Meta tags:
author=Dang Nguyen;
description=Dang Nguyen s homepage ;
keywords=jekyll, jekyll-theme, academic-website, portfolio-website;

Headings (most frequently used words):

news,

Text of the page (most frequently used words):
accepted (13), paper (12), our (9), 2026 (8), 2024 (8), 2023 (7), 2025 (7), the (6), icml (5), may (4), one (4), for (4), jun (4), iclr (4), data (4), dang (3), nguyen (3), sep (3), jan (3), distribution (3), join (3), research (3), training (3), language (3), models (3), via (3), with (2), papers (2), 2022 (2), icassp (2), apr (2), all (2), cross (2), alignment (2), model (2), modal (2), intern (2), synthetic (2), semantic (2), news (2), copyright, powered, theme, hosted, photos, from, unsplash, github, pages, folio, jekyll, two, are, feb, recognized, top, layer, fusion, heterogeneous, neural, networks, start, computer, science, ucla, dmlr, understanding, robustness, multi, contrastive, learning, shift, mar, cisco, phd, google, student, researcher, neurips, changing, reduce, simplicity, bias, improves, generalization, mini, batch, coresets, memory, efficient, mixtures, text, generation, large, gradient, matching, acl, findings, beyond, entropy, boosting, llm, uncertainty, quantification, pairwise, similarity, have, officially, advanced, candidacy, looking, forward, next, stage, journey, need, targeted, image, augmentation, diffusion, selection, fine, tuning, vision, trajectories, fogen, workshop, why, better, than, simple, graph, perspective, task, transfer, adobe, applied, scientist, ctrl, publications, about, toggle, navigation,

Text of the page (random words):
news dang nguyen dang nguyen toggle navigation about publications cv ctrl k news jun 15 2026 i join adobe as an applied scientist intern may 26 2026 our paper why is a b better than b a simple graph perspective on task transfer is accepted to the fogen workshop at icml 2026 apr 30 2026 our paper data selection for fine tuning vision language models via cross modal alignment trajectories is accepted to icml 2026 jan 26 2026 our paper do we need all the synthetic data targeted image augmentation via diffusion models is accepted to iclr 2026 jun 23 2025 i have officially advanced to ph d candidacy looking forward to the next stage of my research journey may 15 2025 our paper beyond semantic entropy boosting llm uncertainty quantification with pairwise semantic similarity is accepted to acl findings 2025 may 01 2025 our paper synthetic text generation for training large language models via gradient matching is accepted to icml 2025 jan 22 2025 our paper mini batch coresets for memory efficient language model training on data mixtures is accepted to iclr 2025 sep 25 2024 our paper changing the training data distribution to reduce simplicity bias improves in distribution generalization is accepted to neurips 2024 sep 23 2024 i join google research as a student researcher jun 17 2024 i join cisco as a phd research intern mar 03 2024 our paper understanding the robustness of multi modal contrastive learning to distribution shift is accepted to dmlr iclr 2024 jan 17 2024 one paper is accepted at iclr 2024 sep 25 2023 i start my ph d in computer science at ucla jun 04 2023 our paper on cross layer alignment for model fusion of heterogeneous neural networks is recognized as one of the top 3 of all papers accepted at icassp 2023 apr 25 2023 one paper is accepted at icml 2023 feb 17 2023 one paper is accepted at icassp 2023 may 15 2022 two papers are accepted at icml 2022 copyright 2026 dang nguyen powered by jekyll with al folio theme hosted by github pages photos from unsplash