When humans design cost or goal specifications for robots, they often produce specifications that are ambiguous, underspecified, or beyond planners' ability to solve. In these cases, corrections provide a valuable tool for human-in-the-loop robot control. Corrections might take the form of new goal specifications, new constraints (e.g. to avoid specific objects), or hints for planning algorithms (e.g. to visit specific waypoints). Existing correction methods (e.g. using a joystick or direct manipulation of an end effector) require full teleoperation or real-time interaction.

Blue noise error patterns are well suited to human perception, and when applied to stochastic rendering techniques, blue noise masks can minimize unwanted low-frequency noise in the final image. Current methods of applying different blue noise masks to each rendered frame result in either white noise frequency spectra temporally, and thus poor convergence and stability, or lower quality spatially. We propose novel blue noise masks that retain high quality blue noise spatially, yet when animated produce values at each pixel that are well distributed over time.

Data clipping is crucial in reducing noise in quantization operations and improving the achievable accuracy of quantization-aware training (QAT). Current practices rely on heuristics to set clipping threshold scalars and cannot be shown to be optimal. We propose Optimally Clipped Tensors And Vectors (OCTAV), a recursive algorithm to determine MSE-optimal clipping scalars. Derived from the fast Newton-Raphson method, OCTAV finds optimal clipping scalars on the fly, for every tensor, at every iteration of the QAT routine.

GPU-accelerated computing systems, which power the AI revolution, rely on increasing amounts of off-chip I/O. To continue scaling, very dense integration of ultra-efficient optical transceivers alongside next-generation processor die will be needed.