Search Results for author:
Found 74 papers, 29 papers with code
Pi-GPS: Enhancing Geometry Problem Solving by Unleashing the Power of Diagrammatic Information
Geometry problem solving has garnered increasing attention due to its potential applications in intelligent education field.
DataMan: Data Manager for Pre-training Large Language Models
In this paper, we train a Data Manager (DataMan) to learn quality ratings and domain recognition from pointwise rating, and use it to annotate a 447B token pre-training corpus with 14 quality ratings and domain type.
Category-free Out-of-Distribution Node Detection with Feature Resonance
Detecting out-of-distribution (OOD) nodes in the graph-based machine-learning field is challenging, particularly when in-distribution (ID) node multi-category labels are unavailable.
D.Va: Validate Your Demonstration First Before You Use It
In-context learning (ICL) has demonstrated significant potential in enhancing the capabilities of large language models (LLMs) during inference.
Towards Robust Incremental Learning under Ambiguous Supervision
Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i. e., label ambiguity and catastrophic forgetting.
Privacy-Preserving Distributed Defense Framework for DC Microgrids Against Exponentially Unbounded False Data Injection Attacks
This paper introduces a novel, fully distributed control framework for DC microgrids, enhancing resilience against exponentially unbounded false data injection (EU-FDI) attacks.
AIGT: AI Generative Table Based on Prompt
Tabular data, which accounts for over 80% of enterprise data assets, is vital in various fields.
A Survey of Open-Source Power System Dynamic Simulators with Grid-Forming Inverter for Machine Learning Applications
The emergence of grid-forming (GFM) inverter technology and the increasing role of machine learning in power systems highlight the need for evaluating the latest dynamic simulators.
Beyond Tree Models: A Hybrid Model of KAN and gMLP for Large-Scale Financial Tabular Data
However, financial datasets in the industry often encounter some challenges, such as data heterogeneity, the predominance of numerical features and the large scale of the data, which can range from tens of millions to hundreds of millions of records.
From Laws to Motivation: Guiding Exploration through Law-Based Reasoning and Rewards
Large Language Models (LLMs) and Reinforcement Learning (RL) are two powerful approaches for building autonomous agents.
Neural Network Certification Informed Power System Transient Stability Preventive Control with Renewable Energy
Existing machine learning-based surrogate modeling methods for transient stability constrained-optimal power flow (TSC-OPF) lack certifications in the presence of unseen disturbances or uncertainties.
TableGPT2: A Large Multimodal Model with Tabular Data Integration
In response, we introduce TableGPT2, a model rigorously pre-trained and fine-tuned with over 593. 8K tables and 2. 36M high-quality query-table-output tuples, a scale of table-related data unprecedented in prior research.
Navigate Complex Physical Worlds via Geometrically Constrained LLM
To enhance the comprehension of geometric and spatial relationships in the complex physical world, the study introduces a set of geometric conventions and develops a workflow based on multi-layer graphs and multi-agent system frameworks.
A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
In our work, to investigate the reasoning patterns of o1, we compare o1 with existing Test-time Compute methods (BoN, Step-wise BoN, Agent Workflow, and Self-Refine) by using OpenAI's GPT-4o as a backbone on general reasoning benchmarks in three domains (i. e., math, coding, commonsense reasoning).
Comparative Study of Data-driven Area Inertia Estimation Approaches on WECC Power Systems
With the increasing integration of inverter-based resources into the power grid, there has been a notable reduction in system inertia, potentially compromising frequency stability.
A Review of Safe Reinforcement Learning Methods for Modern Power Systems
Due to the availability of more comprehensive measurement data in modern power systems, there has been significant interest in developing and applying reinforcement learning (RL) methods for operation and control.
FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
Motivated by this, we formalize different formats of workflow knowledge and present FlowBench, the first benchmark for workflow-guided planning.
On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem.
DORY: Deliberative Prompt Recovery for LLM
Prompt recovery in large language models (LLMs) is crucial for understanding how LLMs work and addressing concerns regarding privacy, copyright, etc.
Data Contamination Calibration for Black-box LLMs
The rapid advancements of Large Language Models (LLMs) tightly associate with the expansion of the training data size.
Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
In this work, we investigate a more practical and universal attack that does not require the presence of a target model and demonstrate that the high-dimensional text embedding space inherently contains NSFW concepts that can be exploited to generate harmful images.
Pre-Trained Model Recommendation for Downstream Fine-tuning
As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task.
RECOST: External Knowledge Guided Data-efficient Instruction Tuning
When it comes to datasets synthesized by LLMs, a common scenario in this field, dirty samples will even be selected with a higher probability than other samples.
Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach
To address this challenge, our research presents a novel framework that harnesses the potential of Deep Reinforcement Learning (DRL), specifically utilizing the Importance Weighted Actor-Learner Architecture (IMPALA) algorithm, executed on the RAY platform.
Energy-based Automated Model Evaluation
The core of the MDE is to establish a meta-distribution statistic, on the information (energy) associated with individual samples, then offer a smoother representation enabled by energy-based learning.
3D-PreMise: Can Large Language Models Generate 3D Shapes with Sharp Features and Parametric Control?
Recent advancements in implicit 3D representations and generative models have markedly propelled the field of 3D object generation forward.
Targeted Representation Alignment for Open-World Semi-Supervised Learning
Open-world Semi-Supervised Learning aims to classify unlabeled samples utilizing information from labeled data while unlabeled samples are not only from the labeled known categories but also from novel categories previously unseen.
Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation
To cope with this problem we propose a novel PU learning framework namely Latent Group-Aware Meta Disambiguation (LaGAM) which incorporates a hierarchical contrastive learning module to extract the underlying grouping semantics within PU data and produce compact representations.
Cyber-Physical Testbed Integrating RTAC with RTDS for Game-Theoretic Topology Control Under Load Altering Attacks
This paper introduces a cyber-physical testbed that integrates the Real-Time Digital Simulator (RTDS) with the Real-Time Automation Controller (RTAC) to enhance cybersecurity in electrical distribution networks.
FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models
While copious solutions, such as active learning for small language models (SLMs) and prevalent in-context learning in the era of large language models (LLMs), have been proposed and alleviate the labeling burden to some extent, their performances are still subject to human intervention.
Voltage-Dependent Electromechanical Wave Propagation Modeling for Dynamic Stability Analysis in Power Systems
Analyzing these characteristics enables the assessment of the impacts of EMW on the performance of the protection system.
Revisiting the Knowledge Injection Frameworks
Briefly, the core of this technique is rooted in an ideological emphasis on the pruning and purification of the external knowledge base to be injected into LLMs.
Deep Reinforcement Learning-Enabled Adaptive Forecasting-Aided State Estimation in Distribution Systems with Multi-Source Multi-Rate Data
Distribution system state estimation (DSSE) is paramount for effective state monitoring and control.
Towards Domain-Specific Features Disentanglement for Domain Generalization
Distributional shift between domains poses great challenges to modern machine learning algorithms.
Resilient Model-Free Asymmetric Bipartite Consensus for Nonlinear Multi-Agent Systems against DoS Attacks
In this letter, we study an unified resilient asymmetric bipartite consensus (URABC) problem for nonlinear multi-agent systems with both cooperative and antagonistic interactions under denial-of-service (DoS) attacks.
CAME: Contrastive Automated Model Evaluation
In this work, we propose Contrastive Automatic Model Evaluation (CAME), a novel AutoEval framework that is rid of involving training set in the loop.
TableGPT: Towards Unifying Tables, Nature Language and Commands into One GPT
Tables are prevalent in real-world databases, requiring significant time and effort for humans to analyze and manipulate.
Towards Cross-Table Masked Pretraining for Web Data Mining
Tabular data pervades the landscape of the World Wide Web, playing a foundational role in the digital architecture that underpins online information.
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Large language models (LLMs) with memory are computationally universal.
Maybe Only 0.5% Data is Needed: A Preliminary Exploration of Low Training Data Instruction Tuning
Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions.
Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility
With most of the related literature in the era of LLM uncharted, we propose an automated workflow that copes with an upscaled number of queries/responses.
Latent Processes Identification From Multi-View Time Series
Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a. k. a.
Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
Our method does not require external triggers and ensures correct labeling of poisoned samples, improving the stealthy nature of the backdoor attack.
Better Sign Language Translation with Monolingual Data
Sign language translation (SLT) systems, which are often decomposed into video-to-gloss (V2G) recognition and gloss-to-text (G2T) translation through the pivot gloss, heavily relies on the availability of large-scale parallel G2T pairs.
Controllable Textual Inversion for Personalized Text-to-Image Generation
The recent large-scale generative modeling has attained unprecedented performance especially in producing high-fidelity images driven by text prompts.
Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"
In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts.
Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
Further, we posit that the crucial merit of FETCH is its transferability where the yielded policy network trained on a variety of datasets is indeed capable to enact feature engineering on unseen data, without requiring additional exploration.
iDAG: Invariant DAG Searching for Domain Generalization
In this work, we first characterize that this failure of conventional ML models in DG is attributed to an inadequate identification of causal structures.
