Related papers: Real-time adaptive optics control with a high leve…
Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…
The forthcoming Extremely Large Telescopes all require adaptive optics systems for their successful operation. The real-time control for these systems becomes computationally challenging, in part limited by the memory bandwidths required…
Object-oriented scripting languages such as JavaScript or Python gain in popularity due to their flexibility. Still, the growing code bases written in the languages call for methods that make possible to automatically control the properties…
Emerging AI applications such as ChatGPT, graph convolutional networks, and other deep neural networks require massive computational resources for training and inference. Contemporary computing platforms such as CPUs, GPUs, and TPUs are…
Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encoded within these models for…
Optical multilayer thin-films are fundamental components that enable the precise control of reflectance, transmittance, and phase shift in the design of photonic systems. Rapid and accessible simulation of these structures holds critical…
We introduce Lyceum, a high-performance computational ecosystem for robot learning. Lyceum is built on top of the Julia programming language and the MuJoCo physics simulator, combining the ease-of-use of a high-level programming language…
We address language-conditioned robotic manipulation using flow-based trajectory generation, which enables training on human and web videos of object manipulation and requires only minimal embodiment-specific data. This task is challenging,…
The Julia programming language was designed to fill the needs of scientific computing by combining the benefits of productivity and performance languages. Julia allows users to write untyped scripts easily without needing to worry about…
In this paper we introduce the concept of real-time hardware-in-the-loop simulation for astronomical adaptive optics, and present the case for the requirement for such a facility. This real-time simulation, when linked with an adaptive…
Over the past few years, the advancement of Multimodal Large Language Models (MLLMs) has captured the wide interest of researchers, leading to numerous innovations to enhance MLLMs' comprehension. In this paper, we present AdaptVision, a…
Although massive pre-trained vision-language models like CLIP show impressive generalization capabilities for many tasks, still it often remains necessary to fine-tune them for improved performance on specific datasets. When doing so, it is…
The Julia programming language continues to gain popularity both for its potential for programmer productivity and for its impressive performance on scientific code. It thus holds potential for large-scale HPC, but we have not yet seen this…
Light-based advanced manufacturing increasingly requires programmable, closed-loop tools that translate human design intent into executable operations at small length scales. Yet a key bottleneck persists across robotic and manufacturing…
Simulation frameworks have been key enablers for the development and validation of autonomous driving systems. However, existing methods struggle to comprehensively address the autonomy-oriented requirements of balancing: (i) dynamical…
Artificial visual attention systems aim to support technical systems in visual tasks by applying the concepts of selective attention observed in humans and other animals. Such systems are typically evaluated against ground truth obtained…
Optical computing offers ultrafast, energy-efficient alternatives to conventional digital processors, yet most implementations remain confined to single-channel processing, severely underutilizing light's information capacity. Here we…
Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized…
For instruments with many occasional users, it is important to have easy to use software. To support the frequent users it is important to be flexible. Using a scripting language to design a GUI and exposing it to the user allows us to do…
This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that…