Meta tags:

Headings (most frequently used words):

about, me, news, contact, zhihan, zhang,

Text of the page (most frequently used words):
2025 (11), for (8), llms (7), following (6), the (6), instruction (6), #zhihan (5), zhang (5), was (5), about (5), and (5), accepted (4), authored (4), paper (4), amazon (4), evaluation (3), tutorial (3), training (3), experience (3), publications (3), where (3), github (2), follow (2), palo (2), alto (2), email (2), feb (2), benchmark (2), llm (2), naacl (2), novel (2), may (2), proposed (2), framework (2), acl (2), data (2), gave (2), methods (2), check (2), emnlp (2), please (2), refer (2), google (2), scholar (2), from (2), university (2), applied (2), scientist (2), work (2), rufus (2), model (2), 2026, powered, fork, minimal, mistakes, academicpages, jekyll, feed, sitemap, office, 611, cowper, street, zhangzhihan719, gmail, com, contact, delivered, new, based, recommender, systems, built, iheval, assessing, capability, hierarchy, first, iterative, verify, then, revise, reasoning, tasks, that, leverages, implicit, user, preferences, generate, preference, tuning, nov, covers, benchmarks, collection, explanability, analyses, out, our, video, slides, news, past, education, internship, full, list, page, prior, joining, industry, earned, computer, science, notre, dame, advised, during, research, centered, received, bachelor, degree, peking, worked, with, sun, yunfang, meng, jiang, name, 张智涵, building, large, language, agent, tailored, shopping, applications, current, focuses, improving, general, capabilities, part, its, post, efforts, linkedin, twitter,

Text of the page (random words):
about me zhihan zhang zhihan zhang about me publications experience zhihan zhang llm applied scientist at amazon follow palo alto ca amazon email twitter linkedin github google scholar about me my name is zhihan zhang 张智涵 i am an applied scientist at amazon where i work on building rufus amazon s large language model agent tailored for shopping applications my current work focuses on improving the general instruction following capabilities of the rufus model as part of its post training efforts prior to joining industry i earned my ph d in computer science from the university of notre dame where i was advised by dr meng jiang during my ph d my research centered on training and evaluation methods for instruction following llms i received my bachelor s degree from peking university where i worked with dr yunfang wu and dr xu sun i gave a tutorial about instruction following llms at emnlp 2025 for my past education and internship experience please refer to experience for the full list of my publications please refer to publications or check my google scholar page news nov 2025 i gave a tutorial about instruction following llms at emnlp 2025 the tutorial covers training methods evaluation benchmarks data collection and explanability analyses of instruction following llms check out our slides and video may 2025 a co authored paper was accepted by acl 2025 we proposed a novel framework that leverages implicit user preferences to generate preference tuning data for llms may 2025 a co authored paper was accepted by acl 2025 we proposed an iterative verify then revise framework for llms on reasoning tasks feb 2025 a first authored paper was accepted by naacl 2025 we built iheval a novel benchmark for assessing llms capability of following the instruction hierarchy feb 2025 a co authored paper was accepted by naacl 2025 we delivered a new evaluation benchmark for llm based recommender systems contact email zhangzhihan719 at gmail com office 611 cowper street palo alto ca sitemap follow github feed 2026 zhihan zhang powered by jekyll academicpages a fork of minimal mistakes