4 papers
ToolExpander: Extending the Frontiers of Tool-Using Reinforcement Learning to Weak LLMs
Fu Chen, Peng Wang, Xiyin Li +3
Training Large Language Models (LLMs) with Group Relative Policy Optimization (GRPO) encounters a significant challenge: models often fail to produce accurate responses, particular…
Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
Nguyen Lan Vi Vu, Thanh-Huy Nguyen, Thien Nguyen +4
Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-l…
Describe Anything Model for Visual Question Answering on Text-rich Images
Yen-Linh Vu, Dinh-Thang Duong, Truong-Binh Duong +8
Recent progress has been made in region-aware vision-language modeling, particularly with the emergence of the Describe Anything Model (DAM). DAM is capable of generating detailed…
Vox-UDA: Voxel-wise Unsupervised Domain Adaptation for Cryo-Electron Subtomogram Segmentation with Denoised Pseudo Labeling
Haoran Li, Xingjian Li, Jiahua Shi +6
Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology facilitating the study of macromolecular structures at near-atomic resolution. Recent volumetric segmentation approach…