Meta tags:
author=Yiqing Liang;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
nbsp (76), and (27), 2025 (22), for (19), 2026 (13), scene (13), yiqing (13), liang (13), project (12), cvpr (11), paper (11), code (10), the (9), end (8), bibtex (8), monocular (8), research (8), 2023 (7), dynamic (7), reconstruction (7), james (7), tompkin (7), data (7), accepted (7), university (7), iccv (6), workshop (6), video (6), view (6), with (6), learning (5), models (5), visual (5), reasoning (5), that (5), from (5), benchmark (5), first (5), luma (5), computer (5), model (4), semantic (4), propose (4), present (4), time (4), flow (4), 2024 (4), training (4), estimation (4), tasks (4), bench (4), uni (4), internship (4), science (4), based (3), world (3), chen (3), graph (3), chang (3), wang (3), neural (3), method (3), real (3), gaussian (3), synthesis (3), zeromsf (3), foundation (3), oral (3), egocentric (3), scale (3), liu (3), llm (3), terminal (3), laser (3), unified (3), generation (3), selected (3), meta (3), reality (3), labs (3), dec (3), nvidia (3), nov (3), feb (3), talk (3), brown (3), was (3), scientist (3), professor (3), reviewing (2), wacv (2), icra (2), aaai (2), content (2), creation (2), using (2), confidence (2), aware (2), completion (2), navigation (2), shuran (2), song (2), enhanced (2), image (2), text (2), sgeitl (2), framework (2), commonsense (2), shih (2), you (2), saff (2), volume (2), attention (2), fields (2), self (2), supervised (2), implicit (2), isotropic (2), methods (2), efficient (2), gaufre (2), lei (2), xiao (2), douglas (2), lanman (2), numair (2), khan (2), novel (2), splatting (2), datasets (2), synthetic (2), tmlr (2), adam (2), harley (2), leonidas (2), guibas (2), mikaela (2), angelina (2), award (2), candidate (2), orazio (2), gallo (2), hang (2), abhishek (2), badki (2), comprehensive (2), geometric (2), core (2), depth (2), multi (2), zhiwen (2), fan (2), egotl (2), think (2), aloud (2), step (2), spatial (2), enabling (2), long (2), horizon (2), jiang (2), modomodo (2), multimodal (2), ding (2), hard (2), realistic (2), command (2), line (2), interfaces (2), capabilities (2), agents (2), iclr (2), free (2), streaming (2), layer (2), wise (2), understanding (2), jun (2), started (2), summer (2), team (2), got (2), presenting (2), work (2), necv (2), giving (2), apr (2), invited (2), may (2), news (2), eecs (2), phd (2), jan (2), received (2), advised (2), jon, barron, template, tpami, tvcj, journal, neurips, eccv, eurographics, iros, 3dv, conference, 1st, organizer, professional, service, 2021, explicitly, priors, module, complete, guide, agent, planning, boyuan, sscnav, 2022, incorporate, kai, wei, suji, park, alireza, zareian, liunian, harold, haoxuan, zhecan, casual, consists, varying, color, density, semantics, information, srinath, sridhar, alexander, meyerowitz, eliot, laidlaw, decomposition, reconstructing, volumes, anisotropic, microscopy, achieving, 1db, psnr, improvement, 000x, faster, inference, over, diffusion, miccai, medical, ema, hanspeter, pfister, markus, hadwiger, johann, danzl, mojtaba, tavakoli, johanna, beyer, jakob, troidl, niiv, interactive, cv4mr, deformable, gaussians, train, renders, separates, static, regions, thu, nguyen, phuoc, zhengqin, deformation, combining, existing, new, dataset, provide, standardized, comparisons, identify, key, factors, affecting, efficiency, quality, runfeng, mikhail, okunev, fast, brittle, complexity, rules, generalizable, understands, diverse, scenarios, utilizing, our, curated, recipe, samples, zero, shot, wild, under, review, covering, five, sparse, pose, spanning, both, standard, challenging, out, distribution, zhangyang, marco, pavone, boris, ivanovic, yan, ziyi, yang, yancheng, zhang, wenyan, cong, e3d, findings, track, introduces, capture, pipeline, records, goals, spoken, word, level, timestamps, metric, labels, human, aligned, supervision, manling, srinivas, shakkottai, zirui, xuhai, hezhen, hitesh, vijay, sicong, dayou, lulin, chains, introduce, systematic, post, rlvr, featuring, rigorous, mixture, problem, formulation, implementation, mmragl, jiacheng, zhu, laixi, shi, zhengzhong, mengzhou, xia, mengdi, zuxin, wenhao, jielin, qiu, domain, mixtures, reinforcement, provides, evaluate, mike, merrill, benchmarking, aligns, achieve, consistent, accurate, spatiotemporal, huaizu, pedro, miraldo, moitreya, chatterjee, yiming, xie, tianye, alignment, jointly, space, logic, single, architecture, tech, lead, manga, all, dsr, jul, recognized, hugging, face, daily, papers, lpr, lightning, nyc, vision, day, mar, presentation, harvard, computing, group, monodygaubench, see, hawaii, e2e3d, show, archived, rising, star, successfully, defended, thesis, gave, hosted, prof, youngjoon, kwon, emory, two, workshops, announced, intern, master, columbia, completed, bachelor, fudan, visiting, student, mit, csail, contributor, during, fortunate, collaborate, stanford, about, blog, twitter, linkedin, github, google, scholar, email,

Text of the page (random words):
yiqing liang yiqing liang research scientist luma ai ph d in computer science brown university email nbsp nbsp cv nbsp nbsp google scholar nbsp nbsp github nbsp nbsp linkedin nbsp nbsp twitter nbsp nbsp blog about i am a research scientist at luma ai and a core contributor to uni 1 i received my ph d in computer science from brown university advised by professor james tompkin during my phd i was fortunate to collaborate with adam harley mikaela angelina uy and leonidas guibas from stanford university i received my master in computer science from columbia university advised by professor shuran song and professor shih fu chang i completed my bachelor in computer science at fudan university and was a visiting student at mit eecs csail i was a research scientist intern at nvidia research with abhishek badki hang su and orazio gallo and at meta reality labs with numair khan lei xiao and douglas lanman news feb 2026 uni 1 luma s first unified understanding and generation model is announced feb 2026 laser is accepted to cvpr 2026 jan 2026 terminal bench is accepted to iclr 2026 jan 2026 two workshops accepted to cvpr 2026 4d world models and ai for content creation dec 2025 i gave an invited talk at emory university hosted by prof youngjoon kwon nov 2025 i successfully defended my phd thesis at brown university nov 2025 i am selected as an eecs rising star 2025 show archived news may 2025 the first end to end 3d learning e2e3d workshop is accepted to iccv 2025 see you in hawaii may 2025 monodygaubench got accepted to tmlr 2025 apr 2025 zeromsf is selected as cvpr 2025 award candidate 0 48 apr 2025 i am giving an invited talk at harvard visual computing group mar 2025 zeromsf is accepted to cvpr 2025 as an oral presentation feb 2025 i am giving a lightning talk at nyc computer vision day 2025 nov 2024 i am presenting my internship work with nvidia research at necv 2024 jun 2024 i started the summer internship at lpr team nvidia research dec 2023 my research is recognized in hugging face daily papers by ak dec 2023 i am presenting my internship work with meta reality labs at necv 2023 jul 2023 saff got accepted to iccv 2023 jun 2023 i started the summer internship at dsr team of meta reality labs selected research view all uni 1 luma s first unified understanding and generation model luma ai tech lead for manga 2026 project uni 1 jointly models time space and logic in a single architecture enabling unified reasoning and visual generation capabilities laser layer wise scale alignment for training free streaming 4d reconstruction tianye ding yiming xie yiqing liang moitreya chatterjee pedro miraldo huaizu jiang cvpr 2026 project nbsp nbsp paper nbsp nbsp code we propose laser a training free streaming 4d reconstruction method that aligns scale layer wise to achieve consistent and accurate spatiotemporal reconstruction from monocular video terminal bench benchmarking agents on hard realistic tasks in command line interfaces mike a merrill et al iclr 2026 project nbsp nbsp paper nbsp nbsp code terminal bench provides a comprehensive benchmark of hard realistic tasks in command line interfaces to evaluate the capabilities of llm based agents modomodo multi domain data mixtures for multimodal llm reinforcement learning yiqing liang jielin qiu wenhao ding zuxin liu james tompkin mengdi xu mengzhou xia zhengzhong tu laixi shi jiacheng zhu iccv 2025 workshop mmragl oral project nbsp nbsp paper nbsp nbsp data nbsp nbsp code nbsp nbsp bibtex we introduce modomodo a systematic post training framework for multimodal llm rlvr featuring a rigorous data mixture problem formulation and benchmark