Related papers: LITHE: Bridging Best-Effort Python and Real-Time C…
Traditional Artificial Cognitive Systems (for example, intelligent robots) share a number of limitations. First, they are usually made up only of machine components; humans are only playing the role of user or supervisor. And yet, there are…
The integration of Supernumerary Limbs (SLs) on humanoid robots poses a significant stability challenge due to the dynamic perturbations they introduce. This thesis addresses this issue by designing a novel hierarchical control architecture…
While GPUs dominate massively parallel computing through the single-instruction, multiple-thread (SIMT) programming model, their underlying single-instruction, multiple-data (SIMD) execution incurs substantial energy overhead from frequent…
To break the context limits of large language models (LLMs) that bottleneck reasoning accuracy and efficiency, we propose the Thread Inference Model (TIM), a family of LLMs trained for recursive and decompositional problem solving, and…
As the automotive industry transitions toward centralized Linux-based architectures, ensuring the predictable execution of mixed-criticality applications becomes essential. However, concurrent use of the Linux network stack introduces…
Microprocessors enable aggressive hardware virtualization by means of which multiple processes temporally execute on the system. These security-critical and ordinary processes interact with each other to assure application progress.…
Hybrid systems are increasingly used in critical applications such as medical devices, infrastructure systems, and autonomous vehicles. Lince is an academic tool for specifying and simulating such systems using a C-like language with…
We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online…
While natural language offers a convenient shared interface for humans and robots, enabling robots to interpret and follow language commands remains a longstanding challenge in manipulation. A crucial step to realizing a performant…
Automated machine learning makes it easier for data scientists to develop pipelines by searching over possible choices for hyperparameters, algorithms, and even pipeline topologies. Unfortunately, the syntax for automated machine learning…
Protecting sensitive information in data-driven collaborations, such as AI training, while meeting the diverse requirements of multiple mutually distrusted stakeholders, is both crucial and challenging. This paper presents Styx, a novel…
Python based Robot Interactive Development Environment (PyRIDE) is a software that supports rapid \textit{interactive} programming of robot skills and behaviours on PR2/ROS (Robot Operating System) platform. One of the key features of…
Spiking Neural Networks (SNNs) mimic the information-processing mechanisms of the human brain and are highly energy-efficient, making them well-suited for low-power edge devices. However, the pursuit of accuracy in current studies leads to…
Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in mscenarios where the amount of compute or quantity of input data varies over time. In such networks the inference…
Distributed machine learning training is one of the most common and important workloads running on data centers today, but it is rarely executed alone. Instead, to reduce costs, computing resources are consolidated and shared by different…
Large reasoning models (LRMs) excel at complex reasoning tasks but typically generate lengthy sequential chains-of-thought, resulting in long inference times before arriving at the final answer. To address this challenge, we introduce…
Energy-harvesting-powered computing offers intriguing and vast opportunities to dramatically transform the landscape of the Internet of Things (IoT) devices by utilizing ambient sources of energy to achieve battery-free computing. In order…
Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks. While scaling rollouts can stabilize training and enhance performance, the computational overhead is a critical issue. In…
Ising machines are effective solvers for complex combinatorial optimization problems. The idea is mapping the optimal solution(s) to a combinatorial optimization problem to the minimum energy state(s) of a physical system, which naturally…
Large language models often improve reasoning by sampling multiple outputs and aggregating their final answers, but precise and efficient control of error levels remains a challenging task. In particular, deciding when to stop sampling…