Meta tags:
Headings (most frequently used words):
about, me, education, news, publications, services, teaching, selected, honors, and, awards, miscellaneous, yuxian, gu,
Text of the page (most frequently used words):
#yuxian (22), code (20), pdf (18), tsinghua (16), pre (16), and (15), huang (15), for (14), minlie (14), the (13), university (13), han (13), training (11), language (10), models (10), liu (10), 2021 (9), 2022 (9), 2024 (9), 2025 (9), dong (9), scholarship (8), wei (8), sun (7), furu (7), large (7), zhang (7), zhu (7), paper (7), 2023 (6), emnlp (6), hao (6), knowledge (6), zhiyuan (6), science (5), research (5), learning (5), xiaoyan (5), model (5), huggingface (5), jianqiu (4), beijing (4), dept (4), cst (4), student (4), department (4), computer (4), spring (4), fall (4), wang (4), distillation (4), zhengyan (4), pei (4), trained (4), open (4), song (4), with (4), main (4), long (4), data (4), comprehensive (3), asia (3), 2019 (3), technology (3), 2020 (3), best (3), graduates (3), acl (3), yaru (3), cheng (3), arxiv (3), zhou (3), zheng (3), chen (3), wentao (3), jie (3), maosong (3), scale (3), train (3), yuan (3), yao (3), yang (3), shot (3), task (3), oral (3), iclr (3), jet (3), nemotron (3), efficient (3), github (2), follow (2), captain (2), team (2), was (2), youth (2), national (2), supercomputer (2), challenge (2), outstanding (2), undergraduate (2), graduate (2), phd (2), honor (2), top (2), selected (2), honors (2), awards (2), oriented (2), neural (2), teaching (2), conference (2), neurips (2), context (2), preprint (2), qingxiu (2), optimal (2), qin (2), jian (2), guan (2), fanchao (2), xiaozhi (2), guoyang (2), zeng (2), shengqi (2), daixuan (2), zhenbo (2), tang (2), juanzi (2), cpm (2), chinese (2), inference (2), fine (2), tune (2), xiao (2), qiu (2), wen (2), xin (2), present (2), cai (2), lei (2), papers (2), few (2), short (2), junyu (2), instruction (2), minillm (2), slides (2), miniplm (2), selection (2), publications (2), education (2), mentored (2), prof (2), design (2), novel (2), architectures (2), this (2), llms (2), work (2), about (2), 2026, powered, fork, minimal, mistakes, academicpages, jekyll, feed, sitemap, like, play, competitive, sport, similar, volleyball, once, won, competition, represented, olympic, games, championship, jianzi, miscellaneous, 2018, silver, prize, community, innovation, excellence, dissertation, excellent, ant, tech, apple, scholars, aiml, fellowship, zhongshimo, 清华大学计算机系钟士模奖学金, grade, 清华大学研究生特等奖学金, object, programming, artificial, network, following, courses, program, committee, member, reviewer, arr, services, yutao, zhixiong, structured, prompting, scaling, 000, examples, yixing, dequan, direct, preference, towards, preprints, deming, yujia, yusheng, haozhe, yanan, huanqi, cao, generative, ning, ding, yuqi, huo, jiezhong, liang, jin, yanyan, lan, zhiwu, xipeng, ruihua, rong, jinhui, wayne, zhao, jun, past, future, chaojun, yanzheng, zhixing, tan, cost, effective, jiaxin, chujie, jianzhu, eva2, investigating, domain, dialogue, systems, machine, intelligence, journal, hou, adapting, meta, graph, information, multi, hop, reasoning, over, relations, evil, selective, masking, guided, lingxiao, luo, bing, peng, when, does, further, mlm, help, empirical, study, dialog, workshop, shaohan, are, supervised, multitask, learners, ppt, prompt, tuning, instructions, unlabeled, zero, cross, generalization, learn, fandong, meng, hongning, via, control, qinghao, shang, haocheng, post, architecture, search, demo, website, new, released, technical, report, news, 2017, eng, have, been, fortunate, collaborate, leading, researchers, during, time, intern, microsoft, visiting, mit, lab, explore, that, improve, performance, while, reducing, computational, costs, such, techniques, distill, from, into, smaller, more, accessible, ones, key, contributions, area, include, compression, develop, theories, algorithms, optimize, powerful, demonstrated, law, pds, curation, recently, tackles, through, three, primary, thrusts, final, year, candidate, advised, dedicated, enhancing, efficiency, across, their, entire, lifecycle, encompassing, downstream, adaptation, conversational, coai, group, google, scholar, email, china,
Text of the page (random words):
about me yuxian gu yuxian gu education publications teaching selected honors and awards cv yuxian gu phd student at tsinghua university follow beijing china email github google scholar about me i am a final year ph d candidate in the conversational ai coai group at tsinghua university advised by prof minlie huang my research is dedicated to enhancing the efficiency of large language models llms across their entire lifecycle encompassing pre training downstream adaptation and inference recently my work tackles this challenge through three primary research thrusts data curation for pre training i develop theories and algorithms to optimize data selection for training powerful and efficient llms as demonstrated in my work on pds instruction pre training and learning law knowledge distillation for model compression i design novel techniques to distill knowledge from large models into smaller more accessible ones my key contributions in this area include minillm and miniplm efficient model architectures i explore and design novel architectures that improve model performance while reducing computational costs such as jet nemotron i have been fortunate to collaborate with leading researchers during my time as an intern at microsoft research asia mentored by dr li dong