Related papers: MuJoCoUni:Persistent Batched Runtime Primitives fo…
Visual tokenization remains a core challenge in unifying visual understanding and generation within the autoregressive paradigm. Existing methods typically employ tokenizers in discrete latent spaces to align with the tokens from large…
Long-horizon tabletop games pose a distinct systems challenge for robotics: small perceptual or execution errors can invalidate accumulated task state, propagate across decision-making modules, and ultimately derail interaction. This paper…
Low-power microcontroller (MCU) hardware is currently evolving from single-core architectures to predominantly multi-core architectures. In parallel, new embedded software building blocks are more and more written in Rust, while C/C++…
Continual learning on edge platforms remains challenging because recurrent networks depend on energy-intensive training procedures and frequent data movement that are impractical for embedded deployments. This work introduces M2RU, a…
Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures…
We present QUBO.jl, an end-to-end Julia package for working with QUBO (Quadratic Unconstrained Binary Optimization) instances. This tool aims to convert a broad range of JuMP problems for straightforward application in many physics and…
Computational micromagnetics has become an essential tool in academia and industry to support fundamental research and the design and development of devices. Consequently, computational micromagnetics is widely used in the community, and…
First-order reinforcement learning with differentiable simulation is promising for quadrotor control, but practical progress remains fragmented across task-specific settings. To support more systematic development and evaluation, we present…
Online collision-free trajectory generation within a shared workspace is fundamental for most multi-robot applications. However, many widely-used methods based on model predictive control (MPC) lack theoretical guarantees on the feasibility…
In recent years, artificial feet based on soft robotics and under-actuation principles emerged to improve mobility on challenging terrains. This paper presents the application of the MuJoCo physics engine to realize a digital twin of an…
A novel parallel patterns library, Groovy Parallel Patterns, is presented which, from the outset, has been designed to exploit more general process parallelism than the usual data and task parallel architectures. The library executes on a…
Monte Carlo event generators are central to high-energy physics analysis. However, workflows based on handwritten scripts can be difficult to reuse, modify, and reproduce when multiple Monte Carlo models, tune variations, run variations,…
Generating robot simulation environments remains a major bottleneck in simulation-based robot learning. Constructing a training-ready MuJoCo scene typically requires expertise in 3D asset modeling, MJCF specification, spatial layout,…
The CODECO Experimentation Framework is an open-source solution designed for the rapid experimentation of Kubernetes-based edge cloud deployments. It adopts a microservice-based architecture and introduces innovative abstractions for (i)…
Robust adaptive control methods are essential for maintaining quadcopter performance under external disturbances and model uncertainties. However, fragmented evaluations across tasks, simulators, and implementations hinder systematic…
5G Radio access network disaggregation and softwarization pose challenges in terms of computational performance to the processing units. At the physical layer level, the baseband processing computational effort is typically offloaded to…
The miniaturization of AI accelerators is paving the way for next-generation wearable applications within wearable technologies. We introduce Mojito, an AI-native runtime with advanced MLOps designed to facilitate the development and…
Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require maintaining task state across many interface transitions. Existing agents typically rely…
We initiate the study of neural-network quantum state algorithms for analyzing continuous-variable lattice quantum systems in first quantization. A simple family of continuous-variable trial wavefunctons is introduced which naturally…
Modeling of command-line interface (CLI) interaction has enabled flexible, execution-free output presentation. However, current approaches struggle to model inputs with complex compositions and inputs whose execution behavior depends on…