Publications (5)
QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining
Fengze Liu, Weidong Zhou, Binbin Liu +8
Quality and diversity are two critical metrics for the training data of large language models (LLMs), positively impacting performance. Existing studies often optimize these metric…
Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images
Tiancheng Lin, Zhimiao Yu, Hongyu Hu +2
Multi-instance learning (MIL) is an effective paradigm for whole-slide pathological images (WSIs) classification to handle the gigapixel resolution and slide-level label. Prevailin…
Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE
Yangming Shi, Shixiang Zhu, Tao Shen +14
We present Mamoda2.5, a unified AR-Diffusion framework that seamlessly integrates multimodal understanding and generation within a single architecture. To efficiently enhance the m…
SLPD: Slide-level Prototypical Distillation for WSIs
Zhimiao Yu, Tiancheng Lin, Yi Xu
Improving the feature representation ability is the foundation of many whole slide pathological image (WSIs) tasks. Recent works have achieved great success in pathological-specifi…
Background Clustering Pre-training for Few-shot Segmentation
Zhimiao Yu, Tiancheng Lin, Yi Xu
Recent few-shot segmentation (FSS) methods introduce an extra pre-training stage before meta-training to obtain a stronger backbone, which has become a standard step in few-shot le…