Search Results for author:
Found 39 papers, 11 papers with code
When Fuzzing Meets LLMs: Challenges and Opportunities
Fuzzing, a widely-used technique for bug detection, has seen advancements through Large Language Models (LLMs).
QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
Subsequently, QuanTest formulates the problem of generating test inputs that maximize the quantum entanglement sufficiency and capture incorrect behaviors of the QNN system as a joint optimization problem and solves it in a gradient-based manner to generate quantum adversarial examples.
Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learning
Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model.
Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation
Meanwhile, while traditional techniques leveraging such semantic information require complex static or dynamic code analysis to obtain features such as data flow and control flow, SeCoT demonstrates that this process can be fully automated via the intrinsic capabilities of LLMs (i. e., in-context learning), while being generalizable and applicable to challenging domains.
At Which Training Stage Does Code Data Help LLMs Reasoning?
Inspired by the great success of code data in training LLMs, we naturally wonder at which training stage introducing code data can really help LLMs reasoning.
UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost.
Vision-based Vineyard Navigation Solution with Automatic Annotation
Autonomous navigation is the key to achieving the full automation of agricultural research and production management (e. g., disease management and yield prediction) using agricultural robots.
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition
With multiple spatial static hypergraphs and dynamic TPH, our network can learn more complete spatial-temporal features.
Adaptive Constraint Partition based Optimization Framework for Large-scale Integer Linear Programming(Student Abstract)
Integer programming problems (IPs) are challenging to be solved efficiently due to the NP-hardness, especially for large-scale IPs.
End-to-End Entity Detection with Proposer and Regressor
Named entity recognition is a traditional task in natural language processing.
Type-supervised sequence labeling based on the heterogeneous star graph for named entity recognition
Named entity recognition is a fundamental task in natural language processing, identifying the span and category of entities in unstructured texts.
NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction
Recently, implicit neural representations have become a promising way to reconstruct surfaces from multiview images due to their high-quality results and simplicity.
Terrain-based vehicle localization using an active suspension system
Second, an algorithm is developed to extract a pitch profile from the road height profile data.
Skeleton-based Action Recognition via Temporal-Channel Aggregation
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps.
Ranked #7 on
Skeleton Based Action Recognition
on N-UCLA
Parameters identification for an inverse problem arising from a binary option using a Bayesian inference approach
We identify the model coefficients from the measured data and attempt to find arbitrage opportunities in different financial markets using a Bayesian inference approach, which is presented as an IOP solution.
Computer Vision for Road Imaging and Pothole Detection: A State-of-the-Art Review of Systems and Algorithms
Computer vision algorithms have been prevalently utilized for 3-D road imaging and pothole detection for over two decades.
Transfer learning for cross-modal demand prediction of bike-share and public transit
The urban transportation system is a combination of multiple transport modes, and the interdependencies across those modes exist.
Medication Error Detection Using Contextual Language Models
Medication errors most commonly occur at the ordering or prescribing stage, potentially leading to medical complications and poor health outcomes.
Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications
To this end, we propose DFLARE, a novel, search-based, black-box testing technique to automatically find triggering inputs that result in deviated behaviors in image classification tasks.
TotalRecall: A Bidirectional Candidates Generation Framework for Large Scale Recommender \& Advertising Systems
Recommender (RS) and Advertising/Marketing Systems (AS) play the key roles in E-commerce companies like Amazaon and Alibaba.
WRICNet:A Weighted Rich-scale Inception Coder Network for Multi-Resolution Remote Sensing Image Change Detection
With the purpose of improving change detection effectiveness of the model in the multi-resolution data set, a weighted rich-scale inception coder network (WRICNet) is proposed in this article, which can make a great fusion of shallow multi-scale features, and deep multi-scale features.
Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
To further improve the robustness of the student, we extend SD to Enhanced Spirit Distillation (ESD) in exploiting a more comprehensive knowledge by introducing the proximity domain which is similar to the target domain for feature extraction.
Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data
Inspired by the ideas of Fine-tuning-based Transfer Learning (FTT) and feature-based knowledge distillation, we propose a new knowledge distillation method for cross-domain knowledge transference and efficient data-insufficient network training, named Spirit Distillation(SD), which allow the student network to mimic the teacher network to extract general features, so that a compact and accurate student network can be trained for real-time semantic segmentation of road scenes.
HDTest: Differential Fuzz Testing of Brain-Inspired Hyperdimensional Computing
Using handwritten digit classification as an example, we show that HDTest can generate thousands of adversarial inputs with negligible perturbations that can successfully fool HDC models.
Market Design for Tradable Mobility Credits
Further, it is more robust in the presence of forecasting errors and non-recurrent events due to the adaptiveness of the market.
Event Stream Super-Resolution via Spatiotemporal Constraint Learning
Therefore, it is imperative to explore the algorithm of event stream super-resolution, which is a non-trivial task due to the sparsity and strong spatio-temporal correlation of the events from an event camera.
Activation Map Adaptation for Effective Knowledge Distillation
Model compression becomes a recent trend due to the requirement of deploying neural networks on embedded and mobile devices.
On the Quality Requirements of Demand Prediction for Dynamic Public Transport
Our results suggest that the optimized performance is mainly affected by the skew of the noise distribution and the presence of infrequently large prediction errors.
Prediction and analysis of Coronavirus Disease 2019
According to the current trend, based on the three models, the total number of people expected to be infected is 49852-57447 in Wuhan, 12972-13405 in non-Hubei areas and 80261-85140 in China respectively.
Populations and Evolution
End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning
This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system.
RNN-Test: Towards Adversarial Testing for Recurrent Neural Network Systems
Compared with the neuron coverage, the proposed state coverage metrics as guidance excel with 4. 17% to 97. 22% higher success (or generation) rate.
Simple is Better: Training an End-to-end Contract Bridge Bidding Agent without Human Knowledge
While playing is relatively easy for modern software, bidding is challenging and requires agents to learn a communication protocol to reach the optimal contract jointly, with their own private information.
Semi-parametric Bayesian variable selection for gene-environment interactions
Existing Bayesian methods for G$\times$E interaction studies are challenged by the high-dimensional nature of the study and the complexity of environmental influences.
Methodology
Towards VQA Models That Can Read
We show that LoRRA outperforms existing state-of-the-art VQA models on our TextVQA dataset.
Ranked #3 on
Visual Question Answering (VQA)
on VizWiz 2018
Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services
This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements.
LEOPARD: Identifying Vulnerable Code for Vulnerability Assessment through Program Metrics
The latter needs the prior knowledge of known vulnerabilities and can only identify similar but not new types of vulnerabilities.
Software Engineering
DLFuzz: Differential Fuzzing Testing of Deep Learning Systems
Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars.
Software Engineering
Pythia v0.1: the Winning Entry to the VQA Challenge 2018
We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2. 0 dataset -- from 65. 67% to 70. 22%.
Ranked #10 on
Visual Question Answering (VQA)
on A-OKVQA
EnFuzz: From Ensemble Learning to Ensemble Fuzzing
For evaluation, we implement EnFuzz , a prototype basing on four strong open-source fuzzers (AFL, AFLFast, AFLGo, FairFuzz), and test them on Google's fuzzing test suite, which consists of widely used real-world applications.
Software Engineering
