Search Results for author:
Found 27 papers, 13 papers with code
Maximal Clique Based Non-Autoregressive Open Information Extraction
However, the popular OpenIE systems usually output facts sequentially in the way of predicting the next fact conditioned on the previous decoded ones, which enforce an unnecessary order on the facts and involve the error accumulation between autoregressive steps.
MSA-CNN: A Lightweight Multi-Scale CNN with Attention for Sleep Stage Classification
Recent advancements in machine learning-based signal analysis, coupled with open data initiatives, have fuelled efforts in automatic sleep stage classification.
A Survey on Speech Large Language Models
The paper further delves into the training strategies for Speech LLMs, proposing potential solutions based on these findings, and offering valuable insights and references for future research in this domain, as well as LLM applications in multimodal contexts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Survey on Graph Neural Networks for Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends
Remaining Useful Life (RUL) prediction is a critical aspect of Prognostics and Health Management (PHM), aimed at predicting the future state of a system to enable timely maintenance and prevent unexpected failures.
Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation
While SFUDA is well-developed in visual tasks, its application to Time-Series SFUDA (TS-SFUDA) remains limited due to the challenge of transferring crucial temporal dependencies across domains.
Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
Considering the adopted bidirectional alignment will also weaken the anchor image activation if appropriate constraints are missing, we propose a self-supervised regularization module to maintain the reliable activation in discriminative regions and improve the inter-class object boundary recognition for complex images with multiple categories of objects.
Foster Adaptivity and Balance in Learning with Noisy Labels
Moreover, existing methods tend to neglect the class balance in selecting samples, leading to biased model performance.
TEGEE: Task dEfinition Guided Expert Ensembling for Generalizable and Few-shot Learning
Our framework employs a dual 3B model approach, with each model assigned a distinct role: one focuses on task definition extraction, while the other handles learning from demonstrations.
K-Link: Knowledge-Link Graph from LLMs for Enhanced Representation Learning in Multivariate Time-Series Data
To capture these dependencies, Graph Neural Networks (GNNs) have emerged as powerful tools, yet their effectiveness is restricted by the quality of graph construction from MTS data.
On Robustness and Generalization of ML-Based Congestion Predictors to Valid and Imperceptible Perturbations
Namely, we show that when a small number of cells (e. g. 1%-5% of cells) have their positions shifted such that a measure of global congestion is guaranteed to remain unaffected (e. g. 1% of the design adversarially shifted by 0. 001% of the layout space results in a predicted decrease in congestion of up to 90%, while no change in congestion is implied by the perturbation).
SEA++: Multi-Graph-based High-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to reduce domain discrepancy at both the local and global sensor levels.
Graph-Aware Contrasting for Multivariate Time-Series Classification
As MTS data typically originate from multiple sensors, ensuring spatial consistency becomes essential for the overall performance of contrastive learning on MTS data.
Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data
For graph construction, we design a decay graph to connect sensors across all timestamps based on their temporal distances, enabling us to fully model the ST dependencies by considering the correlations between DEDT.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
Assessment of Reinforcement Learning for Macro Placement
We provide open, transparent implementation and assessment of Google Brain's deep reinforcement learning approach to macro placement and its Circuit Training (CT) implementation in GitHub.
Intellectual Property Evaluation Utilizing Machine Learning
Intellectual properties is increasingly important in the economic development.
Document-Level Event Extraction via Human-Like Reading Process
Meanwhile, rough reading is explored in a multi-round manner to discover undetected events, thus the multi-events problem is handled.
GenReg: Deep Generative Method for Fast Point Cloud Registration
To solve this challenge, we propose a new data-driven registration algorithm by investigating deep generative neural networks to point cloud registration.
Distilling Holistic Knowledge with Graph Neural Networks
The holistic knowledge is represented as a unified graph-based embedding by aggregating individual knowledge from relational neighborhood samples with graph neural networks, the student network is learned by distilling the holistic knowledge in a contrastive manner.
Discontinuous Named Entity Recognition as Maximal Clique Discovery
Named entity recognition (NER) remains challenging when entity mentions can be discontinuous.
Duality between two generalized Aubry-Andre models with exact mobility edges
A mobility edge (ME) in energy separating extended from localized states is a central concept in understanding various fundamental phenomena like the metal-insulator transition in disordered systems.
Disordered Systems and Neural Networks
TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking
To mitigate the issue, we propose in this paper a one-stage joint extraction model, namely, TPLinker, which is capable of discovering overlapping relations sharing one or both entities while immune from the exposure bias.
Ranked #2 on
Relation Extraction
on NYT11-HRL
ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution
For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels.
Edge corona product as an approach to modeling complex simplical networks
Many graph products have been applied to generate complex networks with striking properties observed in real-world systems.
Discrete Mathematics Social and Information Networks
Deep Bi-Dense Networks for Image Super-Resolution
In this way, feature information propagates from a single dense block to all subsequent blocks, instead of to a single successor.
Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning
Automatic essay scoring (AES) is the task of assigning grades to essays without human interference.
Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture
The cost aggregation sub-architecture is realized by a two-stream network: one for the generation of cost aggregation proposals, the other for the selection of the proposals.
