相关论文: MuJoCoUni:Persistent Batched Runtime Primitives fo…

We study the problem of adding native pulse-level control to heterogeneous High Performance Computing-Quantum Computing (HPCQC) software stacks, using the Munich Quantum Software Stack (MQSS) as a case study. The goal is to expand the…

A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such…

Robust uncertainty quantification (UQ) remains a critical barrier to the safe deployment of deep learning in real-time virtual sensing, particularly in high-stakes domains where sparse, noisy, or non-collocated sensor data are the norm. We…

Mojo is an emerging programming language built on MLIR (Multi-Level Intermediate Representation) and supports JIT (Just-in-Time) compilation. It enables transparent hardware-specific optimizations (e.g., for CPUs and GPUs), while allowing…

Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between inference and training workloads. This serial context…

We introduce Ming-Lite-Uni, an open-source multimodal framework featuring a newly designed unified visual generator and a native multimodal autoregressive model tailored for unifying vision and language. Specifically, this project provides…

Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to…

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this…

Robust execution environments are important for addressing key challenges in quantum computing, such as application development, portability, and reproducibility, and help unlock the development of modular quantum programs, driving forward…

Recent advances in imitation learning have enabled robots to perform increasingly complex manipulation tasks in unstructured environments. However, most learned policies rely on discrete action chunking, which introduces discontinuities at…

Control of complex systems involves both system identification and controller design. Deep neural networks have proven to be successful in many identification tasks, however, from model-based control perspective, these networks are…

Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.e. with a batch size of 1 and no replay buffer. While streaming RL…

We introduce MCUBench, a benchmark featuring over 100 YOLO-based object detection models evaluated on the VOC dataset across seven different MCUs. This benchmark provides detailed data on average precision, latency, RAM, and Flash usage for…

We have extended the Falkon lightweight task execution framework to make loosely coupled programming on petascale systems a practical and useful programming model. This work studies and measures the performance factors involved in applying…

Robotic policies deployed in real-world environments often encounter post-training faults, where retraining, exploration, or system identification are impractical. We introduce an inference-time, cerebellar-inspired residual control…

Computational models have become one of the prevalent methods to model complex phenomena. To accurately model complex interactions, such as detailed biomolecular interactions, scientists often rely on multiscale models comprised of several…

We present Mini-BEHAVIOR, a novel benchmark for embodied AI that challenges agents to use reasoning and decision-making skills to solve complex activities that resemble everyday human challenges. The Mini-BEHAVIOR environment is a fast,…

In scenarios where multiple decision-makers operate within a common decision space, each focusing on their own multi-objective optimization problem (e.g., bargaining games), the problem can be modeled as a multi-party multi-objective…

Translating complex reinforcement learning (RL) environments into high-performance implementations has traditionally required months of specialized engineering. We present a closed-loop methodology that produces equivalent high-performance…

Following the design of more efficient blockchain consensus algorithms, the execution layer has emerged as the new performance bottleneck of blockchains, especially under high contention. Current parallel execution frameworks either rely on…