Recursive Harness Self-Improvement

Συγγραφείς: Lee, Hyunin, Xu, Jinglue, Seely, Jeffrey, Lee, Donghyun, Zaharia, Matei, Tang, Yujin

Θεματικοί όροι: Machine Learning, Artificial Intelligence

Σύνδεσμος πρόσβασης: https://arxiv.org/abs/2607.15524

Sakana Fugu Technical Report

Συγγραφείς: Tang, Yujin, Cetin, Edoardo, Xu, Jinglue, Sun, Qi, Nielsen, Stefan, Richard, Vincent, Goda, Haruto, Tymchenko, Iaroslav, Nguyen, Nhan, Lee, Hyunin, Ashiga, Mari, Kotyan, Shashank, Kuroki, So, Clanuwat, Tarin

Θεματικοί όροι: Machine Learning

Σύνδεσμος πρόσβασης: https://arxiv.org/abs/2606.21228

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models

Συγγραφείς: Lee, Hyunin, Zhang, Yong, Nguyen, Hoang Vu, Liu, Xiaoyi, Park, Namyong, Jung, Christopher, Jin, Rong, Wang, Yang, Wang, Zhigang, Sojoudi, Somayeh, Feng, Xue

Θεματικοί όροι: Machine Learning, Information Retrieval

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2510.09435

Position: AI Safety Must Embrace an Antifragile Perspective

Συγγραφείς: Jin, Ming, Lee, Hyunin

Πηγή: Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. 2025

Θεματικοί όροι: Artificial Intelligence

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2509.13339

Initial State Interventions for Deconfounded Imitation Learning

Συγγραφείς: Pfrommer, Samuel, Bai, Yatong, Lee, Hyunin, Sojoudi, Somayeh

Πηγή: 2023 62nd IEEE Conference on Decision and Control (CDC) Decision and Control (CDC), 2023 62nd IEEE Conference on. :2312-2319 Dec, 2023

Relation: 2023 62nd IEEE Conference on Decision and Control (CDC)

A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety

Συγγραφείς: Lee, Hyunin, Park, Chanwoo, Abel, David, Jin, Ming

Θεματικοί όροι: Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2407.18422

Pausing Policy Learning in Non-stationary Reinforcement Learning

Συγγραφείς: Lee, Hyunin, Jin, Ming, Lavaei, Javad, Sojoudi, Somayeh

Θεματικοί όροι: Computer Science - Machine Learning

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2405.16053

Tempo Adaptation in Non-stationary Reinforcement Learning

Συγγραφείς: Lee, Hyunin, Ding, Yuhao, Lee, Jongmin, Jin, Ming, Lavaei, Javad, Sojoudi, Somayeh

Θεματικοί όροι: Computer Science - Machine Learning

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2309.14989

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction

Συγγραφείς: Ying, Donghao, Guo, Mengzi Amy, Lee, Hyunin, Ding, Yuhao, Lavaei, Javad, Shen, Zuo-Jun Max

Θεματικοί όροι: Computer Science - Machine Learning, Mathematics - Optimization and Control

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2205.10715

Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization

Συγγραφείς: Ding, Yuhao, Zhang, Junzi, Lee, Hyunin, Lavaei, Javad

Θεματικοί όροι: Computer Science - Machine Learning

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2110.10117

Explainable Deep Learning Model for EMG-Based Finger Angle Estimation Using Attention

Συγγραφείς: Lee, Hyunin, Kim, Dongwook, Park, Yong-Lae

Συνεισφορές: Park, Yong-Lae

Θεματικοί όροι: RECOGNITION, SCHEME, ROBOT, Electromyography, Task analysis, Sensors, Muscles, Predictive models, Indexes, Electronics packaging, Surface electromyography (sEMG), finger angle estimation, deep learning, attention, explainable AI

Relation: https://hdl.handle.net/10371/223241; 000825969500001; 167084

Διαθεσιμότητα: https://hdl.handle.net/10371/223241
https://doi.org/10.1109/TNSRE.2022.3188275

Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods With Entropy Regularization

