GitHub

Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

For a minimal example of how to use the environment framework, refer to examples/simple-calculator. For the environment and training data used in our paper, see AgentBench FC. For reproducing the ...
IEEE

SegCR: A Multimodal and Multitask Complementary Fusion Network for Remote Sensing Semantic Segmentation and Cloud Removal

Abstract: The synthetic aperture radar (SAR) can provide complementary information to optical images due to its insensitivity to atmospheric conditions, making optical–SAR fusion semantic segmentation ...
Scientific Research Publishing

Ndiaye, J., Sow, O., Diallo, O., Faye, A.S., Traore, Y., Diop, M.A., et al. (2023) Development of an Intelligent Queue Manager That Takes Account of the Social and Health ...

ABSTRACT: Academic institutions in Senegal, focused on social relations, knowledge transfer, and research, must now modernize in the face of health risks, theological developments, economic and social ...
IEEE

Multitask Hybrid Knowledge Distillation for Unsupervised Anomaly Detection

Abstract: Detecting both logical and structural anomalies in an unsupervised anomaly detection task is a significant challenge due to the inherent differences between the two types of anomalies. The ...