Search Results for author:
Found 25 papers, 5 papers with code
BIT’s system for AutoSimulTrans2021
In this paper we introduce our Chinese-English simultaneous translation system participating in AutoSimulTrans2021.
Kaiwu: A Multimodal Manipulation Dataset and Framework for Robot Learning and Human-Robot Interaction
Cutting-edge robot learning techniques including foundation models and imitation learning from humans all pose huge demands on large-scale and high-quality datasets which constitute one of the bottleneck in the general intelligent robot fields.
Efficient AI in Practice: Training and Deployment of Efficient LLMs for Industry Applications
Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendations to generative tasks.
AIArena: A Blockchain-Based Decentralized AI Training Platform
The rapid advancement of AI has underscored critical challenges in its development and implementation, largely due to centralized control by a few major corporations.
SoK: Decentralized AI (DeAI)
The centralization of Artificial Intelligence (AI) poses significant challenges, including single points of failure, inherent biases, data privacy concerns, and scalability issues.
Multi-Continental Healthcare Modelling Using Blockchain-Enabled Federated Learning
One of the biggest challenges of building artificial intelligence (AI) model in healthcare area is the data sharing.
Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs
Safety limitations in service robotics across various industries have raised significant concerns about the need for robust mechanisms ensuring that robots adhere to safe practices, thereby preventing actions that might harm humans or cause property damage.
PE-MVCNet: Multi-view and Cross-modal Fusion Network for Pulmonary Embolism Prediction
In a clinical setting, physicians tend to rely on the contextual information provided by Electronic Medical Records (EMR) to interpret medical imaging.
Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studies
Causal emergence theory aims to bridge these two concepts and even employs measures of causality to quantify emergence.
Market Misconduct in Decentralized Finance (DeFi): Analysis, Regulatory Challenges and Policy Implications
The rise of blockchain and Decentralized Finance (DeFi) underscores this intertwined evolution of technology and finance.
Leverage Staking with Liquid Staking Derivatives (LSDs): Opportunities and Risks
In the Proof of Stake (PoS) Ethereum ecosystem, users can stake ETH on Lido to receive stETH, a Liquid Staking Derivative (LSD) that represents staked ETH and accrues staking rewards.
An Approach for Multi-Object Tracking with Two-Stage Min-Cost Flow
Specifically, we employ the minimum network flow algorithm with high-confidence detections as input in the first stage to obtain the candidate tracklets that need correction.
Synthetic IMU Datasets and Protocols Can Simplify Fall Detection Experiments and Optimize Sensor Configuration
The proposed method simplifies fall detection data acquisition experiments, provides novel venue for generating low cost synthetic data in scenario where acquiring data for machine learning is challenging and paves the way for customizing machine learning configurations.
SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection
We find that substructure differences commonly exist between ID and OOD graphs, and design SGOOD with a series of techniques to encode task-agnostic substructures for effective OOD detection.
zkFL: Zero-Knowledge Proof-based Gradient Aggregation for Federated Learning
Federated learning (FL) is a machine learning paradigm, which enables multiple and decentralized clients to collaboratively train a model under the orchestration of a central aggregator.
Finding emergence in data by maximizing effective information
Quantifying emergence and modeling emergent dynamics in a data-driven manner for complex dynamical systems is challenging due to the lack of direct observations at the micro-level.
Defending Against Poisoning Attacks in Federated Learning with Blockchain
In the era of deep learning, federated learning (FL) presents a promising approach that allows multi-institutional data owners, or clients, to collaboratively train machine learning models without compromising data privacy.
Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning
We evaluate our method both in closed-loop simulation and real world driving, and demonstrate the neural network planner has outstanding performance in complex urban autonomous driving scenarios.
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain
Federated learning (FL) is a promising way to allow multiple data owners (clients) to collaboratively train machine learning models without compromising data privacy.
Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval
Most existing methods regard ZS-SBIR as a traditional classification problem and employ a cross-entropy or triplet-based loss to achieve retrieval, which neglect the problems of the domain gap between sketches and natural images and the large intra-class diversity in sketches.
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
Dynamic Fusion based Federated Learning for COVID-19 Detection
To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections.
Nonparametric Density Estimation for High-Dimensional Data - Algorithms and Applications
Density Estimation is widely adopted in the domain of unsupervised learning especially for the application of clustering.
Scale Aggregation Network for Accurate and Efficient Crowd Counting
In this paper, we propose a novel encoder-decoder network, called extit{Scale Aggregation Network (SANet)}, for accurate and efficient crowd counting.
Ranked #6 on
Crowd Counting
on WorldExpo’10
Reinforcement Learning applied to Single Neuron
In summary, we took the initial endeavor to study the reinforcement learning for multi-agents system.
