Search Results for author:
Found 22 papers, 6 papers with code
CodeV: Issue Resolving with Visual Data
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks.
Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
Training linear classifiers on probing tasks is a principle approach to denote the vector of a certain concept in the representation space.
Deep Computer Vision for Solar Physics Big Data: Opportunities and Challenges
With recent missions such as advanced space-based observatories like the Solar Dynamics Observatory (SDO) and Parker Solar Probe, and ground-based telescopes like the Daniel K. Inouye Solar Telescope (DKIST), the volume, velocity, and variety of data have made solar physics enter a transformative era as solar physics big data (SPBD).
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia.
Global-local Fourier Neural Operator for Accelerating Coronal Magnetic Field Model
The goal of this study is to accelerate coronal magnetic field simulation using deep learning, specifically, the Fourier Neural Operator (FNO).
CodeS: Natural Language to Code Repository via Multi-Layer Sketch
For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.
Towards Uncovering How Large Language Model Works: An Explainability Perspective
Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque.
Can Programming Languages Boost Each Other via Instruction Tuning?
Results demonstrate that programming languages can significantly improve each other.
PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
In this paper, we propose a novel RRTF (Rank Responses to align Test&Teacher Feedback) framework, which can effectively and efficiently boost pre-trained large language models for code generation.
On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee
This paper focuses on two model compression techniques: low-rank approximation and weight pruning in neural networks, which are very popular nowadays.
Linear RNNs Provably Learn Linear Dynamic Systems
We study the learning ability of linear recurrent neural networks with Gradient Descent.
Reinforcement Learning-based Defect Mitigation for Quality Assurance of Additive Manufacturing
Since AM typically fabricates a small number of customized products, this paper aims to create an online learning-based strategy to mitigate the new defects in AM process while minimizing the number of samples needed.
Anomaly Detection in Additive Manufacturing Processes using Supervised Classification with Imbalanced Sensor Data based on Generative Adversarial Network
It is beneficial to generate effective artificial sample data for the abnormal states to make a more balanced training set.
A Novel Sparse Bayesian Learning and Its Application to Fault Diagnosis for Multistation Assembly Systems
Fault diagnosis is to identify process faults that cause the excessive dimensional variation of the product using dimensional measurements.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
Self-scalable Tanh (Stan): Faster Convergence and Better Generalization in Physics-informed Neural Networks
To address this, a Self-scalable tanh (Stan) activation function is proposed for the PINNs.
Smooth Robust Tensor Completion for Background/Foreground Separation with Missing Pixels: Novel Algorithm with Convergence Guarantee
The objective of this study is to address the problem of background/foreground separation with missing pixels by combining the video acquisition, video recovery, background/foreground separation into a single framework.
On the Provable Generalization of Recurrent Neural Networks
In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$.
Robust Tensor Principal Component Analysis: Exact Recovery via Deterministic Model
Tensor, also known as multi-dimensional array, arises from many applications in signal processing, manufacturing processes, healthcare, among others.
Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?
In this paper, we follow this line to study the topology (sub-level sets) of the loss landscape of deep ReLU neural networks with a skip connection and theoretically prove that the skip connection network inherits the good properties of the two-layer network and skip connections can help to control the connectedness of the sub-level sets, such that any local minima worse than the global minima of some two-layer ReLU network will be very ``shallow".
Second-Order Convergence of Asynchronous Parallel Stochastic Gradient Descent: When Is the Linear Speedup Achieved?
This may have a negative influence on the convergence of the algorithm.
Solving Pictorial Jigsaw Puzzle by Stigmergy-inspired Internet-based Human Collective Intelligence
And through feedback, each player is provided with personalized feedback information based on the current COG and the player's exploration result, in order to accelerate his/her puzzle-solving process.
