Meta tags:
description=;

Headings (most frequently used words):

et, al, chowdhery, learning, of, 2023, machine, language, and, models, scaling, with, on, in, gemini, multimodal, arxiv, palm, pathways, journal, research, jmlr, wei, international, conference, large, neurips, 2021, proceedings, systems, mlsys, outstanding, paper, award, for, lu, kandula, acm, aakanksha, selected, publications, team, family, highly, capable, preprint, 2312, 11805, dec, narang, devlin, modeling, chung, hou, instruction, finetuned, 2024, driess, xia, florence, an, embodied, model, icml, singhal, azizi, encode, clinical, knowledge, nature, 620, 172, 180, wang, self, consistency, improves, chain, thought, reasoning, representations, iclr, jaszczur, mohiuddin, kaiser, gajewski, michalewski, kanerva, sparse, is, enough, transformers, hazimeh, zhao, sathiamoorthy, dselect, differentiable, selection, the, mixture, experts, applications, to, multi, task, pope, douglas, efficiently, transformer, inference, barham, dean, ghemawat, hand, hurt, isard, lim, pang, roy, sepassi, asynchronous, distributed, dataflow, ml, 2022, chaudhuri, accelerating, queries, probabilistic, predicates, sigmod, 2018, optasia, relational, platform, efficient, scale, video, analytics, symposium, cloud, computing, socc, santa, clara, ca, 2016, recent, talks,

Text of the page (most frequently used words):
and (15), 2023 (13), pdf (12), #chowdhery (11), learning (10), #machine (8), the (8), scaling (7), language (7), models (6), award (6), research (5), talks (5), palm (5), for (5), mlsys (5), outstanding (5), large (4), neurips (4), stanford (4), gemini (4), systems (4), paper (4), publications (4), was (4), aakanksha (4), menu (4), keynote (3), 2024 (3), 2022 (3), multimodal (3), with (3), pathways (3), self (3), lead (3), google (3), about (3), talk (2), speaker (2), scientific (2), computing (2), iclr (2), icml (2), reasoning (2), kandula (2), acm (2), distributed (2), proceedings (2), 2021 (2), wei (2), international (2), conference (2), model (2), journal (2), jmlr (2), arxiv (2), selected (2), paul (2), baran (2), marconi (2), young (2), scholar (2), engineering (2), university (2), technical (2), researcher (2), improving (2), agents (2), reflection (2), close (2), open (2), berkeley, 294, department, energy, advanced, meeting, pimrc, ita, panelist, panel, beyond, invited, workshops, 528, youtube, recent, optasia, relational, platform, efficient, scale, video, analytics, symposium, cloud, socc, santa, clara, 2016, chaudhuri, accelerating, queries, probabilistic, predicates, sigmod, 2018, barham, dean, ghemawat, hand, hurt, isard, lim, pang, roy, sepassi, asynchronous, dataflow, pope, douglas, efficiently, transformer, inference, hazimeh, zhao, sathiamoorthy, dselect, differentiable, selection, mixture, experts, applications, multi, task, jaszczur, mohiuddin, kaiser, gajewski, michalewski, kanerva, sparse, enough, transformers, wang, consistency, improves, chain, thought, representations, singhal, azizi, encode, clinical, knowledge, nature, 620, 172, 180, website, driess, xia, florence, embodied, chung, hou, instruction, finetuned, blog, narang, devlin, modeling, team, family, highly, capable, preprint, 2312, 11805, dec, 2012, honors, awards, completed, phd, electrical, from, awarded, contributions, dissertation, field, communications, internet, before, this, 540b, pre, training, finetuning, also, core, contributor, medpalm, project, prior, joining, several, interdisciplinary, initiatives, microsoft, princeton, across, teaching, fall, winter, 2025, program, chair, 2026, cs329a, pushing, frontier, agentic, llms, leveraging, techniques, enable, autonomous, especially, software, startup, adjunct, professor, skip, content,

Text of the page (random words):
aakanksha chowdhery 0 skip to content aakanksha chowdhery talks publications about open menu close menu aakanksha chowdhery talks publications about open menu close menu talks publications about aakanksha chowdhery adjunct professor stanford researcher reflection ai i am pushing the frontier of agentic llms by leveraging rl techniques to enable autonomous self improving agents especially in software engineering at the startup reflection ai at stanford i am co teaching cs329a self improving ai agents in fall winter 2025 and i am the program chair for mlsys 2026 before this i was the technical lead of 540b palm model and lead researcher in gemini at google in pre training scaling and finetuning of large language models i was also a core contributor in palm e medpalm and pathways project at google prior to joining google i was technical lead for several interdisciplinary research initiatives at microsoft research and princeton university across machine learning and distributed systems i completed my phd in electrical engineering from stanford university and was awarded the paul baran marconi young scholar award for the outstanding scientific contributions of my dissertation in the field of communications and internet selected honors awards outstanding paper award mlsys 2023 outstanding paper award mlsys 2022 paul baran marconi young scholar award 2012 selected publications machine learning gemini team et al gemini a family of highly capable multimodal models arxiv preprint arxiv 2312 11805 dec 2023 pdf a chowdhery s narang j devlin et al palm scaling language modeling with pathways journal of machine learning research jmlr 2023 pdf blog h w chung l hou j wei et al scaling instruction finetuned language models journal of machine learning research jmlr 2024 pdf d driess f xia p florence et al palm e an embodied multimodal language model international conference on machine learning icml 2023 pdf website k singhal s azizi et al large language models encode clinical knowledge nature 620 172 180 2023 pdf x wang j wei et al self consistency improves chain of thought reasoning in language models international conference on learning representations iclr 2023 pdf s jaszczur a chowdhery a mohiuddin l kaiser w gajewski h michalewski and j kanerva sparse is enough in scaling transformers neurips 2021 pdf h hazimeh z zhao a chowdhery m sathiamoorthy et al dselect k differentiable selection in the mixture of experts with applications to multi task learning neurips 2021 pdf systems r pope s douglas a chowdhery et al efficiently scaling transformer inference proceedings of machine learning and systems mlsys 2023 outstanding paper award pdf p barham a chowdhery j dean s ghemawat s hand d hurt m isard h lim r pang s roy r sepassi et al pathways asynchronous distributed dataflow for ml proceedings of machine learning and systems mlsys 2022 outstanding paper award pdf y lu a chowdhery s kandula and s chaudhuri accelerating machine learning queries with probabilistic predicates acm sigmod 2018 pdf y lu a chowdhery and s kandula optasia a relational platform for efficient large scale video analytics acm symposium on cloud computing socc santa clara ca 2016 pdf recent talks stanford cs 528 talk on multimodal reasoning gemini palm e 2024 youtube invited talks at iclr 2023 icml 2023 and neurips 2022 workshops keynote panelist at neurips 2023 panel on beyond scaling keynote speaker at pimrc 2023 and ita 2023 keynote speaker at department of energy advanced scientific computing research meeting 2024 berkeley cs 294 talk on scaling large language models 2023