Related papers: From Ad-Hoc Scripts to Orchestrated Pipelines: Arc…
Transformer models serve as the backbone of many state-ofthe-art language models, and most use the scaled dot-product attention (SDPA) mechanism to capture relationships between tokens. However, the straightforward implementation of SDPA…
We propose the joint graph attention neural network (GAT), clustering with adaptive neighbors (CAN) and probabilistic graphical model for dynamic power flow analysis and fault characteristics. In fact, computational efficiency is the main…
Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep…
With the increasing frequency and sophistication of Distributed Denial of Service (DDoS) attacks, it has become critical to develop more efficient and interpretable detection methods. Traditional detection systems often struggle with…
In this paper, we propose the integration of approaches to Engineering Multi-Agent Systems (EMAS) with the Developer Operations (DevOps) industry best practice. Whilst DevOps facilitates the organizational autonomy of software teams, as…
IOTA Tangle is a distributed ledger technology (DLT), primarily designed for Internet-of-Things (IoT) networks and applications. IOTA Tangle utilizes a direct acyclic graph (DAG) structure for the ledger, with its protocol offering features…
The pre-train then fine-tune approach has advanced GNNs by enabling general knowledge capture without task-specific labels. However, an objective gap between pre-training and downstream tasks limits its effectiveness. Recent graph prompting…
The construction of Supervised Fine-Tuning (SFT) datasets is a critical yet under-theorized stage in the post-training of Large Language Models (LLMs), as prevalent practices often rely on heuristic aggregation without a systematic…
Spatial dataflow architectures such as reconfigurable dataflow accelerators (RDA) can provide much higher performance and efficiency than CPUs and GPUs. In particular, vectorized reconfigurable dataflow accelerators (vRDA) in recent…
The European Union Deforestation Regulation (EUDR) requires companies to prove their products do not contribute to deforestation, creating a critical demand for precise, asset-level environmental impact data. Current databases lack the…
This paper argues for an accelerator development toolchain that takes into account the whole system containing the accelerator. With whole-system visibility, the toolchain can better assist accelerator scoping and composition in the context…
Leveraging labelled data from multiple domains to enable prediction in another domain without labels is a significant, yet challenging problem. To address this problem, we introduce the framework DAPDAG (\textbf{D}omain \textbf{A}daptation…
Many real-world scientific workflows can be represented by a Directed Acyclic Graph (DAG), where each node represents a task and a directed edge signifies a dependency between two tasks. Due to the increasing computational resource…
Many scientific workflows can be represented by a Directed Acyclic Graph (DAG) where each node represents a task, and there will be a directed edge between two tasks if and only if there is a dependency relationship between the two i.e. the…
This work presents Drake, a dynamic executive for temporal plans with choice. Dynamic plan execution strategies allow an autonomous agent to react quickly to unfolding events, improving the robustness of the agent. Prior work developed…
Distributed Ledger Technology (DLT) is promising to become the foundation of many decentralised systems. However, the unbalanced and unregulated network layout contributes to the inefficiency of DLT especially in the Internet of Things…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
Traffic forecasting is crucial for public safety and resource optimization, yet is very challenging due to three aspects: i) current existing works mostly exploit intricate temporal patterns (e.g., the short-term thunderstorm and long-term…
Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still…
Scientific and engineering verticals often suffer from data scarcity and strict executability requirements: models must generate not only fluent text, but also syntactically valid, tool-compilable scripts. We present a schema-first…