implementation egotl egocentric think aloud chains for long horizon tasks lulin liu dayou li yiqing liang sicong jiang hitesh vijay hezhen hu xuhai xu zirui liu srinivas shakkottai manling li zhiwen fan cvpr 2026 findings track project egotl introduces a think aloud capture pipeline for egocentric data that records step by step goals spoken reasoning with word level timestamps and metric scale spatial labels enabling human aligned supervision for long horizon egocentric spatial reasoning e3d bench a benchmark for end to end 3d geometric foundation models wenyan cong yiqing liang yancheng zhang ziyi yang yan wang boris ivanovic marco pavone chen chen zhangyang wang zhiwen fan under review 2025 project nbsp nbsp paper nbsp nbsp code nbsp nbsp bibtex we present the first comprehensive benchmark for 3d end to end 3d geometric foundation models covering five core tasks sparse view depth estimation video depth estimation 3d reconstruction multi view pose estimation novel view synthesis and spanning both standard and challenging out of distribution datasets zero shot monocular scene flow estimation in the wild yiqing liang abhishek badki hang su james tompkin orazio gallo cvpr 2025 oral award candidate 0 48 project nbsp nbsp paper nbsp nbsp video nbsp nbsp code nbsp nbsp bibtex we present zeromsf the first generalizable 3d foundation model that understands monocular scene flow for diverse real world scenarios utilizing our curated data recipe of 1m synthetic training samples monocular dynamic gaussian splatting is fast and brittle and scene complexity rules yiqing liang mikhail okunev mikaela angelina uy runfeng li leonidas j guibas james tompkin adam harley tmlr 2025 project nbsp nbsp paper nbsp nbsp data nbsp nbsp code nbsp nbsp bibtex we present a benchmark of dynamic gaussian splatting methods for monocular view synthesis combining existing datasets and a new synthetic dataset to provide standardized comparisons and identify key factors affecting efficiency and quality gaufre gaussian deformation fields for real time dynamic novel view synthesis yiqing liang numair khan zhengqin li thu nguyen phuoc douglas lanman james tompkin lei xiao cvpr 2024 cv4mr wacv 2025 project nbsp nbsp paper nbsp nbsp code nbsp nbsp bibtex we propose gaufre a dynamic scene reconstruction method using deformable 3d gaussians for monocular video that is efficient to train renders in real time and separates static and dynamic regions niiv interactive self supervised neural implicit isotropic volume reconstruction jakob troidl yiqing liang johanna beyer mojtaba tavakoli johann danzl markus hadwiger hanspeter pfister james tompkin miccai workshop on efficient medical ai ema 2025 project nbsp nbsp paper nbsp nbsp code we propose a self supervised neural implicit method for reconstructing isotropic 3d volumes from anisotropic microscopy data achieving 1db psnr improvement and 1 000x faster inference over diffusion based methods semantic attention flow fields for monocular dynamic scene decomposition yiqing liang eliot laidlaw alexander meyerowitz srinath sridhar james tompkin iccv 2023 project nbsp nbsp paper nbsp nbsp code nbsp nbsp bibtex we present saff a dynamic neural volume reconstruction of a casual monocular video that consists of time varying color density scene flow semantics and attention information sgeitl scene graph enhanced image text learning for visual commonsense reasoning zhecan wang haoxuan you liunian harold li alireza zareian suji park yiqing liang kai wei chang shih fu chang aaai 2022 paper nbsp nbsp bibtex we propose a scene graph enhanced image text learning sgeitl framework to incorporate visual scene graph in commonsense reasoning sscnav confidence aware semantic scene completion for visual semantic navigation yiqing liang boyuan chen shuran song icra 2021 project nbsp nbsp paper nbsp nbsp video nbsp nbsp code nbsp nbsp bibtex we explicitly model scene priors using a confidence aware semantic scene completion module to complete the scene and guide the agent s navigation planning professional service organizer 4d world models workshop cvpr 2026 ai for content creation workshop cvpr 2026 1st end to end 3d learning workshop iccv 2025 conference reviewing neurips cvpr eccv iccv eurographics wacv iros icra aaai 3dv journal reviewing tpami ra l tvcj based on jon barron s template