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation
Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme.
Ranked #2 on
Multimodal Machine Translation
on Multi30K
SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning
Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth.
Topology Change Aware Data-Driven Probabilistic Distribution State Estimation Based on Gaussian Process
Abstract—This paper addresses the distribution system state estimation (DSSE) with unknown topology change.
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
To overcome the potential side effect of excessive clean set selection procedure, we further devise a novel SSL framework that is able to train balanced and unbiased classifiers on the separated clean and noisy samples.
Ranked #1 on
Learning with noisy labels
on CIFAR-10N-Worst
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
The aspect-based sentiment analysis (ABSA) is a fine-grained task that aims to determine the sentiment polarity towards targeted aspect terms occurring in the sentence.
Ranked #6 on
Aspect-Based Sentiment Analysis (ABSA)
on SemEval-2014 Task-4
(using extra training data)
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
Robust Data-Driven Linear Power Flow Model with Probability Constrained Worst-Case Errors
To limit the probability of unacceptable worst-case linearization errors that might yield risks for power system operations, this letter proposes a robust data-driven linear power flow (RD-LPF) model.
Deps-SAN: Neural Machine Translation with Dependency-Scaled Self-Attention Network
However, succeeding researches pointed out that limited by the uncontrolled nature of attention computation, the NMT model requires an external syntax to capture the deep syntactic awareness.
Contrastive Label Disambiguation for Partial Label Learning
Partial label learning (PLL) is an important problem that allows each training example to be labeled with a coarse candidate set, which well suits many real-world data annotation scenarios with label ambiguity.
VeniBot: Towards Autonomous Venipuncture with Semi-supervised Vein Segmentation from Ultrasound Images
In the modern medical care, venipuncture is an indispensable procedure for both diagnosis and treatment.
VeniBot: Towards Autonomous Venipuncture with Automatic Puncture Area and Angle Regression from NIR Images
For the automation, we focus on the positioning part and propose a Dual-In-Dual-Out network based on two-step learning and two-task learning, which can achieve fully automatic regression of the suitable puncture area and angle from near-infrared(NIR) images.
A robust extended Kalman filter for power system dynamic state estimation using PMU measurements
Simulations carried out on the IEEE 39-bus test system reveal that our robust extended Kalman filter exhibits good tracking capabilities under Gaussian process and observation noise while suppressing observation outliers, even in position of leverage.
Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.
Data-Driven Assisted Chance-Constrained Energy and Reserve Scheduling with Wind Curtailment
Case studies performed on the PJM 5-bus and IEEE 118-bus systems demonstrate that the proposed method is capable of accurately accounting the influence of wind curtailment dispatch in CCO.
Systems and Control Systems and Control
PIANOTREE VAE: Structured Representation Learning for Polyphonic Music
The dominant approach for music representation learning involves the deep unsupervised model family variational autoencoder (VAE).
Model-Free Voltage Regulation of Unbalanced Distribution Network Based on Surrogate Model and Deep Reinforcement Learning
Accurate knowledge of the distribution system topology and parameters is required to achieve good voltage controls, but this is difficult to obtain in practice.
Distributed Voltage Regulation of Active Distribution System Based on Enhanced Multi-agent Deep Reinforcement Learning
This paper proposes a data-driven distributed voltage control approach based on the spectrum clustering and the enhanced multi-agent deep reinforcement learning (MADRL) algorithm.
Data-driven Optimal Power Flow: A Physics-Informed Machine Learning Approach
This paper proposes a data-driven approach for optimal power flow (OPF) based on the stacked extreme learning machine (SELM) framework.
BIG-bench Machine Learning
Physics-informed machine learning
Roles of Dynamic State Estimation in Power System Modeling, Monitoring and Operation
Power system dynamic state estimation (DSE) remains an active research area.
Prediction Under Uncertainty with Error Encoding Networks
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty.
Prediction Under Uncertainty with Error-Encoding Networks
In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty.
Disentangling factors of variation in deep representation using adversarial training
The only available source of supervision during the training process comes from our ability to distinguish among different observations belonging to the same category.
Disentangling factors of variation in deep representations using adversarial training
During training, the only available source of supervision comes from our ability to distinguish among different observations belonging to the same class.
Energy-based Generative Adversarial Network
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold and higher energies to other regions.
Character-level Convolutional Networks for Text Classification
This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification.
Ranked #16 on
Sentiment Analysis
on Yelp Fine-grained classification
Stacked What-Where Auto-encoders
The objective function includes reconstruction terms that induce the hidden states in the Deconvnet to be similar to those of the Convnet.
