Search Results for author:
Found 47 papers, 19 papers with code
UrbanSense:AFramework for Quantitative Analysis of Urban Streetscapes leveraging Vision Large Language Models
To address this, we propose a multimodal research framework based on vision-language models, enabling automated and scalable analysis of urban streetscape style differences.
FloorplanMAE:A self-supervised framework for complete floorplan generation from partial inputs
Experimental results show that the FloorplanMAE model can generate high-quality complete floor plans from incomplete partial plans.
ArchiLense: A Framework for Quantitative Analysis of Architectural Styles Based on Vision Large Language Models
Architectural cultures across regions are characterized by stylistic diversity, shaped by historical, social, and technological contexts in addition to geograph-ical conditions.
Integrating Building Thermal Flexibility Into Distribution System: A Privacy-Preserved Dispatch Approach
Specifically, we first develop an optimal dispatch model for the distribution system integrating buildings, which can be extended to other storage-like flexibility resources.
Fast Critical Clearing Time Calculation for Power Systems with Synchronous and Asynchronous Generation
The increasing penetration of renewables is replacing traditional synchronous generation in modern power systems with low-inertia asynchronous converter-interfaced generators (CIGs).
A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models
Traditional Reinforcement Learning (RL) suffers from replicating human-like behaviors, generalizing effectively in multi-agent scenarios, and overcoming inherent interpretability issues. These tasks are compounded when deep environment understanding, agent coordination and dynamic optimization are required.
On the Data-Driven Modeling of Price-Responsive Flexible Loads: Formulation and Algorithm
The flexible loads in power systems, such as interruptible and transferable loads, are critical flexibility resources for mitigating power imbalances.
Dynamic Energy Flow Analysis of Integrated Electricity and Gas Systems: A Semi-Analytical Approach
Ensuring the safe and reliable operation of integrated electricity and gas systems (IEGS) requires dynamic energy flow (DEF) simulation tools that achieve high accuracy and computational efficiency.
MindAligner: Explicit Brain Functional Alignment for Cross-Subject Visual Decoding from Limited fMRI Data
Brain decoding aims to reconstruct visual perception of human subject from fMRI signals, which is crucial for understanding brain's perception mechanisms.
Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models
We introduce Sigma, an efficient large language model specialized for the system domain, empowered by a novel architecture including DiffQKV attention, and pre-trained on our meticulously collected system domain data.
Comparative Analysis of Control Observer-Based Methods for State Estimation of Lithium-Ion Batteries in Practical Scenarios
To pave their way, this study performs a comprehensive and systematic evaluation of four main categories of control observer-based methods in different practical scenarios considering estimation accuracy, computational time convergence speed, stability, and robustness against measurement uncertainties.
Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation
Experimental results demonstrate the effectiveness of our approach, achieving a 5% absolute performance improvement on Leandojo benchmark.
Automated Proof Generation for Rust Code via Self-Evolution
SAFE also re-purposes the large number of synthesized incorrect proofs to train the self-debugging capability of the fine-tuned models, empowering them to fix incorrect proofs based on the verifier's feedback.
Quantify Gas-to-Power Fault Propagation Speed:A Semi-Implicit Simulation Approach
Thirdly, to accurately locate the simulation events, which can not be predicted a priori, we propose a critical-time-location strategy based on the continuous Runge-Kutta approach.
Contextualized Data-Wrangling Code Generation in Computational Notebooks
With CoCoMine, we construct CoCoNote, a dataset containing 58, 221 examples for Contextualized Data-wrangling Code generation in Notebooks.
AutoVerus: Automated Proof Generation for Rust Code
AutoVerus uses LLM to automatically generate correctness proof for Rust code.
Nonlinear PDE Constrained Optimal Dispatch of Gas and Power: A Global Linearization Approach
To address it, we propose a globally linearized gas network model based on the Koopman operator theory, avoiding the commonly used local linearization and spatial discretization.
High Performance Im2win and Direct Convolutions using Three Tensor Layouts on SIMD Architectures
We compare the optimized im2win convolution with the direct convolution and PyTorch's im2col-based convolution across the aforementioned layouts on SIMD machines.
Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection
Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images.
Ranked #1 on
Multi-class Anomaly Detection
on MVTec AD
Absolute-Unified Multi-Class Anomaly Detection via Class-Agnostic Distribution Alignment
We propose Class-Agnostic Distribution Alignment (CADA) to align the mismatched score distribution of each implicit class without knowing class information, which enables unified anomaly detection for all classes and samples.
