Deep Learning
Learning Physics Constrained Dynamics Using Autoencoders Tsung-Y en Y ang
We consider the problem of estimating states ( e.g., position and velocity) and physical parameters ( e.g., friction, elasticity) from a sequence of observations
Center of the left camera Center of the right camera Epipolar lines left image plane right image plane A point in a physical scene Rectified Rectified epipolar line
Thus, alleviating the impacts of the Sim2Real photometric gap in stereo matching DNNs becomes a pressing need.
On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
While in some applications the goal is to "nudge" the pre-trained
Keunseo Kim
Supplementary Material for the Paper entitled "Locally Most Powerful Bayesian Test for Out-of-Distribution Detection Using Deep Generative Models" We present the implementation details for the V AE and Glow, used in Section 5. First, the structure of the Glow is presented in Table 1, where the "Level" refers to the number of scales that split the dimension of the latent space defined in the multi-scale architecture (Dinh et al., 2016), the "Depth per level" refers to the number of flow layers that are repeated on each scale, "In-channels hidden units" refers to the number of input channels and the number of hidden units of the neural network that defines the parameters of the flow layers, and the "Coupling" refers to the type of the coupling layers. For the training, we used the Adam optimizer with learning rate of 0.001 and batch size of 64 for both datasets. Next, Table 2 presents the structure for the V AE, which is the same as that used in Xiao et al. (2020). Batch normalization layer (BN) and activation layer by ReLU function (ReLU) were added after each convolutional layer. For training the V AE, we used the Adam optimizer with a learning rate of 0.0005, weight decay of 0.00003, and batch size of 64 for both datasets.
Reports of the Workshops Held at the 2025 AAAI Conference on Artificial Intelligence
The Workshop Program of the Association for the Advancement of Artificial Intelligence's 39th Conference on Artificial Intelligence (AAAI-25) was held in Philadelphia, Pennsylvania, on February 25 - March 4, 2025. TIKA is envisioned to create an open knowledge resource and serve as a hub for research, education and training on knowledge representation and knowledge engineering. Over 50 AI researchers convened at the workshop over two days. The discussions focused on different aspects of creating an open knowledge resource including foundational knowledge, automated reasoning, knowledge curation, education on knowledge axiomatization, and evaluation of outcomes. The opening discussion confirmed that the idea of curated knowledge, that is, knowledge captured in an expressive formal language that can be explicitly examined and verified by humans, is compelling. It must, however, be situated in the modern context of AI. Such a resource should address the limitations of existing generative ...
Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics
We take inspiration from a popular framework in neuroscience: "predictive coding".
Neural Routing by Memory
It relieves each procedure's learning difficulty and thus leads to superior performance.
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect Lorenzo Noci Dept of Computer Science ETH Zürich lorenzo.noci@inf.ethz.ch Kevin Roth
The " cold posterior effect " (CPE) in Bayesian deep learning describes the uncom-forting observation that the predictive performance of Bayesian neural networks