Search Results for author:
Found 35 papers, 21 papers with code
Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian
In this paper, we conduct a survey to explore the practitioners' perspectives on code readability in the age of LLMs and investigate the readability of our LLM-based software development agents framework, HULA, by comparing its generated code with human-written code in real-world scenarios.
Eliza: A Web3 friendly AI Agent Operating System
AI Agent, powered by large language models (LLMs) as its cognitive core, is an intelligent agentic system capable of autonomously controlling and determining the execution paths under user's instructions.
BadSFL: Backdoor Attack against Scaffold Federated Learning
Federated learning (FL) enables the training of deep learning models on distributed clients to preserve data privacy.
Human-In-the-Loop Software Development Agents
In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plans and source code for a given task.
PSELDNets: Pre-trained Neural Networks on Large-scale Synthetic Datasets for Sound Event Localization and Detection
Recently, deep neural networks trained on large-scale datasets have achieved remarkable success in the sound event classification (SEC) field, prompting an open question of whether these advancements can be extended to develop general-purpose SELD models.
Direction of Arrival Estimation
Sound Event Localization and Detection
M4Fog: A Global Multi-Regional, Multi-Modal, and Multi-Stage Dataset for Marine Fog Detection and Forecasting to Bridge Ocean and Atmosphere
Marine fog poses a significant hazard to global shipping, necessitating effective detection and forecasting to reduce economic losses.
Multi-Scale Representations by Varying Window Attention for Semantic Segmentation
VWA leverages the local window attention (LWA) and disentangles LWA into the query window and context window, allowing the context's scale to vary for the query to learn representations at multiple scales.
VN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting
Sparse meteorological forecasting is indispensable for fine-grained weather forecasting and deserves extensive attention.
Selective-Memory Meta-Learning with Environment Representations for Sound Event Localization and Detection
In addition, we introduce environment representations to characterize different acoustic settings, enhancing the adaptability of our attenuation approach to various environments.
META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection
For learning-based sound event localization and detection (SELD) methods, different acoustic environments in the training and test sets may result in large performance differences in the validation and evaluation stages.
Ariadne's Thread:Using Text Prompts to Improve Segmentation of Infected Areas from Chest X-ray images
Segmentation of the infected areas of the lung is essential for quantifying the severity of lung disease like pulmonary infections.
Doubly Robust Self-Training
Self-training is an important technique for solving semi-supervised learning problems.
PaRK-Detect: Towards Efficient Multi-Task Satellite Imagery Road Extraction via Patch-Wise Keypoints Detection
In this paper, we propose a new scheme for multi-task satellite imagery road extraction, Patch-wise Road Keypoints Detection (PaRK-Detect).
Weather2K: A Multivariate Spatio-Temporal Benchmark Dataset for Meteorological Forecasting Based on Real-Time Observation Data from Ground Weather Stations
To the best of our knowledge, our Weather2K is the first attempt to tackle weather forecasting task by taking full advantage of the strengths of observation data from ground weather stations.
Zero-shot Clarifying Question Generation for Conversational Search
In this work, we innovatively explore generating clarifying questions in a zero-shot setting to overcome the cold start problem and we propose a constrained clarifying question generation system which uses both question templates and query facets to guide the effective and precise question generation.
SwiftAvatar: Efficient Auto-Creation of Parameterized Stylized Character on Arbitrary Avatar Engines
To this end, we propose SwiftAvatar, a novel avatar auto-creation framework that is evidently superior to previous works.
Pre-trained Language Models Can be Fully Zero-Shot Learners
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data?
Privileged Prior Information Distillation for Image Matting
Performance of trimap-free image matting methods is limited when trying to decouple the deterministic and undetermined regions, especially in the scenes where foregrounds are semantically ambiguous, chromaless, or high transmittance.
Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains
Our system submitted to the DCASE 2022 Task 3 is based on our previous proposed Event-Independent Network V2 (EINV2) with a novel data augmentation method.
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
How to learn highly compact yet effective sentence representation?
Lawin Transformer: Improving Semantic Segmentation Transformer with Multi-Scale Representations via Large Window Attention
In this paper, we succeed in introducing multi-scale representations into semantic segmentation ViT via window attention mechanism and further improves the performance and efficiency.
Ranked #14 on
Semantic Segmentation
on DADA-seg
SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution
However, existing methods mostly train the DNNs on uniformly sampled LR-HR patch pairs, which makes them fail to fully exploit informative patches within the image.
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Internet video delivery has undergone a tremendous explosion of growth over the past few years.
ConTNet: Why not use convolution and transformer at the same time?
It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.
Adaptive Self-training for Neural Sequence Labeling with Few Labels
Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing.
Contextual Graph Reasoning Networks
Graph Reasoning has shown great potential recently in modeling long-range dependencies, which are crucial for various computer vision tasks.
Adaptive Self-training for Few-shot Neural Sequence Labeling
While self-training serves as an effective mechanism to learn from large amounts of unlabeled data -- meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
GINet: Graph Interaction Network for Scene Parsing
GI unit is further improved by the SC-loss to enhance the semantic representations over the exemplar-based semantic graph.
FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images
To further promote the research of ship detection, we introduced a new fine-grained ship detection datasets, which is named as FGSD.
The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification
The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component.
Ranked #32 on
Fine-Grained Image Classification
on FGVC Aircraft
C-DLinkNet: considering multi-level semantic features for human parsing
Human parsing is an essential branch of semantic segmentation, which is a fine-grained semantic segmentation task to identify the constituent parts of human.
Learning Feature Interactions with Lorentzian Factorization Machine
Learning representations for feature interactions to model user behaviors is critical for recommendation system and click-trough rate (CTR) predictions.
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
Road extraction is a fundamental task in the field of remote sensing which has been a hot research topic in the past decade.
Ranked #2 on
Road Segmentation
on DeepGlobe
(IoU metric)
Towards Efficient Large-Scale Graph Neural Network Computing
This evolution has led to large graph-based irregular and sparse models that go beyond what existing deep learning frameworks are designed for.
RPC Considered Harmful: Fast Distributed Deep Learning on RDMA
Its computation is typically characterized by a simple tensor data abstraction to model multi-dimensional matrices, a data-flow graph to model computation, and iterative executions with relatively frequent synchronizations, thereby making it substantially different from Map/Reduce style distributed big data computation.