Multi-class Anomaly Detection
Unsupervised Anomaly Detection
On the Solution Uniqueness of Data-Driven Modeling of Flexible Loads (with Supplementary Material)
To address this, we analyze the structural and practical identifiability of the PFL model, deriving the dataset condition that guarantees the solution uniqueness.
GAgent: An Adaptive Rigid-Soft Gripping Agent with Vision Language Models for Complex Lighting Environments
This paper introduces GAgent: an Gripping Agent designed for open-world environments that provides advanced cognitive abilities via VLM agents and flexible grasping abilities with variable stiffness soft grippers.
Semi-implicit Continuous Newton Method for Power Flow Analysis
Explicit CNMs are prone to non-convergence issues due to their limited stable region, while implicit CNMs introduce additional iteration-loops of nonlinear equations.
Competition-Level Problems are Effective LLM Evaluators
Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about these abilities and the potential data contamination problem recently.
Privacy-Preserved Aggregate Thermal Dynamic Model of Buildings
The thermal inertia of buildings brings considerable flexibility to the heating and cooling load, which is known to be a promising demand response resource.
Enhancing Large Language Models in Coding Through Multi-Perspective Self-Consistency
We propose the Multi-Perspective Self-Consistency (MPSC) framework incorporating both inter- and intra-consistency across outputs from multiple perspectives.
Aggregate Model of District Heating Network for Integrated Energy Dispatch: A Physically Informed Data-Driven Approach
Second, we propose a physics-informed estimator for the AGM that is robust to low-quality measurements, in which the physical constraints associated with the parameter normalization and sparsity are embedded to improve the accuracy and robustness.
Constructing Multilingual Code Search Dataset Using Neural Machine Translation
Code search is a task to find programming codes that semantically match the given natural language queries.
Im2win: An Efficient Convolution Paradigm on GPU
Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the neural network.
Im2win: Memory Efficient Convolution On SIMD Architectures
However, the im2col data transformation can lead to at least 2$\times$ memory footprint compared to not using data transformation at all, thus limiting the size of neural network models running on memory-limited systems.
ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction
Most advanced unsupervised anomaly detection (UAD) methods rely on modeling feature representations of frozen encoder networks pre-trained on large-scale datasets, e. g. ImageNet.
Code Execution with Pre-trained Language Models
Code execution is a fundamental aspect of programming language semantics that reflects the exact behavior of the code.
AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models
Impressively, GPT-4 surpasses average human performance on SAT, LSAT, and math competitions, attaining a 95% accuracy rate on the SAT Math test and a 92. 5% accuracy on the English test of the Chinese national college entrance exam.
TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs
On the other hand, there are also many existing models and systems (symbolic-based or neural-based) that can do some domain-specific tasks very well.
Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation
Our CGTP framework is an end to end and interpretable model, including three main stages: context encoding, goal interactive prediction and trajectory interactive prediction.
Automating Code Review Activities by Large-Scale Pre-training
In this research, we focus on utilizing pre-training techniques for the tasks in the code review scenario.
ReACC: A Retrieval-Augmented Code Completion Framework
Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development.
UniXcoder: Unified Cross-Modal Pre-training for Code Representation
Furthermore, we propose to utilize multi-modal contents to learn representation of code fragment with contrastive learning, and then align representations among programming languages using a cross-modal generation task.
GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges
However, although numerous algorithms are proposed based on fundus images or OCT volumes in computer-aided diagnosis, there are still few methods leveraging both of the modalities for the glaucoma assessment.
Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax Hierarchy
While there are many efforts to extend the context window, we introduce an architecture-independent approach for leveraging the syntactic hierarchies of source code for incorporating entire file-level context into a fixed-length window.
CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation
Benchmark datasets have a significant impact on accelerating research in programming language tasks.
Ranked #1 on
Cloze Test
on CodeXGLUE - CT-maxmin
CodeBLEU: a Method for Automatic Evaluation of Code Synthesis
Evaluation metrics play a vital role in the growth of an area as it defines the standard of distinguishing between good and bad models.
GraphCodeBERT: Pre-training Code Representations with Data Flow
Instead of taking syntactic-level structure of code like abstract syntax tree (AST), we use data flow in the pre-training stage, which is a semantic-level structure of code that encodes the relation of "where-the-value-comes-from" between variables.
Ranked #3 on
Type prediction
on ManyTypes4TypeScript
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
Analysis of regularized Nyström subsampling for regression functions of low smoothness
This paper studies a Nystr\"om type subsampling approach to large kernel learning methods in the misspecified case, where the target function is not assumed to belong to the reproducing kernel Hilbert space generated by the underlying kernel.
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies?
