Zobrazeno 1 - 10
of 2 262
pro vyhledávání: '"WANG Chenyu"'
With the advancement and boom of autonomous vehicles, vehicular digital twins (VDTs) have become an emerging research area. VDT can solve the issues related to autonomous vehicles and provide improved and enhanced services to users. Recent studies ha
Externí odkaz:
http://arxiv.org/abs/2409.01683
Autor:
Li, Xiner, Zhao, Yulai, Wang, Chenyu, Scalia, Gabriele, Eraslan, Gokcen, Nair, Surag, Biancalani, Tommaso, Regev, Aviv, Levine, Sergey, Uehara, Masatoshi
Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural, we often aim to optimize downstream reward functions while preservin
Externí odkaz:
http://arxiv.org/abs/2408.08252
Error slice discovery associates structured patterns with model errors. Existing methods discover error slices by clustering the error-prone samples with similar patterns or assigning discrete attributes to each sample for post-hoc analysis. While th
Externí odkaz:
http://arxiv.org/abs/2408.07832
Autor:
Ma, Yang, Wang, Dongang, Liu, Peilin, Masters, Lynette, Barnett, Michael, Cai, Weidong, Wang, Chenyu
The heterogeneity of neurological conditions, ranging from structural anomalies to functional impairments, presents a significant challenge in medical imaging analysis tasks. Moreover, the limited availability of well-annotated datasets constrains th
Externí odkaz:
http://arxiv.org/abs/2407.08948
Autor:
Wang, Chenyu, Wang, Yihan
This study evaluates the effectiveness of zero-shot compression techniques on large language models (LLMs) under long-context. We identify the tendency for computational errors to increase under long-context when employing certain compression methods
Externí odkaz:
http://arxiv.org/abs/2406.06773
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render the repres
Externí odkaz:
http://arxiv.org/abs/2405.18193
Autor:
Wang, Dongang, Liu, Peilin, Wang, Hengrui, Beadnall, Heidi, Kyle, Kain, Ly, Linda, Cabezas, Mariano, Zhan, Geng, Sullivan, Ryan, Cai, Weidong, Ouyang, Wanli, Calamante, Fernando, Barnett, Michael, Wang, Chenyu
Training deep neural networks reliably requires access to large-scale datasets. However, obtaining such datasets can be challenging, especially in the context of neuroimaging analysis tasks, where the cost associated with image acquisition and annota
Externí odkaz:
http://arxiv.org/abs/2404.03451
Quality Assurance (QA) aims to prevent mistakes and defects in manufactured products and avoid problems when delivering products or services to customers. QA for AI systems, however, poses particular challenges, given their data-driven and non-determ
Externí odkaz:
http://arxiv.org/abs/2402.16391
Autor:
Bhirangi, Raunaq, Wang, Chenyu, Pattabiraman, Venkatesh, Majidi, Carmel, Gupta, Abhinav, Hellebrekers, Tess, Pinto, Lerrel
Reasoning from sequences of raw sensory data is a ubiquitous problem across fields ranging from medical devices to robotics. These problems often involve using long sequences of raw sensor data (e.g. magnetometers, piezoresistors) to predict sequence
Externí odkaz:
http://arxiv.org/abs/2402.10211
Autor:
Stark, Hannes, Jing, Bowen, Wang, Chenyu, Corso, Gabriele, Berger, Bonnie, Barzilay, Regina, Jaakkola, Tommi
Discrete diffusion or flow models could enable faster and more controllable sequence generation than autoregressive models. We show that na\"ive linear flow matching on the simplex is insufficient toward this goal since it suffers from discontinuitie
Externí odkaz:
http://arxiv.org/abs/2402.05841