4 citations · 6 across the 5 of their papers we have counts for
5 papers
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Contrastive Centroid Supervision Alleviates Domain Shift in Medical Image Classification
Wenshuo Zhou, Dalu Yang, Binghong Wu +6
Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world…
Progressive Hard-case Mining across Pyramid Levels for Object Detection
Binghong Wu, Yehui Yang, Dalu Yang +5
In object detection, multi-level prediction (e.g., FPN) and reweighting skills (e.g., focal loss) have drastically improved one-stage detector performance. However, the synergy bet…
Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
Yehui Yang, Fangxin Shang, Binghong Wu +5
Diabetic retinopathy (DR) grading from fundus images has attracted increasing interest in both academic and industrial communities. Most convolutional neural network (CNN) based al…
Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening
Dalu Yang, Yehui Yang, Tiantian Huang +3
There are extensive researches focusing on automated diabetic reti-nopathy (DR) detection from fundus images. However, the accuracy drop is ob-served when applying these models in…