Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce instabilities, but the success of training remains strongly influenced by the choice of the hyperparameters.

To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has not yet produced state-of-the-art results. We present a simple, yet effective fusion approach for multi-frame optical flow that benefits from longer-term temporal cues. Our method first warps the optical flow from previous frames to the current, thereby yielding multiple plausible estimates. It then fuses the complementary information carried by these estimates into a new optical flow field.

We introduce a novel and efficient method for rendering large models composed of individually-oriented voxels. The core of this method is a new algorithm for computing the intersection point and normal of a 3D ray with an arbitrarily-oriented 3D box, which also has non-rendering applications in GPU physics, such as ray casting and particle collision detection. We measured throughput improvements of 2× to 10× for the intersection operation versus previous ray-box intersection algorithms on GPUs.

With the dramatic shrink of feature size and the advance of semiconductor technology nodes, numerous and complicated design rules need to be followed, and a chip design can only be taped-out after passing design rule check (DRC). The high design complexity seriously deteriorates design routability, which can be measured by the number of DRC violations after the detailed routing stage. In addition, a modern large-scaled design typically consists of many huge macros due to the wide use of intellectual properties (IPs).

Early routability prediction helps designers and tools perform preventive measures so that design rule violations can be avoided in a proactive manner. However, it is a huge challenge to have a predictor that is both accurate and fast. In this work, we study how to leverage convolutional neural network to address this challenge. The proposed method, called RouteNet, can either evaluate the overall routability of cell placement solutions without global routing or predict the locations of DRC (Design Rule Checking) hotspots.

Virtual reality experiences via immersive optics and sound are becoming ubiquitous; there are several consumer systems (e.g., Oculus Rift and HTC Vive) now available with these capabilities. Other sensory experiences, such as that of touch remain elusive in this field. The most successful examples of haptic sensation (e.g., Nintendo 64's Rumble Pack and its descendants) are vibrotactile, which do not afford for persistent, morphological shape experiences.

Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structured prediction, which optimizes over complex labels, while modeling within-label interactions. However, it is unclear what principles should guide the design of a structured prediction model that utilizes the power of deep learning components.