Search Results for author:
Found 20 papers, 7 papers with code
DocMEdit: Towards Document-Level Model Editing
Model editing aims to correct errors and outdated knowledge in the Large language models (LLMs) with minimal cost.
EDBench: Large-Scale Electron Density Data for Molecular Modeling
Existing molecular machine learning force fields (MLFFs) generally focus on the learning of atoms, molecules, and simple quantum chemical properties (such as energy and force), but ignore the importance of electron density (ED) $\rho(r)$ in accurately understanding molecular force fields (MFFs).
High-Throughput LLM inference on Heterogeneous Clusters
Secondly, LLM inference instances within a heterogeneous cluster possess varying processing capacities, leading to different processing speeds for handling inference requests.
FAME: Towards Factual Multi-Task Model Editing
To facilitate the application of model editing in real-world scenarios, we propose the challenge of practicality.
MaskMol: Knowledge-guided Molecular Image Pre-Training Framework for Activity Cliffs
Activity cliffs, which refer to pairs of molecules that are structurally similar but show significant differences in their potency, can lead to model representation collapse and make the model challenging to distinguish them.
Expert-Token Resonance: Redefining MoE Routing through Affinity-Driven Active Selection
(3) Theoretical derivation and experimental evidence of reduced expert capacity bounds under dynamic token distribution evolution.
EFSA: Towards Event-Level Financial Sentiment Analysis
In this paper, we extend financial sentiment analysis~(FSA) to event-level since events usually serve as the subject of the sentiment in financial text.
Transform then Explore: a Simple and Effective Technique for Exploratory Combinatorial Optimization with Reinforcement Learning
The technique is originated from physics, but is very effective in enabling RL agents to explore to continuously improve the solutions during test.
Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
Although promising, the dynamics of LEO networks, characterized by the high mobility of satellites and short ground-to-satellite link (GSL) duration, pose unique challenges for FEEL.
LocMoE: A Low-Overhead MoE for Large Language Model Training
However, the performance of MoE is limited by load imbalance and high latency of All-to-All communication, along with relatively redundant computation owing to large expert capacity.
Key Gene Mining in Transcriptional Regulation for Specific Biological Processes with Small Sample Sizes Using Multi-network pipeline Transformer
Gene mining is an important topic in the field of life sciences, but traditional machine learning methods cannot consider the regulatory relationships between genes.
Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially in drug-drug interactions (DDIs).
Bounded KRnet and its applications to density estimation and approximation
In this paper, we develop an invertible mapping, called B-KRnet, on a bounded domain and apply it to density estimation/approximation for data or the solutions of PDEs such as the Fokker-Planck equation and the Keller-Segel equation.
Gradient-enhanced deep neural network approximations
We propose in this work the gradient-enhanced deep neural networks (DNNs) approach for function approximations and uncertainty quantification.
Adaptive deep density approximation for fractional Fokker-Planck equations
To this end, we represent the solution with an explicit PDF model induced by a flow-based deep generative model, simplified KRnet, which constructs a transport map from a simple distribution to the target distribution.
Solving time dependent Fokker-Planck equations via temporal normalizing flow
In this work, we propose an adaptive learning approach based on temporal normalizing flows for solving time-dependent Fokker-Planck (TFP) equations.
SegTime: Precise Time Series Segmentation without Sliding Window
We propose a neural networks approach SegTime that finds precise breakpoints, obviates sliding windows, handles long-term dependencies, and it is insensitive to the label changing frequency.
A general kernel boosting framework integrating pathways for predictive modeling based on genomic data
Predictive modeling based on genomic data has gained popularity in biomedical research and clinical practice by allowing researchers and clinicians to identify biomarkers and tailor treatment decisions more efficiently.
Learning to Identify High Betweenness Centrality Nodes from Scratch: A Novel Graph Neural Network Approach
By training on small-scale networks, the learned model is capable of assigning relative BC scores to nodes for any unseen networks, and thus identifying the highly-ranked nodes.
A pathway-based kernel boosting method for sample classification using genomic data
Most of the methods focus on testing marginal significance of the associations between pathways and clinical phenotypes.