and as a visiting student at mit han lab mentored by prof song han education 2021 9 present ph d student department of computer science and technology tsinghua university 2017 9 2021 6 b eng department of computer science and technology tsinghua university news new 2025 8 22 we released the jet nemotron technical report on arxiv publications conference papers yuxian gu qinghao hu shang yang haocheng xi junyu chen song han han cai jet nemotron efficient language model with post neural architecture search neurips 2025 pdf code website huggingface demo yuxian gu li dong hongning wang yaru hao qingxiu dong minlie huang furu wei data selection via optimal control for language models iclr 2025 oral top 1 8 pdf code huggingface slides yuxian gu hao zhou fandong meng jie zhou minlie huang miniplm knowledge distillation for pre training language models iclr 2025 pdf code huggingface yuxian gu li dong furu wei minlie huang minillm knowledge distillation of large language models iclr 2024 pdf code huggingface slides yuxian gu li dong furu wei minlie huang pre training to learn in context acl 2023 main long paper oral pdf code yuxian gu pei ke xiaoyan zhu minlie huang learning instructions with unlabeled data for zero shot cross task generalization emnlp 2022 main long paper oral pdf code yuxian gu xu han zhiyuan liu minlie huang ppt pre trained prompt tuning for few shot learning acl 2022 main long paper pdf code daixuan cheng yuxian gu shaohan huang junyu bi minlie huang furu wei instruction pre training language models are supervised multitask learners emnlp 2024 main long paper pdf code huggingface qi zhu yuxian gu lingxiao luo bing li cheng li wei peng minlie huang xiaoyan zhu when does further pre training mlm help an empirical study on task oriented dialog pre training emnlp 2021 workshop best paper pdf code yuxian gu zhengyan zhang xiaozhi wang zhiyuan liu maosong sun train no evil selective masking for task guided pre training emnlp 2020 short paper pdf code xin lv yuxian gu xu han lei hou juanzi li zhiyuan liu adapting meta knowledge graph information for multi hop reasoning over few shot relations emnlp 2019 short paper pdf code journal papers yuxian gu jiaxin wen hao sun yi song pei ke chujie zheng zheng zhang jianzhu yao lei liu xiaoyan zhu minlie huang eva2 0 investigating open domain chinese dialogue systems with large scale pre training 2022 machine intelligence research pdf code zhengyan zhang yuxian gu xu han shengqi chen chaojun xiao zhenbo sun yuan yao fanchao qi jian guan pei ke yanzheng cai guoyang zeng zhixing tan zhiyuan liu minlie huang wentao han yang liu xiaoyan zhu maosong sun cpm 2 large scale cost effective pre trained language models 2022 ai open pdf pre train code fine tune code xu han zhengyan zhang ning ding yuxian gu xiao liu yuqi huo jiezhong qiu yuan yao ao zhang liang zhang wentao han minlie huang qin jin yanyan lan yang liu zhiyuan liu zhiwu lu xipeng qiu ruihua song jie tang ji rong wen jinhui yuan wayne xin zhao jun zhu pre trained models past present and future 2022 ai open pdf zhengyan zhang xu han hao zhou pei ke yuxian gu deming ye yujia qin yusheng su haozhe ji jian guan fanchao qi xiaozhi wang yanan zheng guoyang zeng huanqi cao shengqi chen daixuan li zhenbo sun zhiyuan liu minlie huang wentao han jie tang juanzi li xiaoyan zhu maosong sun cpm a large scale generative chinese pre trained language model 2021 ai open pdf pre train code fine tune code inference code preprints yuxian gu li dong yaru hao qingxiu dong minlie huang furu wei towards optimal learning of language models arxiv preprint 2024 pdf code yixing li yuxian gu li dong dequan wang yu cheng furu wei direct preference knowledge distillation for large language models arxiv preprint 2024 pdf code yaru hao yutao sun li dong zhixiong han yuxian gu furu wei structured prompting scaling in context learning to 1 000 examples pdf code services program committee member conference reviewer emnlp 2022 2023 acl 2023 2024 arr 2023 2024 neurips 2024 teaching i was a ta for the following undergraduate courses artificial neural network 2020 fall 2021 fall 2022 fall 2023 fall object oriented programming 2021 spring 2022 spring 2023 spring 2024 spring selected honors and awards tsinghua top grade scholarship for graduates 清华大学研究生特等奖学金 2025 the best honor for graduates in tsinghua zhongshimo scholarship the department of computer science tsinghua university 清华大学计算机系钟士模奖学金 2025 the best honor for graduates in the department of computer science tsinghua university apple scholars in aiml phd fellowship 2025 ant research in tech scholarship 2025 national scholarship 2025 comprehensive scholarship tsinghua university 2022 2024 excellent graduate tsinghua university 2021 outstanding graduate dept cst tsinghua university 2021 outstanding undergraduate dissertation tsinghua university 2021 comprehensive scholarship dept cst tsinghua university 2020 science and technology innovation excellence scholarship dept cst tsinghua university 2019 silver prize asia student supercomputer challenge asia supercomputer community 2019 comprehensive scholarship dept cst tsinghua university 2018 miscellaneous i like to play jianzi jianqiu a competitive sport similar to volleyball i am the captain of tsinghua jianqiu team and was the captain of the beijing youth jianqiu team i once won the championship of the jianqiu competition in beijing and represented beijing in national youth olympic games sitemap follow github feed 2026 yuxian gu powered by jekyll academicpages a fork of minimal mistakes
|