User profiles for Kuan-Chieh Wang
Kuan-Chieh (Jackson) WangSnap Inc. Verified email at stanford.edu Cited by 2406 |
Neural relational inference for interacting systems
Interacting systems are prevalent in nature, from dynamical systems in physics to complex
societal dynamics. The interplay of components can give rise to complex behavior, which can …
societal dynamics. The interplay of components can give rise to complex behavior, which can …
Your classifier is secretly an energy based model and you should treat it like one
We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based
model for the joint distribution p(x,y). In this setting, the standard class probabilities can be …
model for the joint distribution p(x,y). In this setting, the standard class probabilities can be …
Variational model inversion attacks
Given the ubiquity of deep neural networks, it is important that these models do not reveal
information about sensitive data that they have been trained on. In model inversion attacks, a …
information about sensitive data that they have been trained on. In model inversion attacks, a …
Lingvo: a modular and scalable framework for sequence-to-sequence modeling
Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning
research, with a particular focus towards sequence-to-sequence models. Lingvo models …
research, with a particular focus towards sequence-to-sequence models. Lingvo models …
The comparison of solitary and collaborative modes of game-based learning on students' science learning and motivation
CH Chen, KC Wang, YH Lin - Journal of Educational Technology & Society, 2015 - JSTOR
In this study, we investigated and compared solitary and collaborative modes of game-based
learning in promoting students’ science learning and motivation. A total of fifty seventh …
learning in promoting students’ science learning and motivation. A total of fifty seventh …
Prob: Probabilistic objectness for open world object detection
Open World Object Detection (OWOD) is a new and challenging computer vision task that
bridges the gap between classic object detection (OD) benchmarks and object detection in the …
bridges the gap between classic object detection (OD) benchmarks and object detection in the …
Understanding and mitigating exploding inverses in invertible neural networks
Invertible neural networks (INNs) have been used to design generative models, implement
memory-saving gradient computation, and solve inverse problems. In this work, we show that …
memory-saving gradient computation, and solve inverse problems. In this work, we show that …
LOVM: Language-only vision model selection
Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular
due to their exceptional performance on downstream vision applications, particularly in the …
due to their exceptional performance on downstream vision applications, particularly in the …
Centroid-based deep metric learning for speaker recognition
Speaker embedding models that utilize neural networks to map utterances to a space where
distances reflect similarity between speakers have driven recent progress in the speaker …
distances reflect similarity between speakers have driven recent progress in the speaker …
[PDF][PDF] Classifying NBA offensive plays using neural networks
The amount of raw information available for basketball analytics has been given a great
boost with the availability of player tracking data. This facilitates detailed analyses of player …
boost with the availability of player tracking data. This facilitates detailed analyses of player …