Deep Learning
Sanity Checks for Saliency Maps
Julius Adebayo, Justin Gilmer, Michael Muelly, Ian Goodfellow, Moritz Hardt, Been Kim
Through extensive experiments we show that some existing saliency methods are independent both of the model and of the data generating process.
Exploiting LLM Quantization
While LLM quantization's impact on utility has been extensively explored, this work for the first time studies its adverse effects from a security perspective.
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier
Top-level human players perform about 350 actions per minute [1].
Attention in Convolutional LSTM for Gesture Recognition
Liang Zhang, Guangming Zhu, Lin Mei, Peiyi Shen, Syed Afaq Ali Shah, Mohammed Bennamoun
In the preliminary "Res3D+ConvLSTM+MobileNet" architecture, the blocks 1-4 of Res3D [16] are used first to learn the local short-term spatiotemporal feature maps which have a relativelylargespatialsize.
Uncertainty-Aware Attention for Reliable Interpretation and Prediction
Jay Heo, Hae Beom Lee, Saehoon Kim, Juho Lee, Kwang Joon Kim, Eunho Yang, Sung Ju Hwang
Neural Information Processing Systems http://nips.cc/