Συγγραφείς: Ding, Yuhao, Zhang, Junzi, Lee, Hyunin, Lavaei, Javad

Συνεισφορές: U. S. Army Research Laboratory and the U.S. Army Research Office, Office of Naval Research, Air Force Office of Scientific Research, National Science Foundation, UC Noyce Initiative

Πηγή: IEEE Transactions on Automatic Control ; volume 70, issue 8, page 5129-5144 ; ISSN 0018-9286 1558-2523 2334-3303

Διαθεσιμότητα: https://doi.org/10.1109/tac.2025.3540965
https://ieeexplore.ieee.org/ielam/9/11099039/10882911-aam.pdf
http://xplorestaging.ieee.org/ielx8/9/11099039/10882911.pdf?arnumber=10882911

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction.

Συγγραφείς: YING, DONGHAO¹ donghaoy@berkeley.edu, GUO, MENGZI AMY¹ mengzi_guo@berkeley.edu, LEE, HYUNIN¹ hyunin@berkeley.edu, DING, YUHAO² yuhao.ding3@gmail.com, LAVAEI, JAVAD¹ lavaei@berkeley.edu, SHEN, ZUO-JUN MAX³ maxshen@hku.hk

Πηγή: Journal of Artificial Intelligence Research. 2025, Vol. 83, p1-53. 53p.

Θεματικοί όροι: Markov processes, Algorithms

A Hypothesis on Black Swan in Unchanging Environments

Συγγραφείς: Lee, Hyunin, Park, Chanwoo, Abel, David, Jin, Ming

Όροι ευρετηρίου: Computer Science - Artificial Intelligence, Computer Science - Machine Learning, text

Σύνδεσμος: http://arxiv.org/abs/2407.18422

Mey, Adeena (2024) 침묵시키지 않기: 임흥순의 캄보디아 [Not Silencing. Im Heung-soon’s Cambodia]. In: 임흥순 콤플렉스-IM Heung-soon Complex. Arts Council Korea: Artist Survey, Research, and Criticism . Downlight Artbooks, Seoul, pp. 149-158. ISBN 979-11-987973-4-6

Συγγραφείς: Lee, Hyunin, Song, Kahyun, Mey, Adeena

Όροι ευρετηρίου: Fine Art, Cinematics and Photography, Film & Video, Book Section, NonPeerReviewed

Σύνδεσμος: https://ualresearchonline.arts.ac.uk/id/eprint/22488/1/Mey_ImHeungSoon_kr.pdf
https://ualresearchonline.arts.ac.uk/id/eprint/22488/
https://www.arko.or.kr/artcenter/board/view/881?bid=&page=2&cid=714895
https://ualresearchonline.arts.ac.uk/id/eprint/22488
https://www.arko.or.kr/artcenter/board/view/881?bid=&page=2&cid=714895

침묵시키지 않기: 임흥순의 캄보디아 [Not Silencing. Im Heung-soon’s Cambodia]

Συγγραφείς: Mey, Adeena

Συνεισφορές: Lee, Hyunin, Song, Kahyun

Θεματικοί όροι: Fine Art, Cinematics and Photography, Film & Video

Περιγραφή αρχείου: text

Relation: https://ualresearchonline.arts.ac.uk/id/eprint/22488/1/Mey_ImHeungSoon_kr.pdf; Mey, Adeena (2024) 침묵시키지 않기: 임흥순의 캄보디아 [Not Silencing. Im Heung-soon’s Cambodia]. In: 임흥순 콤플렉스-IM Heung-soon Complex. Arts Council Korea: Artist Survey, Research, and Criticism . Downlight Artbooks, Seoul, pp. 149-158. ISBN 979-11-987973-4-6

Διαθεσιμότητα: https://ualresearchonline.arts.ac.uk/id/eprint/22488/
https://ualresearchonline.arts.ac.uk/id/eprint/22488/1/Mey_ImHeungSoon_kr.pdf
https://www.arko.or.kr/artcenter/board/view/881?bid=&page=2&cid=714895