Meta tags:
description=personal website;

Headings (most frequently used words):

research, interest, selected, publications, previously,

Text of the page (most frequently used words):
liu (31), and (30), shengchao (26), for (23), arxiv (20), code (19), paper (19), project (14), page (14), workshop (12), hongyu (12), guo (12), neurips (11), tang (10), learning (10), jian (9), 2023 (9), with (9), iclr (9), the (9), representation (8), weitao (8), dynamics (8), prof (7), wang (7), model (7), generative (7), science (7), 2025 (6), oral (6), multi (6), 2022 (6), molecular (6), research (5), intelligence (5), graph (5), icml (5), deep (5), molecule (5), modeling (5), anima (5), anandkumar (5), design (5), this (4), yingyu (4), liang (4), christian (4), borgs (4), jennifer (4), chayes (4), task (4), training (4), weiyang (4), pretraining (4), geometric (4), yanjing (4), zhuoxinran (4), models (4), 2024 (4), nature (4), physics (4), dimitris (3), anthony (3), gitter (3), university (3), 2020 (3), molecules (3), 2019 (3), zhiming (3), materials (3), are (3), chengpeng (3), jiarui (3), weili (3), nie (3), text (3), chaowei (3), xiao (3), protein (3), using (3), flow (3), 2026 (3), interest (3), you (3), but (3), ideas (3), not (3), paradigms (3), shengchao1224 (2), gmail (2), com (2), advisors (2), papailiopoulos (2), 2018 (2), artificial (2), postdoc (2), unsupervised (2), applications (2), spotlight (2), mehmet (2), demirel (2), gram (2), transfer (2), neural (2), tmlr (2), aware (2), structured (2), ai4science (2), 2021 (2), zhang (2), ebm (2), geometry (2), hanchen (2), denoising (2), matching (2), group (2), symmetric (2), differential (2), equation (2), modal (2), diffusion (2), inspired (2), preparation (2), proteins (2), discovery (2), when (2), glfrontiers (2), structure (2), based (2), editing (2), retrieval (2), machine (2), ling (2), conversational (2), biology (2), drug (2), divin (2), yan (2), inertial (2), frames (2), hong (2), yuhao (2), capability (2), from (2), free (2), genai (2), foundations (2), latent (2), space (2), optimization (2), self (2), please (2), follow (2), two (2), lab (2), engineering (2), good (2), students (2), who (2), scientific (2), unless, otherwise, noted, site, licensed, under, creative, commons, attribution, sharealike, international, license, personal, website, shengchao_liu, chao1224, intern, facebook, iqvia, servicenow, nvidia, wisconsin, madison, 2015, advisor, université, montréal, quebec, institute, mila, california, berkeley, previously, simple, graphs, mlmm, furkan, bad, global, minima, exist, sgd, can, reach, them, phenomena, video, achlioptas, loss, balanced, weighting, reduce, negative, appendix, aaai, student, abstract, lbtw, attentive, walk, aggregating, networks, siddhant, garg, zhenmei, shi, property, prediction, aistats, meng, zuobai, huiyu, cai, sgnn, pre, gtrl, ssl, joan, lasenby, graphmvp, invariant, distance, geossl, stochastic, moleculesde, joint, auto, encoding, trajectory, jiujiu, chen, xuecang, moleculejae, quantum, network, spatea, symmetry, informed, crystalline, datasets, benchmarks, zhiling, zheng, chenru, duan, omar, yaghi, geom3d, steerable, factors, entangled, zuoxinran, bolei, zhou, graphcg, zhuoran, qiao, moleculestm, guided, framework, yutao, zhu, zhao, arvind, ramanathan, proteindt, large, language, pathway, detection, first, version, chatpathway, chatgpt, powered, domain, feedback, syns, jiongxiao, yijin, yang, chatdrug, manifold, constrained, nucleus, level, proceedings, national, academy, sciences, pnas, caltech, news, nucleusdiff, rigid, assembly, yoshua, bengio, assembleflow, grained, ligand, binding, communications, ai4differentialequations, hannan, vignesh, bhethanabotla, neuralmd, along, amplitude, shuning, chang, jiasheng, rong, fan, rigidssl, rigidity, conformational, ensembles, biorxiv, zhanghan, zeju, qiu, bernhard, schölkopf, inertialar, autoregressive, generation, haorui, yuqiang, minimal, collapse, frustration, stop, gradient, louie, yao, distinguishing, elicitation, creation, post, energy, perspective, multitask, pretrain, repr, interp, optim, likelihood, physai, selected, publications, world, physical, classical, initio, inverse, small, crystal, genomics, interpolation, semantics, reasoning, architecture, llm, controllable, conditional, supervised, interested, don, know, where, start, refer, reading, list, tutorial, there, need, email, apply, simply, fill, out, will, within, weeks, thank, your, form, have, posts, introducing, our, feel, take, look, xiaohongshu, rednote, zhihu, solid, math, communication, skills, necessary, always, looking, motivated, phd, ras, visitors, interns, due, high, volume, emails, apologize, haven, been, able, reply, individually, prospective, special, thanks, following, reflections, randy, pausch, last, lecture, think, like, amateur, expert, quick, more, important, people, wish, analyze, without, mathematics, must, settle, reduced, understanding, richard, feynman, life, surprisingly, short, solve, problems, that, excite, most, become, stronger, shared, discussed, criticized, owned, come, debts, those, came, before, curiosity, passion, trends, focus, creating, novel, publishing, papers, 