Meta tags:

Headings (most frequently used words):

aahlad, puli, about, me, news, olds,

Text of the page (most frequently used words):
the (20), for (15), and (13), was (9), models (9), learning (9), causal (8), with (8), work (8), link (8), new (7), 2022 (7), estimation (6), 2023 (6), nyu (5), from (5), survival (5), phd (5), about (5), 2025 (5), nov (4), paper (4), via (4), 2024 (4), science (4), inference (3), where (3), prof (3), calibration (3), improve (3), assumptions (3), general (3), neurips (3), email (3), interest (3), you (3), led (3), distribution (3), generalization (3), oct (3), published (3), workshop (3), how (3), feature (3), representations (3), aahlad (3), github (2), research (2), worked (2), also (2), two (2), but (2), explicit (2), analysis (2), predictive (2), functional (2), confounders (2), using (2), positivity (2), variables (2), shoot (2), contrarian (2), aistats (2), spurious (2), correlations (2), induced (2), between (2), nuisance (2), that (2), are (2), out (2), june (2), arxiv (2), nurd (2), iclr (2), march (2), improved (2), apple (2), scholars (2), fellowship (2), scis (2), icml (2), july (2), accepted (2), ood (2), all (2), level (2), prediction (2), improves (2), losses (2), not (2), improving (2), language (2), controllably (2), efficient (2), attention (2), experts (2), hold (2), gradients (2), faculty (2), fellow (2), center (2), data (2), puli (2), hosted, pages, theme, orderedlist, intern, summer, 2019, adobe, san, jose, working, bayesian, attribution, targeting, previously, software, developer, 2017, completed, introduced, amazing, mentors, fateful, fun, undergrad, enrolled, department, iit, madras, david, sontag, uri, shalit, clinical, machine, group, dbmi, columbia, university, olds, cal, add, differentiable, loss, allowing, trade, off, quality, fundamental, nonparametric, which, violate, control, functions, ivs, method, instrumental, only, treatment, process, links, 2020, along, punchlines, these, test, statistic, use, crts, robustness, mis, specified, covariate, distributions, contra, statistics, controlled, variable, selection, apr, 2021, mukund, sudarshan, what, sort, come, performance, guarantees, under, relationship, label, some, correlated, covariates, presence, named, rising, star, trustworthy, initiative, january, mark, goldstein, clear, updated, version, code, results, announcement, very, happy, recipient, organized, website, diet, april, second, success, sept, gave, talk, health, informs, nuisances, negativa, tmlr, defended, dissertation, coming, soon, august, papers, lead, nhi, adrial, saporta, multi, modal, contrastive, symile, explanations, reveal, through, definition, encoding, shows, learn, entire, algorithms, framing, meta, dataset, problem, black, box, jan, acl, transformer, simple, class, called, race, retrieval, equal, building, sequence, primitives, compression, need, ml4h, modeling, let, speak, mixture, heads, ucrl, probing, high, concepts, llm, extracting, llms, robust, shifts, mar, 2026, news, eternally, excited, ideas, finding, good, applications, want, chat, earlier, focused, making, generalize, across, different, populations, informed, insights, techniques, settings, standard, like, ignorability, overlap, primary, application, healthcare, particle, discovery, classifying, medical, images, shortcut, due, better, current, aims, studying, mitigating, role, overfitting, closes, gap, built, they, will, used, causality, interpretability, more, generally, obtained, computer, courant, institute, fortunate, advised, during, partially, supported, rajesh, ranganath, view, profile, publications, assistant, professor, dot, edu, may,

Text of the page (random words):
about me aahlad puli aahlad puli cv as of may 2025 assistant professor faculty fellow at the center for data science nyu email aahlad at nyu dot edu publications view my github profile about me i am a faculty fellow at the center for data science at nyu i obtained my phd in computer science from the courant institute nyu where i was fortunate to be advised by prof rajesh ranganath during my phd i was partially supported by the apple scholars in ai ml phd fellowship my research closes the gap between how models are built and how they will be used out of distribution generalization causality interpretability and more generally feature learning my current work aims to improve feature learning in ml models by studying and mitigating the role of gradients in overfitting my earlier work focused on making models generalize across different populations better representations for ood shortcut learning due to gradients the was informed by insights and techniques from work in causal inference in settings standard assumptions like ignorability and positivity overlap do not hold my primary application of interest is ai for healthcare e g classifying medical images and survival analysis but i also hold an interest in ml for science in general ml for particle discovery i m eternally excited about new ideas and finding good applications for my work shoot me an email if you want to chat news mar 2026 extracting representations in llms robust to distribution shifts at the ucrl workshop at iclr about improved probing for high level concepts in llm representations nov 2025 new paper let the experts speak improving survival prediction calibration via mixture of experts heads at ml4h improves survival modeling nov 2025 new paper attention and compression is all you need for controllably efficient language models on building controllably efficient sequence models with attention primitives nov 2025 new paper learning is not a race improving retrieval in language models via equal learning at acl improves feature learning in transformer via a simple class of losses called e losses jan 2025 black box causal inference shows how to learn entire estimation algorithms by framing causal estimation as a meta learning dataset level prediction problem oct 2024 two papers at neurips 2024 explanations that reveal all through the definition of encoding lead by nhi and i multi modal contrastive learning with symile led by adrial saporta august 2024 defended my phd dissertation link coming soon june 2024 nuisances via negativa accepted by tmlr link oct 2023 gave a talk about ood generalization in health at informs sept 2023 new paper accepted at neurips 2023 link july 2023 the second scis workshop was a success at icml 2023 link april 2023 diet was published at aistats link july 2022 organized the scis workshop at icml 2022 website march 2022 very happy to be a recipient of the apple scholars in ai ml phd fellowship announcement march 2022 updated version of nurd on arxiv with code and improved results link january 2022 nurd published at iclr 2022 and work led by mark goldstein published at clear 2022 link oct 21 named rising star by the trustworthy ml initiative june 21 new work on arxiv what sort of predictive models come with performance guarantees under spurious correlations induced by a relationship between the label and some nuisance variables that are correlated on the covariates out of distribution generalization in the presence of nuisance induced spurious correlations apr 21 link to work at aistats 2021 led by mukund sudarshan a new contrarian test statistic to use in crts to improve robustness to mis specified covariate distributions contra contrarian statistics for controlled variable selection nov 20 links to my work at neurips 2020 along with punchlines shoot me an email if these interest you general method for causal estimation from instrumental variables using only treatment process assumptions general control functions for causal estimation from ivs fundamental nonparametric assumptions for causal estimation using functional confounders which violate positivity causal estimation with functional confounders add on differentiable loss to improve calibration of survival models allowing explicit trade off with predictive quality x cal explicit calibration for survival analysis olds i was an intern in the summer of 2019 in adobe research san jose working on bayesian attribution models for ad targeting previously i worked as a software developer at dbmi columbia university in 2017 i completed my ms in cs also at nyu i was introduced to causal inference in the clinical machine learning group where i worked with two amazing mentors prof uri shalit and prof david sontag my fateful but fun undergrad was from iit madras where i was enrolled in the ee department hosted on github pages theme by orderedlist