Meta tags:
description=Hi I m Lev! headshot.jpg I m a graduate student at the University of Toronto focusing on AI Safety supervised by Sheila McIlraith and Roger Grosse. Currently, I m working on applying training data …;

Headings (most frequently used words):

-

Text of the page (most frequently used words):
https (7), and (6), the (5), span (4), toronto (4), sheila (4), arxiv (4), lev (3), mcilraith (3), edu (3), models (3), unlearning (3), learning (3), for (3), mckinney (3), workshop (3), __lev (3), url (3), class (2), www (2), roger (2), grosse (2), like (2), functions (2), large (2), language (2), predictions (2), reward (2), reinforcement (2), with (2), keiran (2), paster (2), 2025 (2), openreview (2), net (2), forum (2), mckinney__ (2), latent (2), from (2), 2303 (2), 08112 (2), org (2), pdf (2), _deep (2), neurips (2), info (2), dot (2), rightimg, tinyimg, headshot, jpg, graduate, student, university, focusing, safety, supervised, rgrosse, currently, working, applying, training, data, attribution, techniques, influence, understand, processes, out, context, reasoning, previously, done, research, understanding, transformer, far, center, human, compatible, artificial, intelligence, chai, humancompatible, model, based, mbrl, here, example, papers, preprints, anvith, thudi, juhan, bae, tara, rezaei, kheirkhah, nicolas, papernot, baker, gauss, newton, llm, era, _icml, machine, generative, ai_, vffttndvw6, nora, belrose, zach, furman, logan, smith, danny, halawi, igor, ostrovsky, stella, biderman, jacob, steinhardt, eliciting, transformers, tuned, lens, preprint, 2023, yawen, duan, david, krueger, adam, gleave, fragility, learned, 2022_, 2022, abs, 2301, 03652, jimmy, blast, dynamics, bootstrapping, 2021_, 2021, vwa_hknx_kr, contact, levmckinney,

Text of the page (random words):
lev mckinney hi i m lev span class rightimg span class tinyimg headshot jpg span span i m a graduate student at the university of toronto focusing on ai safety supervised by sheila mcilraith https www cs toronto edu sheila and roger grosse https www cs toronto edu rgrosse currently i m working on applying training data attribution techniques like influence functions to understand processes like out of context reasoning in large language models i ve previously done research on unlearning in large language models understanding transformer predictions at far ai reward learning at the center for human compatible artificial intelligence chai https humancompatible ai and model based reinforcement learning mbrl with keiran paster here at u of t example papers preprints lev e mckinney anvith thudi juhan bae tara rezaei kheirkhah nicolas papernot sheila a mcilraith and roger baker grosse gauss newton unlearning for the llm era in _icml 2025 workshop on machine unlearning for generative ai_ 2025 https openreview net forum id vffttndvw6 nora belrose zach furman __lev e mckinney__ logan smith danny halawi igor ostrovsky stella biderman and jacob steinhardt eliciting latent predictions from transformers with the tuned lens arxiv preprint arxiv 2303 08112 2023 url https arxiv org pdf 2303 08112 pdf __lev e mckinney__ yawen duan david krueger and adam gleave on the fragility of learned reward functions in _deep reinforcement learning workshop neurips 2022_ 2022 url https arxiv org abs 2301 03652 keiran paster __lev e mckinney __ sheila a mcilraith and jimmy ba blast latent dynamics models from bootstrapping in _deep rl workshop neurips 2021_ 2021 url https openreview net forum id vwa_hknx_kr info contact info levmckinney at cs dot toronto dot edu