科研的核心秘诀在于提出正确的问题, 如果一个问题过于困难, 也许并不是我们能力不够, 而是问题本身还没有被问对, 科研的意义, 不在于起点, 而在于终点, want, share, some, inspiring, values, highlights, dot, mail, tenure, track, assistant, professor, principal, investigator, lies, intersection, main, focuses, developing, methods, accelerate, existing, well, leveraging, enable, new, chemistry, geoscience, principles, understand, characterize, internal, mechanisms, including, emerging, representations, phase, transitions, wave, computer, chinese, kong, experiences, talks, teaching,

Text of the page (random words):
shengchao liu shengchao liu research group teaching talks experiences i am a tenure track assistant professor in computer science and engineering at the chinese university of hong kong and the principal investigator of the wave intelligence lab my research lies at the intersection of artificial intelligence and physics with two main focuses 1 developing physics inspired ai methods to accelerate existing scientific paradigms as well as leveraging generative models to enable new paradigms of scientific discovery with applications in chemistry materials science biology and geoscience and 2 using principles from physics to understand and characterize the internal mechanisms of ai models including emerging paradigms of generative modeling latent space representations and phase transitions in optimization and training dynamics e mail shengchao1224 at gmail dot com highlights i want to share some inspiring research values 科研的意义 不在于起点 而在于终点 科研的核心秘诀在于提出正确的问题 如果一个问题过于困难 也许并不是我们能力不够 而是问题本身还没有被问对 special thanks to weiyang for the following reflections focus on creating novel ideas not publishing papers follow curiosity and passion not trends ideas are not owned but come with debts to those who came before ideas become stronger when shared discussed and criticized life is surprisingly short so solve problems that interest and excite you most people who wish to analyze nature without using mathematics must settle for a reduced understanding richard p feynman it is good to be quick but it is more important to be deep think like an amateur do as an expert last lecture by prof randy pausch for prospective students due to the high volume of emails i apologize if i haven t been able to reply individually i am always looking for self motivated phd students postdoc and ras visitors interns solid math engineering and good communication skills are necessary we have posts introducing our lab on zhihu and xiaohongshu rednote please feel free to take a look there is no need to email me to apply simply fill out this form and i will follow up within two weeks thank you for your interest if you re interested in ai but don t know where to start please refer to this tutorial and this reading list research interest foundations representation learning structured geometric graph representation learning transfer learning self supervised learning multi task learning science for ai deep generative modeling genai llm ebm controllable conditional generative modeling learning dynamics optimization training dynamics architecture design latent space interpolation representation semantics reasoning ai for science molecule representation and inverse design small molecules proteins crystal materials genomics physical dynamics classical molecular dynamics ab initio molecular dynamics world model selected publications ai for science ️ physics for ai foundations genai for science ️ physai for science likelihood optim interp repr pretrain multitask on distinguishing capability elicitation from capability creation in post training a free energy perspective yuhao li shengchao liu arxiv project page a minimal model of representation collapse frustration stop gradient and dynamics louie hong yao yuhao li shengchao liu arxiv project page inertialar autoregressive 3d molecule generation with inertial frames haorui li weitao du yuqiang li hongyu guo shengchao liu icml 2026 arxiv project page code rigidssl rigidity aware geometric pretraining for protein design and conformational ensembles zhanghan ni yanjing li zeju qiu bernhard schölkopf hongyu guo weiyang liu shengchao liu iclr 2026 paper arxiv project page biorxiv code k flow flow along the k amplitude for generative modeling weitao du shuning chang jiasheng tang yu rong fan wang shengchao liu iclr 2026 paper arxiv code iclr deep generative model workshop 2025 oral neuralmd a multi grained symmetric differential equation