K. L. Han
YOU?
Author Swipe
View article: FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation
FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation Open
Data-driven modeling of fluid dynamics has advanced rapidly with neural PDE solvers, yet a fair and strong benchmark remains fragmented due to the absence of unified PDE datasets and standardized evaluation protocols. Although architectura…
View article: Enhancing wheat quality through color sorting: a novel approach for classifying kernels based on vitreousness
Enhancing wheat quality through color sorting: a novel approach for classifying kernels based on vitreousness Open
Introduction Wheat is a major food crop used in producing bread, noodles, and cookies. Kernel vitreousness, closely related to protein content, is key to determining wheat’s processing purpose. Traditionally, vitreousness is visually asses…
View article: Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models
Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models Open
Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by decomposing complex problems into step-by-step solutions, improving performance on reasoning tasks. However, current CoT disclosure policies vary widely across diffe…
View article: Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction
Concept-Reversed Winograd Schema Challenge: Evaluating and Improving Robust Reasoning in Large Language Models via Abstraction Open
While Large Language Models (LLMs) have showcased remarkable proficiency in reasoning, there is still a concern about hallucinations and unreliable reasoning issues due to semantic associations and superficial logical chains. To evaluate t…
View article: Exploring Correlations of Self-Supervised Tasks for Graphs
Exploring Correlations of Self-Supervised Tasks for Graphs Open
Graph self-supervised learning has sparked a research surge in training informative representations without accessing any labeled data. However, our understanding of graph self-supervised learning remains limited, and the inherent relation…
View article: BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations
BrainODE: Dynamic Brain Signal Analysis via Graph-Aided Neural Ordinary Differential Equations Open
Brain network analysis is vital for understanding the neural interactions regarding brain structures and functions, and identifying potential biomarkers for clinical phenotypes. However, widely used brain signals such as Blood Oxygen Level…
View article: Can GNN be Good Adapter for LLMs?
Can GNN be Good Adapter for LLMs? Open
Recently, large language models (LLMs) have demonstrated superior capabilities in understanding and zero-shot learning on textual data, promising significant advances for many text-related domains. In the graph domain, various real-world s…
View article: STCF conceptual design report (Volume 1): Physics & detector
STCF conceptual design report (Volume 1): Physics & detector Open
The super τ -charm facility (STCF) is an electron–positron collider proposed by the Chinese particle physics community. It is designed to operate in a center-of-mass energy range from 2 to 7 GeV with a peak luminosity of 0.5 × 10 35 cm −2 …
View article: GraphLLM: Boosting Graph Reasoning Ability of Large Language Model
GraphLLM: Boosting Graph Reasoning Ability of Large Language Model Open
The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to …
View article: Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs
Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs Open
Text-attributed Graphs (TAGs) are commonly found in the real world, such as social networks and citation networks, and consist of nodes represented by textual descriptions. Currently, mainstream machine learning methods on TAGs involve a t…
View article: A feasibility study of the reflection readout method of Resistive-Plate Chambers
A feasibility study of the reflection readout method of Resistive-Plate Chambers Open
The conventional readout method of the RPC detector uses two sets of orthogonal readout strips placed at the both sides of the gas gap to collect signals of opposite polarities to obtain space points. A new readout method utilizing the ref…