Meta tags:
description=;

Headings (most frequently used words):

science, computer, 2023, massachusetts, institute, of, technology, 2018, yale, university, my, search, recent, news, publications, education, ph, cognitive, global, affairs, people, financially, invested, in, future, open, philanthropy, nsf, graduate, research, fellowship, truman, scholarship, parents, bibtex,

Text of the page (most frequently used words):
andi (25), peng (25), paper (21), the (20), and (19), workshop (16), human (14), 2024 (14), learning (8), from (8), with (7), 2022 (7), news (7), julie (7), shah (7), slides (6), for (6), research (6), mit (6), 2023 (6), #institute (5), yale (5), 2020 (5), neurips (5), iclr (5), oral (5), andreea (5), bobu (5), guided (5), humans (5), preferences (5), attending (5), machine (4), project (4), site (4), feedback (4), ilia (4), sucholutsky (4), language (4), rss (4), jacob (4), andreas (4), science (4), technology (4), about (4), state (3), university (3), ece (3), kamar (3), kori (3), inkpen (3), emre (3), kiciman (3), besmira (3), nushi (3), bias (3), fair (3), poster (3), icml (3), pulkit (3), agrawal (3), tianmin (3), shu (3), policy (3), abstractions (3), thomas (3), griffiths (3), belinda (3), robots (3), social (3), intelligence (3), pragmatic (3), feature (3), adaptive (3), how (3), conference (3), anthropic (3), working (3), presenting (3), level (2), technical (2), report (2), summers (2), 2019 (2), what (2), you (2), hiring (2), towards (2), framework (2), aaai (2), tackling (2), climate (2), change (2), top (2), collaboration (2), chi (2), nature (2), systems (2), make (2), standards (2), loop (2), adaptation (2), open (2), aligned (2), alignment (2), hri (2), agents (2), nishanth (2), kumar (2), theodore (2), sumers (2), future (2), robot (2), representations (2), corl (2), abstraction (2), contrastive (2), explanations (2), non (2), all (2), publications (2), help (2), models (2), jul (2), main (2), also (2), rewards (2), aug (2), national (2), global (2), affairs (2), 2018 (2), massachusetts (2), computer (2), boston (2), currently (2), serve (2), where (2), school (2), that (2), learn (2), through (2), lot (2), before (2), download, copy, bibtex, copyright, 2026, data, maps, united, states, peace, usip, william, casey, king, christine, houle, akshay, bery, yuhan, lim, yara, hattab, reem, hussein, katherine, kirk, megan, wilson, joe, english, early, detection, boko, haram, attacks, nigeria, aiaa, scitech, 2017, nasa, robert, falck, justin, gray, christopher, heath, nariman, sharifrazi, gazi, sakib, andrew, oberlander, golda, nguyen, colin, jeffrey, chin, kenneth, decker, conceptual, feasibility, study, hyperloop, vehicle, next, generation, transport, undergraduate, thesis, integrated, approach, studying, terrorism, hcomp, siddharth, suri, see, get, impact, representation, criteria, aies, spotlight, malina, simard, halm, perils, objectivity, normative, judicial, decision, making, nebojsa, jojic, bistra, dilkina, dan, morris, blake, elias, kolya, malkin, anthony, ortiz, caleb, robinson, fast, land, cover, mapping, centered, approaches, responsible, percolation, assessing, multiaxial, dataset, trust, reliance, teams, investigations, performance, teamwork, lucas, joppa, leehi, yona, amy, luers, greenhouse, gas, accounting, reliable, build, interoperable, evaluation, jonathan, frankle, yonadav, shavit, jessica, zosa, forde, strengthening, subcommunities, sustainable, growth, front, page, story, video, mark, aviv, netanyahu, diagnosis, test, time, tmlr, finalist, oustanding, certification, dylan, hadfield, menell, xander, davies, stephen, casper, problems, fundamental, limitations, reinforcement, code, noga, zaslavsky, eoin, kenny, mycal, tucker, complexity, controlled, preprint, adrian, weller, lukas, muttenthaler, getting, representational, llm, preference, conditioned, icra, collaborative, work, safety, anca, dragan, aligning, jhu, david, abel, yuying, sun, reward, relevant, datasets, benchmarks, chuang, gan, behzad, dariush, kwonjoon, lee, sunli, chen, hongxin, zhang, zhenting, jiaming, shen, qiushi, lyu, weihua, constrained, inclusive, embodied, assistance, challenge, 