zhang yingqing he hanyuan liu haoxin chen xiaodong cun xintao wang ying shan tien tsin wong ieee transactions on visualization and computer graphics tvcg 2025 paper nbsp nbsp arxiv nbsp nbsp project nbsp nbsp code given text description and video structure depth our approach can generate temporally coherent and high fidelity videos its applications include dynamic 3d scene to video creation real life scene to video and video rerendering magicstick controllable video editing via control handle transformations yue ma xiaodong cun sen liang jinbo xing yingqing he chenyang qi siran chen qifeng chen ieee cvf winter conference on applications of computer vision wacv 2025 arxiv nbsp nbsp project nbsp nbsp code magicstick is a unified framework to modify video properties e g shape size location motion leveraging the keyframe transformations on the extracted internal control signals rival real world image variation by aligning diffusion inversion chain yuechen zhang jinbo xing eric lo jiaya jia neural information processing systems neurips spotlight 2023 arxiv nbsp nbsp project nbsp nbsp code given a real world image our proposed method can generate its semantic aligned variants the approach is compatible with customized image generation inpainting controllable image synthesis style transfer etc animate a story storytelling with retrieval augmented video generation yingqing he menghan xia haoxin chen xiaodong cun yuan gong jinbo xing yong zhang xintao wang chao weng ying shan qifeng chen ai4va eccv workshop 2024 arxiv nbsp nbsp project nbsp nbsp code we utilize the abundance of existing video clips and synthesize a coherent storytelling video by customizing their appearances with given visual concepts video colorization with pre trained text to image diffusion models hanyuan liu minshan xie jinbo xing chengze li chi sing leung tien tsin wong acm multimedia mm 2025 arxiv nbsp nbsp project nbsp nbsp code we present an effective video colorization method an adaptation of a pre trained text to image diffusion model for video colorization improved diffusion based image colorization via piggybacked models hanyuan liu jinbo xing minshan xie chengze li tien tsin wong arxiv preprint 2023 arxiv nbsp nbsp project nbsp nbsp code we present a novel image colorization method which leaverages the rich diffusion model prior it takes text based image colorization to another semantic level codetalker speech driven 3d facial animation with discrete motion prior jinbo xing menghan xia yuechen zhang xiaodong cun jue wang tien tsin wong computer vision and pattern recognition cvpr 2023 arxiv nbsp nbsp paper nbsp nbsp project nbsp nbsp demo nbsp nbsp code we minimize the over smoothed facial expression using a learned discrete motion prior which means more dramatic and expressive facial motions with more accurate lip movements can be achieved ref npr reference based non photorealistic radiance fields yuechen zhang zexin he jinbo xing xufeng yao jiaya jia computer vision and pattern recognition cvpr 2023 arxiv nbsp nbsp paper nbsp nbsp project nbsp nbsp video nbsp nbsp data nbsp nbsp code we present a controllable scene stylization method utilizing radiance fields to stylize a 3d scene with a single stylized 2d view taken as reference scale arbitrary invertible image downscaling jinbo xing wenbo hu menghan xia tien tsin wong ieee transactions on image processing tip 2023 paper nbsp nbsp project nbsp nbsp code nbsp nbsp interactive inspection we present a scale arbitrary invertible image downscaling network aidn to natively downscale hr images with arbitrary scale factors meanwhile the hr images could be restored with aidn whenever necessary flow aware synthesis a generic motion model for video frame interpolation jinbo xing wenbo hu yuechen zhang tien tsin wong computational visual media cvm 2021 paper we present a flow aware multi frame interpolation method to address the complicated non linear motions in the real world unstructured knowledge access in task oriented dialog modeling using language inference knowledge retrieval and knowledge integrative response generation mudit chaudhary borislav dzodzo sida huang chun hei lo mingzhi lyu lun yiu nie jinbo xing tianhua zhang xiaoying zhang jingyan zhou hong cheng wai lam helen meng all authors contribute equally aaai conference on artificial intelligence workshop program aaaiw dstc9 2021 arxiv nbsp nbsp paper nbsp nbsp code nbsp nbsp paper reading nbsp nbsp poster we propose a system capable of accessing unstructured knowledge for task oriented dialog work experiences alibaba tongyi lab wan research intern mentor yu liu mar 2025 oct 2025 adobe research research scientist intern mentor dr long mai jul 2024 jan 2025 tencent ai lab research intern mentor dr menghan xia jun 2022 jul 2024 stanley ho big data decision analytics research centre cuhk research assistant supervisor prof helen meng may 2020 aug 2021 electronic engineering dept cuhk summer research intern supervisor prof ni zhao may 2018 jul 2018 awards postgraduate studentship distinguished academic performance scholarship of msc programme elite stream student scholarship 2018 2019 computer science scholarship dean s list of faculty of engineering 2016 2019 2020 full scholarship for undergraduate students mainland invited talks oct 2025 innovation and application of generative image animation image to video at games webinar feb 2025 unified motion control for image to video generation at black forest labs bfl jun 2024 controllable video generation at huawei workshop organizer 2nd higen cvpr 2026 organizer 1st higen iccv 2025 teaching 2023 2024 spring computational imaging and vision csci 3290 2023 2024 fall advanced gpu programming csci 5390 2022 2023 spring introduction to multimedia systems csci 3280 2021 2022 spring introduction to multimedia systems csci 3280 2021 2022 fall problem solving by programming engg 1110 2021 2022 fall computer game software production cmsc 5727 academic services journal review ieee transactions on pattern analysis and machine intelligence tpami ieee transactions on visualization and computer graphics tvcg international journal of computer vision ijcv acm computing surveys csur ieee transactions on multimedia tmm the visual computer journal tvcj ieee transactions on circuits and systems for video technology tcsvt conference review eccv 2024 mm 2024 siggraph asia 2024 iclr 2025 cvpr 2025 siggraph 2025 iccv 2025 neurips 2025 siggraph asia 2025 iclr 2026 cvpr 2026 chi 2026 eg 2026 eccv 2026 siggraph asia 2026 misc i am a keen amateur photographer a lover of league of legends and apex legends best rank in diamond last updated may 2026 web page design credit to jon barron