Meta tags:
author=Junbo Li;
description=A simple, whitespace theme for academics. Based on [*folio](htt????/github.com/bogoli/-folio) design. ;
keywords=AI researcher;

Headings (most frequently used words):

junbo, li, news, selected, publications,

Text of the page (most frequently used words):
and (31), 2024 (17), junbo (13), wang (11), 2025 (11), with (9), pdf (9), neurips (9), 2023 (9), 2022 (8), accepted (8), 2026 (7), for (7), first (7), author (7), from (6), the (6), website (5), learning (5), llms (5), icml (5), turn (5), paper (5), glad (5), prof (5), reinforcement (4), eric (4), xing (4), language (4), liu (4), llm360 (4), ppo (4), agentic (4), sep (4), start (4), internship (4), amazon (4), eccv (3), zhang (3), vip (3), yang (3), score (3), matching (3), hongyi (3), fednar (3), iclr (3), qiang (3), training (3), sparse (3), subspace (3), variational (3), inference (3), tianhua (3), tao (3), code (3), track (3), web2code (3), hierarchical (3), asynchronous (3), local (3), sgd (3), preference (3), alignment (3), prior (3), informed (3), eacl (3), selected (3), student (3), our (3), crystalcoder (3), colm (3), may (3), research (3), oral (2), presentation (2), zhuoran (2), zhaoran (2), model (2), optimization (2), ruqi (2), networks (2), conference (2), modeling (2), zhengzhong (2), zhiqiang (2), shen (2), bowen (2), tan (2), llm (2), benchmarks (2), large (2), zhangyang (2), estimation (2), findings (2), publications (2), jul (2), visiting (2), featured (2), recent (2), spotlight (2), cpal (2), two (2), crystalchat (2), both (2), dec (2), jan (2), austin (2), aug (2), honored (2), fellowship (2), degree (2), computer (2), science (2), worked (2), year (2), mathematics (2), reasoning (2), current (2), copyright, powered, theme, hosted, photos, unsplash, github, pages, folio, jekyll, supp, cihang, xie, huan, unified, certified, detection, recovery, patch, attack, vision, transformers, nati, srebro, anmol, kabra, gene, exponential, family, based, via, chong, tian, qirong, ang, federated, normalized, annealing, regularization, qiu, zichen, miao, bayesian, neural, aurick, qiao, yuqi, suqi, sun, omkar, pangarkar, richard, fan, victor, miller, guowei, haonan, fajri, koto, liping, tang, nikhil, ranjan, xuguang, ren, roberto, iriondo, cun, mark, schulze, preslav, nakov, tim, baldwin, zhiting, yonghao, zhuang, willie, neiswanger, towards, fully, transparent, open, source, william, marshall, bhargav, kanakiya, joel, hestness, natalia, vassilieva, crystal, illuminating, abilities, datasets, sukmin, yun, haokun, lin, rusiru, thushara, mohammad, qazim, bhat, yongxin, zutao, jiang, mingkai, deng, jinhong, others, scale, webpage, dataset, evaluation, framework, multimodal, shashidhar, gandham, omar, baldonado, adithya, gangidi, pavan, balaji, aditya, akella, geon, woo, kim, halos, over, slow, geo, distributed, pipa, statistical, peng, zhou, rui, meng, meet, vadera, lihong, level, advantage, improved, multi, join, sailing, mbzuai, lab, jun, release, including, base, models, well, fine, tuned, versions, english, outperforms, llama, codellama, ambersafe, amberchat, amber, scratch, are, study, papers, rufus, years, funding, thank, you, fellow, snowflake, receive, graduate, dean, prestigious, point72, cubist, news, was, also, earned, master, santa, cruz, bachelor, 2021, during, undergraduate, high, school, studied, math, competitions, one, won, china, mathematical, olympiad, cmo, silver, medal, fudan, university, applied, probabilistic, machine, focuses, below, list, areas, denotes, contributions, red, search, coding, seeking, starting, fall, feel, free, reach, out, interested, second, fortunately, advised, recipient, phd, atlas, about, toggle, navigation,

