activity
20142023
most citedPredicting Aqueous Solubility of Organic Molecules Using Deep Learning Models with Varied Molecular Representations

83 citations · 457 across the 62 of their papers we have counts for

collaborators
Showing 2021Show all

18 papers · 1 filter

cs.CV2021

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Jichao Zhang, Enver Sangineto, Hao Tang +4

Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid/s…

cs.LG2021★ 2 cited

Structure-Aware Label Smoothing for Graph Neural Networks

Yiwei Wang, Yujun Cai, Yuxuan Liang +5

Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect th…

math.GT2021

The mapping class group of manifolds which are like projective planes

Yang Su, Wei Wang

In this paper we compute the mapping class group of simply-connected closed smooth manifolds with integral homology …

math.NA2021

On the asymptotical regularization with convex constraints for inverse problems

Min Zhong, Wei Wang

In this paper, we consider the asymptotical regularization with convex constraints for nonlinear ill-posed problems. The method allows to use non-smooth penalty terms, including th…

cs.IR2021★ 3 cited

Self-supervised Representation Learning for Trip Recommendation

Qiang Gao, Wei Wang, Kunpeng Zhang +2

Trip recommendation is a significant and engaging location-based service that can help new tourists make more customized travel plans. It often attempts to suggest a sequence of po…

cs.CV2021

Automatic Vocabulary and Graph Verification for Accurate Loop Closure Detection

Haosong Yue, Jinyu Miao, Weihai Chen +3

Localizing pre-visited places during long-term simultaneous localization and mapping, i.e. loop closure detection (LCD), is a crucial technique to correct accumulated inconsistenci…

math.SP2021★ 10 cited

Approximating the ground state eigenvalue via the effective potential

Ilias Chenn, Wei Wang, Shiwen Zhang

In this paper, we study 1-d random Schrödinger operators on a finite interval with Dirichlet boundary conditions. We are interested in the approximation of the ground state energy…

cs.LG2021★ 1 cited

Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression

Sheng Lin, Wei Jiang, Wei Wang +4

Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices.…

cs.CL2021★ 9 cited

Incorporating External POS Tagger for Punctuation Restoration

Ning Shi, Wei Wang, Boxin Wang +3

Punctuation restoration is an important post-processing step in automatic speech recognition. Among other kinds of external information, part-of-speech (POS) taggers provide inform…

cond-mat.mtrl-sci2021★ 83 cited

Predicting Aqueous Solubility of Organic Molecules Using Deep Learning Models with Varied Molecular Representations

Gihan Panapitiya, Michael Girard, Aaron Hollas +3

Determining the aqueous solubility of molecules is a vital step in many pharmaceutical, environmental, and energy storage applications. Despite efforts made over decades, there are…

physics.soc-ph2021

Competing spreading dynamics in simplicial complex

Wenyao Li, Xiaoyu Xue, Liming Pan +2

Interactions in biology and social systems are not restricted to pairwise but can take arbitrary sizes. Extensive studies have revealed that the arbitrary-sized interactions signif…

math.PR2021

Stochastic transport equation with bounded and Dini continuous drift

Jinlong Wei, Guangying Lv, Wei Wang

The results established by Flandoli, Gubinelli and Priola ({\it Invent. Math.} {\bf 180} (2010) 1--53) for stochastic transport equation with bounded and Hölder continuous drift ar…

cs.CV2021★ 64 cited

Robust Differentiable SVD

Wei Wang, Zheng Dang, Yinlin Hu +2

Eigendecomposition of symmetric matrices is at the heart of many computer vision algorithms. However, the derivatives of the eigenvectors tend to be numerically unstable, whether u…

cs.CV2021★ 23 cited

Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations

Guanghao Yin, Wei Wang, Zehuan Yuan +5

Although single-image super-resolution (SISR) methods have achieved great success on single degradation, they still suffer performance drop with multiple degrading effects in real…

physics.ins-det2021

The Design and Sensitivity of JUNO's scintillator radiopurity pre-detector OSIRIS

JUNO Collaboration, Angel Abusleme, Thomas Adam +598

The OSIRIS detector is a subsystem of the liquid scintillator fillling chain of the JUNO reactor neutrino experiment. Its purpose is to validate the radiopurity of the scintillator…

eess.SY2021★ 1 cited

Reduced Dynamics and Control for an Autonomous Bicycle

Jiaming Xiong, Bo Li, Ruihan Yu +3

In this paper, we propose the reduced model for the full dynamics of a bicycle and analyze its nonlinear behavior under a proportional control law for steering. Based on the Gibbs-…

cs.RO2021★ 1 cited

RadarLoc: Learning to Relocalize in FMCW Radar

Wei Wang, Pedro P. B. de Gusmo, Bo Yang +2

Relocalization is a fundamental task in the field of robotics and computer vision. There is considerable work in the field of deep camera relocalization, which directly estimates p…

cs.CL2021

FGNET-RH: Fine-Grained Named Entity Typing via Refinement in Hyperbolic Space

Muhammad Asif Ali, Yifang Sun, Bing Li +1

Fine-Grained Named Entity Typing (FG-NET) aims at classifying the entity mentions into a wide range of entity types (usually hundreds) depending upon the context. While distant sup…