Related papers: A Particular Bug Trap: Execution Replay Using Virt…
A number of trusted execution environments (TEEs) have been proposed by both academia and industry. However, most of them require specific hardware or firmware changes and are bound to specific hardware vendors (such as Intel, AMD, ARM, and…
This is the era of High Performance Computing (HPC). There is a great demand of the best performance evaluation techniques for the file and storage systems. The task of evaluation is both necessary and hard. It gives in depth analysis of…
Irregular embedding lookups are a critical bottleneck in recommender models, sparse large language models, and graph learning models. In this paper, we first demonstrate that, by offloading these lookups to specialized access units,…
The recently completed research project DEEP-ER has developed a variety of hardware and software technologies to improve the I/O capabilities of next generation high-performance computers, and to enable applications recovering from the…
Continual lifelong learning is an machine learning framework inspired by human learning, where learners are trained to continuously acquire new knowledge in a sequential manner. However, the non-stationary nature of streaming training data…
This paper describes the development and verification of a competitive parachute system for Micro Air Vehicles, in particular focusing on verification of the embedded software. We first introduce the overall solution including a system…
Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…
While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that…
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing approaches remain limited: full trajectories are often too…
Participants of the Berlin Summit on Earth Virtualization Engines (EVEs) discussed ideas and concepts to improve our ability to cope with climate change. EVEs aim to provide interactive and accessible climate simulations and data for a wide…
We describe a novel approach for adapting an existing software model checker to perform precise runtime verification. The software under test is allowed to communicate with the wider environment (including the file system and network). The…
IT based scientific research requires high computational resources. The limitation on funding and infrastructure led the high performance computing era from supercomputer to cluster and grid computing technology. Parallel application…
The entity registry system (ERS) is a decentralized entity registry that can be used to replace the Web as a platform for publishing linked data when the latter is not available. In developing countries, where off-line is the default mode…
End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function…
Recently, we can notice a transition to data-driven techniques in Automated Program Repair (APR), in particular towards deep neural networks. This entails training on hundreds of thousands or even millions of non-executable code fragments.…
Ethereum blockchain uses smart contracts (SCs) to implement decentralized applications (dApps). SCs are executed by the Ethereum virtual machine (EVM) running within an Ethereum client. Moreover, the EVM has been widely adopted by other…
Reinforcement Learning (RL) has achieved significant success in application domains such as robotics, games and health care. However, training RL agents is very time consuming. Current implementations exhibit poor performance due to…
Through its affordances, immersive virtual reality (VR) offers a means to apply embodied and external cognition from the physical realm to solving analytical problems that are typically only conceptual. We present an example of executing a…
With the capacity of continual learning, humans can continuously acquire knowledge throughout their lifespan. However, computational systems are not, in general, capable of learning tasks sequentially. This long-standing challenge for deep…
Video Large Language Models (Video-LLMs) have shown strong video understanding, yet their application to long-form videos remains constrained by limited context windows. A common workaround is to compress long videos into a handful of…