2025, idan, shenfeld, mehul, damani, hard, think, input, allocation, computation, archival, journal, papers, started, big, safer, may, honored, part, cohort, well, organize, task, specification, pioneers, beforehand, rlc, beyond, taking, leave, lead, security, evaluations, frontier, red, team, nov, recent, people, financially, invested, parents, truman, scholarship, nsf, graduate, fellowship, philanthropy, education, cognitive, linkedin, twitter, google, scholar, email, love, being, outdoors, even, brutal, winters, current, goal, run, sub, marathon, reach, out, chat, running, preferred, subject, line, your, cat, dope, this, doing, history, buff, heart, care, deeply, academic, communities, create, safe, ethical, equitable, special, government, employee, previous, life, worked, advisory, board, teach, course, policymakers, jackson, schmidt, futures, nist, white, house, office, ostp, defense, innovation, unit, diu, interested, building, rich, knowledge, whether, directly, users, priors, lms, thinking, utilize, pretrained, conjunction, interactively, founder, was, previously, researcher, post, training, claude, phd, student, csail, advised, spent, facebook, dynamics, ibm, watson, lab, grad, two, years, resident, microsoft, did, undergrad, got, start, read, dead, philosophers, brian, scassellati, search,

Text of the page (random words):
andi peng search andi peng andi peng about news publications i am a co founder of humans i was previously a researcher at anthropic working on rl and post training of claude 3 5 through 4 5 and before that a phd student at mit csail advised by jacob andreas and julie shah i ve spent summers at facebook ai research fair boston dynamics ai institute mit ibm watson ai lab and before grad school two years as an ai resident at microsoft research i did my undergrad at yale where i got my start in research with brian scassellati and read a lot of dead philosophers i m interested in building agents that learn representations from rich human knowledge whether directly e g from users or through priors e g from lms currently i m thinking a lot about how to utilize pretrained models in conjunction with human feedback to interactively learn aligned preferences rewards a history buff at heart i care deeply about working with non academic communities to create safe ethical and equitable ai i currently serve as a special government employee for the defense innovation unit diu in a previous life i worked at the white house office of science and technology policy ostp national institute of standards and technology nist and schmidt futures i also serve on the advisory board of the yale jackson school of global affairs where i co teach a course on ai for policymakers i love being outdoors even in the brutal boston winters a current goal is to run a sub 3 00 marathon this is how i m doing reach out to chat about research policy or running preferred subject line your cat is dope email cv google scholar twitter linkedin education ph d computer science 2023 massachusetts institute of technology m s computer science 2023 massachusetts institute of technology b s cognitive science 2018 yale university b a global affairs 2018 yale university people financially invested in my future open philanthropy nsf graduate research fellowship truman scholarship my parents recent news all news nov 2024 attending corl i ll be presenting adaptive language guided abstraction from contrastive explanations in the main conference aug 2024 i am taking leave from mit to lead national security evaluations on the frontier red team at anthropic aug 2024 attending rlc i ll be presenting pragmatic feature preferences in the rl beyond rewards workshop jul 2024 attending icml i ll be presenting pragmatic feature preferences in the main conference i ll also be attending the alignment workshop beforehand jul 2024 attending rss i m honored to be part of the 2024 rss pioneers cohort as well as help organize the social intelligence in humans and robots workshop and the task specification workshop may 2024 i started at anthropic i ll be working to help make big models safer publications all papers journal conference workshop non archival learning how hard to think input adaptive allocation of lm computation mehul damani idan shenfeld andi peng andreea bobu jacob andreas iclr 2025 paper adaptive language guided abstraction from contrastive explanations andi peng