model for learning protein ligand binding dynamics shengchao liu weitao du hannan xu yanjing li zhuoxinran li vignesh bhethanabotla divin yan christian borgs anima anandkumar hongyu guo jennifer chayes nature communications 2025 paper arxiv project page code iclr ai4differentialequations workshop 2024 oral assembleflow rigid flow matching with inertial frames for molecular assembly hongyu guo yoshua bengio shengchao liu iclr 2025 paper code nucleusdiff manifold constrained nucleus level denoising diffusion model for structure based drug design shengchao liu divin yan weitao du weiyang liu zhuoxinran li hongyu guo christian borgs jennifer chayes anima anandkumar proceedings of the national academy of sciences pnas 2025 paper arxiv project page icml gram workshop 2024 caltech news chatdrug chatgpt powered conversational drug editing using retrieval and domain feedback shengchao liu jiongxiao wang yijin yang chengpeng wang ling liu hongyu guo chaowei xiao iclr 2024 paper arxiv project page code icml syns and ml workshop 2023 oral chatpathway conversational large language models for biology pathway detection in preparation first version in neurips glfrontiers workshop 2023 oral proteindt a text guided protein design framework shengchao liu yanjing li zhuoxinran li anthony gitter yutao zhu jiarui lu zhao xu weili nie arvind ramanathan chaowei xiao jian tang hongyu guo anima anandkumar nature machine intelligence 2025 paper arxiv project page code moleculestm multi modal molecule structure text model for text based editing and retrieval shengchao liu weili nie chengpeng wang jiarui lu zhuoran qiao ling liu jian tang chaowei xiao anima anandkumar nature machine intelligence 2023 paper arxiv project page code neurips ai4science workshop 2022 graphcg unsupervised discovery of steerable factors when graph deep generative models are entangled shengchao liu chengpeng wang jiarui lu weili nie hanchen wang zuoxinran li bolei zhou jian tang tmlr 2024 paper arxiv project page code neurips glfrontiers workshop 2022 oral geom3d symmetry informed geometric representation for molecules proteins and crystalline materials shengchao liu weitao du yanjing li zhuoxinran li zhiling zheng chenru duan zhiming ma omar yaghi anima anandkumar christian borgs jennifer chayes hongyu guo jian tang neurips datasets and benchmarks 2023 paper arxiv code spatea a quantum inspired neural network for geometric modeling weitao du shengchao liu hongyu guo in preparation arxiv moleculejae molecule joint auto encoding trajectory pretraining with 2d and 3d diffusion weitao du jiujiu chen xuecang zhang zhiming ma shengchao liu neurips 2023 paper arxiv code moleculesde a group symmetric stochastic differential equation model for molecule multi modal pretraining shengchao liu weitao du zhiming ma hongyu guo jian tang icml 2023 paper arxiv project page code geossl molecular geometry pretraining with se 3 invariant denoising distance matching shengchao liu hongyu guo jian tang iclr 2023 paper arxiv project page code graphmvp pre training molecular graph representation with 3d geometry shengchao liu hanchen wang weiyang liu joan lasenby hongyu guo jian tang iclr 2022 paper arxiv project page code neurips ssl workshop 2021 iclr gtrl workshop 2022 spotlight sgnn ebm structured multi task learning for molecular property prediction shengchao liu meng qu zuobai zhang huiyu cai jian tang aistats 2022 paper arxiv project page code neurips ai4science workshop 2021 aware attentive walk aggregating graph neural networks mehmet f demirel shengchao liu siddhant garg zhenmei shi yingyu liang tmlr 2022 paper arxiv code lbtw loss balanced task weighting to reduce negative transfer in multi task learning shengchao liu yingyu liang anthony gitter aaai student abstract 2019 paper appendix code bad global minima exist and sgd can reach them shengchao liu dimitris papailiopoulos dimitris achlioptas neurips 2020 paper code video neurips 2020 icml deep learning phenomena workshop 2019 oral n gram graph simple unsupervised representation for graphs with applications to molecules shengchao liu mehmet furkan demirel yingyu liang neurips 2019 spotlight paper arxiv code neurips mlmm workshop 2018 previously 2023 2025 postdoc university of california berkeley advisors prof jennifer chayes and prof christian borgs 2020 2023 ph d quebec artificial intelligence institute mila and université de montréal advisor prof jian tang 2015 2018 m s university of wisconsin madison advisors prof anthony gitter prof yingyu liang and prof dimitris papailiopoulos research intern at facebook iqvia servicenow ai and nvidia shengchao liu shengchao1224 at gmail com chao1224 shengchao_liu personal website unless otherwise noted this site is licensed under a creative commons attribution sharealike 4 0 international license