Text of the page (random words):
junbo li toggle navigation about current publications junbo li i m a second year ph d student in computer science at ut austin fortunately co advised by prof atlas wang and prof qiang liu i am a recipient of amazon ai phd fellowship i m seeking a research internship in agentic llm rl starting from 2026 fall feel free to reach out if interested my current research focuses on agentic reasoning search coding llms and reinforcement learning below is a selected list of research areas i ve worked on red denotes first author contributions agentic reasoning llms and reinforcement learning turn ppo eacl 2026 prior informed preference alignment icml 2025 crystalcoder colm 2024 web2code neurips 2024 llm360 colm 2024 score matching for reinforcement learning neurips 2022 optimization and probabilistic machine learning hierarchical asynchronous local sgd icml 2025 sparse subspace variational inference iclr 2024 fednar neurips 2023 vip eccv 2022 i was a visiting student with prof eric xing from 2023 to 2024 and also with prof ruqi zhang in 2023 i earned my master s degree in computer science from uc santa cruz in 2023 and my bachelor s degree in mathematics and applied mathematics from fudan university in 2021 during my undergraduate i worked with prof zhaoran wang and zhuoran yang in high school i studied math competitions for one year and won a silver medal in the china mathematical olympiad cmo news may 26 2026 glad to start an internship at point72 cubist jan 04 2026 my first author paper turn ppo is accepted by eacl findings 2026 dec 16 2025 honored to receive the graduate dean s prestigious fellowship sep 22 2025 glad to start an internship at snowflake aug 15 2025 honored to be selected as an amazon ai ph d fellow with 2 years of funding thank you amazon may 12 2025 glad to start an internship at amazon rufus may 03 2025 two papers accepted by icml 2025 prior informed preference alignment first author and hierarchical asynchronous local sgd sep 26 2024 our web2code is accepted by neurips 2024 aug 24 2024 glad to start my ph d study at ut austin jul 10 2024 our llm360 and crystalcoder are accepted by colm 2024 jan 16 2024 my first author paper sparse subspace variational inference is accepted by iclr 2024 and is featured in the recent spotlight track at cpal 2025 dec 14 2023 we release llm360 including two 7b base models training from scratch amber and crystalcoder as well as the fine tuned versions amberchat ambersafe and crystalchat our crystalchat outperforms both llama 2 and codellama on both english and code benchmarks sep 21 2023 my first author paper fednar is accepted by neurips 2023 and is featured in the recent spotlight track at cpal 2024 jun 27 2023 glad to join sailing mbzuai lab as a visiting student sep 14 2022 my co first author paper score matching for rl is accepted by neurips 2022 as the oral presentation jul 08 2022 my first author paper vip is accepted by eccv 2022 selected publications turn ppo turn level advantage estimation with ppo for improved multi turn rl in agentic llms junbo li peng zhou rui meng meet p vadera lihong li and yang li eacl findings 2026 pdf pipa preference alignment as prior informed statistical estimation junbo li zhangyang wang and qiang liu icml 2025 pdf halos hierarchical asynchronous local sgd over slow networks for geo distributed large language model training geon woo kim junbo li shashidhar gandham omar baldonado adithya gangidi pavan balaji zhangyang wang and aditya akella icml 2025 web2code a large scale webpage to code dataset and evaluation framework for multimodal llms sukmin yun haokun lin rusiru thushara mohammad qazim bhat yongxin wang zutao jiang mingkai deng jinhong wang tianhua tao junbo li and others neurips datasets and benchmarks track 2024 pdf crystal illuminating llm abilities on language and code tianhua tao junbo li bowen tan hongyi wang william marshall bhargav m kanakiya joel hestness natalia vassilieva zhiqiang shen eric p xing and zhengzhong liu conference on language modeling 2024 pdf website llm360 towards fully transparent open source llms zhengzhong liu aurick qiao willie neiswanger hongyi wang bowen tan tianhua tao junbo li yuqi wang suqi sun omkar pangarkar richard fan yi gu victor miller yonghao zhuang guowei he haonan li fajri koto liping tang nikhil ranjan zhiqiang shen xuguang ren roberto iriondo cun mu zhiting hu mark schulze preslav nakov tim baldwin and eric p xing conference on language modeling 2024 pdf website training bayesian neural networks with sparse subspace variational inference junbo li zichen miao qiang qiu and ruqi zhang iclr 2024 pdf fednar federated optimization with normalized annealing regularization junbo li ang li chong tian qirong ho eric p xing and hongyi wang neurips 2023 pdf website exponential family model based reinforcement learning via score matching gene li junbo li anmol kabra nati srebro zhaoran wang and zhuoran yang neurips oral presentation 2022 pdf website vip unified certified detection and recovery for patch attack with vision transformers junbo li huan zhang and cihang xie eccv 2022 pdf supp website copyright 2026 junbo li powered by jekyll with al folio theme hosted by github pages photos from unsplash