belinda z li ilia sucholutsky nishanth kumar julie a shah jacob andreas andreea bobu corl 2024 paper constrained human ai an inclusive embodied ai assistance challenge weihua du qiushi lyu jiaming shen zhenting qi hongxin zhang sunli chen andi peng tianmin shu kwonjoon lee behzad dariush chuang gan neurips 2024 datasets and benchmarks paper pragmatic feature preferences learning reward relevant preferences from human feedback andi peng yuying sun tianmin shu david abel icml 2024 paper jhu news learning with language guided state abstractions andi peng ilia sucholutsky belinda z li theodore r sumers thomas l griffiths jacob andreas julie a shah iclr 2024 rss workshop on social intelligence in humans and robots 2023 oral paper project site mit news aligning robot representations with humans andreea bobu andi peng pulkit agrawal julie a shah anca d dragan hri 2024 icra workshop on collaborative robots and work of the future 2022 rss workshop on social intelligence in humans and robot 2022 neurips workshop on ml safety 2022 paper preference conditioned language guided abstractions andi peng andreea bobu belinda z li theodore r sumers ilia sucholutsky nishanth kumar thomas l griffiths julie a shah hri 2024 iclr workshop on llm agents 2024 paper project site mit news getting aligned on representational alignment ilia sucholutsky lukas muttenthaler adrian weller andi peng thomas l griffiths preprint paper human guided complexity controlled abstractions andi peng mycal tucker eoin m kenny noga zaslavsky pulkit agrawal julie a shah neurips 2023 paper code open problems and fundamental limitations of reinforcement learning from human feedback stephen casper xander davies andi peng dylan hadfield menell tmlr 2023 finalist oustanding certification paper diagnosis feedback adaptation a human in the loop framework for test time policy adaptation andi peng aviv netanyahu mark k ho tianmin shu andreea bobu julie a shah pulkit agrawal icml 2023 neurips workshop on human in the loop learning 2022 paper poster video project site mit news front page story strengthening subcommunities towards sustainable growth in ai research andi peng jessica zosa forde yonadav shavit jonathan frankle iclr workshop on ml evaluation standards 2022 paper make greenhouse gas accounting reliable build interoperable systems amy luers leehi yona andi peng lucas joppa nature 2022 paper investigations of performance and bias in human ai teamwork in hiring andi peng besmira nushi emre kiciman kori inkpen ece kamar aaai 2022 oral top 4 chi workshop on trust and reliance on ai human teams 2020 oral paper dataset poster on the nature of bias percolation assessing multiaxial collaboration in human ai systems andi peng besmira nushi kori inkpen emre kiciman ece kamar chi workshop on human centered approaches to fair and responsible ai 2020 oral paper slides human machine collaboration for fast land cover mapping caleb robinson anthony ortiz kolya malkin blake elias andi peng dan morris bistra dilkina nebojsa jojic aaai 2020 oral top 3 neurips workshop on tackling climate change with machine learning 2019 iclr workshop on tackling climate change with machine learning 2020 paper poster slides project site the perils of objectivity towards a normative framework for fair judicial decision making andi peng malina simard halm aies 2020 spotlight paper slides what you see is what you get the impact of representation criteria on human bias in hiring andi peng besmira nushi emre kiciman kori inkpen siddharth suri ece kamar hcomp 2019 paper slides an integrated machine learning approach to studying terrorism andi peng undergraduate thesis yale university paper conceptual feasibility study of the hyperloop vehicle for next generation transport kenneth decker jeffrey chin andi peng colin summers golda nguyen andrew oberlander gazi sakib nariman sharifrazi christopher heath justin s gray robert d falck aiaa scitech 2017 nasa technical report paper slides early detection of boko haram attacks in nigeria andi peng joe english megan wilson katherine kirk reem hussein yara hattab yuhan lim akshay bery christine houle william casey king technical report united states institute of peace usip paper slides state level maps state level data copyright andi peng 2026 bibtex copy download