Related papers: Towards Agentic Defect Reasoning: A Graph-Assisted…
Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted…
In enterprise settings, efficiently retrieving relevant information from large and complex knowledge bases is essential for operational productivity and informed decision-making. This research presents a systematic empirical framework for…
Computational biology offers immense potential for reducing the high costs and protracted cycles of new drug development through adverse drug reaction (ADR) prediction. However, current methods remain impeded by drug data scarcity-induced…
We propose a learning-based method for adaptively generating low probability of detection (LPD) radar waveforms that blend into their operating environment. Our waveforms are designed to follow a distribution that is indistinguishable from…
Laser powder bed fusion (LPBF) holds promise to efficiently produce metal parts. However, LPBF incurs stochastic melt pool (MP) spattering, which would roughen workpiece in-process surface, thus weakening inter-layer bonding and causing…
Memory mechanism is a core component of LLM-based agents, enabling reasoning and knowledge discovery over long-horizon contexts. Existing agent memory systems are typically designed within isolated paradigms (e.g., explicit, parametric, or…
Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools.…
Numerical simulation of the laser powder bed fusion (LPBF) procedure for additive manufacturing (AM) is difficult due to the presence of multiple scales in both time and space, ranging from the part scale (order of millimeters/seconds) to…
Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack the ability to assess the actual synthesis operations, such…
Motivated by the limitations of current spectral analysis methods-such as reliance on single-modality data, limited generalizability, and poor interpretability-we propose a novel multi-modal spectral analysis framework that integrates prior…
Table-based fact verification task aims to verify whether the given statement is supported by the given semi-structured table. Symbolic reasoning with logical operations plays a crucial role in this task. Existing methods leverage programs…
Various Graph Neural Networks (GNNs) have been successful in analyzing data in non-Euclidean spaces, however, they have limitations such as oversmoothing, i.e., information becomes excessively averaged as the number of hidden layers…
The Large Hadron Collider at CERN produces immense volumes of complex data from high-energy particle collisions, demanding sophisticated analytical techniques for effective interpretation. Neural Networks, including Graph Neural Networks,…
Large Language Models (LLMs) are evolving into autonomous agents, yet current "frameless" development--relying on ambiguous natural language without engineering blueprints--leads to critical risks such as scope creep and open-loop failures.…
Marking anatomical landmarks in cephalometric radiography is a critical operation in cephalometric analysis. Automatically and accurately locating these landmarks is a challenging issue because different landmarks require different levels…
Surface defect inspection plays an important role in the process of industrial manufacture and production. Though Convolutional Neural Network (CNN) based defect inspection methods have made huge leaps, they still confront a lot of…
Various industries have produced a large number of documents such as industrial plans, technical guidelines, and regulations that are structurally complex and content-wise fragmented. This poses significant challenges for experts and…
Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures of robustness and generalization. This paper attributes these deficiencies to spurious reasoning, i.e.,…
Laser powder bed fusion (LPBF) is an additive manufacturing (AM) technology. To achieve high product quality, the powder is best spread as a uniform, dense layer. The challenge for LPBF manufacturers is to develop a spreading process that…
Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG…